The Real Reason Robots Shouldn’t Look Like Humans | Documentary

The robots of the future will be soft, flexible, and diverse in shape, making them safer and more capable than traditional metallic humanoids.

When people think about robots, they usually imagine something like a Boston Dynamics robot, metallic and humanoid. But the robots we'll see in the future might not look like that at all. If humans are interacting with something on a daily basis, it's probably best not to make it sharp, delicate, and heavy. Instead, advanced robots might be made safer if they're soft, flexible, and come in all kinds of shapes and sizes. So instead of Sonny from I, Robot, something like Baymax from "Big Hero 6" might be closer to what's in our future.

This is a compilation video of five of my videos on the surprisingly different ways robots can look, and why we build them that way. This is my first time trying out a series, and honestly, it's been a busy time for the Veritasium team. We're working on some exciting things in the background. But in the meantime, we wanted to put this together for all of you. I also caught up with Dr. Elliot Hawkes, the scientist behind two of these robots, to get an update on how they're progressing and when we can expect to see them in our lives.

Are there more developments happening with the jumping robots? Dr. Hawkes responded, "We have a whole nother project on jumping, and it doesn't even use springs. So I won't give away our secrets yet. But keep an eye out for that one too, 'cause that's gonna be fun." He confirmed that they have another jumping robot with a totally novel design, and he believes it's going to be better than the one they had before.

Non-humanoid robots aren't just safer for us to interact with. One of their biggest advantages over traditional robots is that they don't just do things humans already do, but better. Instead, they're specialized to master entirely new abilities, often ones that no human can tackle. For instance, there is a robot that can grow to hundreds of times its size, and it can't be stopped by adhesives or spikes. Although it looks kind of simple and cheap, it has dozens of potential applications, including one day maybe saving your life.

These robots can be made out of almost any material, but they all follow the same basic principle. Powered by compressed air, they grow from the tip. This allows the robot to pass through tight spaces and also over sticky surfaces. For example, something like a car will get stuck to adhesives in the wheels. But if you do the same thing with the vine robot, the robot is able to extend. It can navigate curvy and twisted passageways effortlessly, which suggests some of the applications it's well suited for.

=> 00:03:36

Even if an inflatable robot gets punctured, it can keep going with enough air pressure.

The inflatable robot is well-suited for various applications. Now, you might think spikes would be the downfall of an inflatable robot. However, even if it's punctured, as long as you have sufficient air pressure, the robot keeps going. In fact, you might be able to hear it leaking now, so I'll have to turn up the pressure. This by itself is not yet a robot. But once we add steering, a camera, some sensors, and maybe some intelligence as to where we're directing it, then we could say it's a robot. This is sort of the backbone of a robot. This is what allows us to build our type of robots.

The idea for this device came from a vine in my office that was on a shelf, kind of out of the sunlight. Over the course of a year or so, it slowly grew out this tendril, out and around the edge of the shelf towards the sunlight. I thought that was a pretty cool thing it just did. So, I started thinking, well, is there a way you could do that robotically?

The solution is really elegant in its simplicity. Just take some airtight tubing and fold it in on itself. It's kinda like a water wiggly, those toys that are really hard to hold. When you inflate it with compressed air, it starts growing out from the tip. If you want the tube to always bend at a certain spot, you could just tape the tubing on the outside to shorten one of the sides. For example, you could tape it into a helical shape to create a deployable antenna.

Retracting the tube is a challenging problem. When you're in a constrained environment, all you really have to do is pull on what we call the tail, the material that is passing through the core of the body. You pull on it, and it basically outgrows, just going back inside itself. However, if you're in a big open area and you try pulling on that, instead of inverting or retracting, it tends to coil up and make an ugly shape. The engineers have come up with ways to retract the tube to prevent it from buckling using internal rollers.

The tube doesn't have to be the same diameter the whole way along. Here, there's actually a much wider section. Think of it like a pillow that's packed into the end of the robot. If you sit cross-legged on it, it grows underneath the table just as usual, and then, as the pillow part starts inflating, it can actually lift you up. My balance is not great, as we can see. Try standing on it. What's amazing is that this doesn't require much pressure above atmospheric. Just a tenth of an atmosphere applied over a large area, like a square meter, can lift something as heavy as a thousand kilograms, all the while remaining soft.

=> 00:06:37

Soft robots can navigate tight spaces and lift heavy objects, making them perfect for search and rescue missions.

The force applied with low pressure can be significant as long as the area is large enough. For instance, the pillow mentioned has an area of 600 square inches. With just one PSI, it can exert 600 pounds of force. At two PSI, it can exert 1,200 pounds. Despite this, it feels really soft because of the low PSI. It's important that the device remains soft to avoid causing harm.

These devices can be designed with a cross-section that changes along their length. This allows a small body to grow into, for example, a collapsed building and potentially lift a large object off someone who is trapped, or in a car crash. They can apply huge forces using very soft, lightweight, and cheap materials. These robots can also be deployed in search and rescue operations by attaching sensors like a camera onto the front. They are hard to stop and can navigate through cluttered environments like collapsed buildings. Due to their low cost, many can be deployed simultaneously, increasing the chances of finding someone.

To keep a camera connected to the front of the robot as it grows, one method is to use an end cap that allows the camera to stay on the front, pushed from behind by the robot. Another method involves a tiny wireless camera mounted on an external frame that interlocks with an internal frame inside the pressurized part of the robot body. This mechanism prevents the camera from falling off as the robot grows, similar to how a roller coaster's wheels go around the track.

The vine robot can be actively steered by attaching artificial muscles to it. These muscles work by inflating and expanding sideways, which causes them to contract in length. However, instead of these somewhat stiff muscles, they now use tubes of ripstop nylon fabric with the braid oriented at 45 degrees. This fabric forms the main robot body, with three pneumatic muscles connected to it. Each muscle is connected to its own air supply and regulators. As the robot extends from the tip, it can be steered by shortening and lengthening the sides, similar to how tendons in an arm move a hand.

=> 00:09:27

Our vine robot can navigate tight spaces, withstand sharp objects, and explore ancient tunnels or assist in medical intubation with ease.

Our vine robot is equipped with muscles along its side. As these muscles inflate, they turn the robot one way, and inflating the muscle on the other side turns it the other way. The vine robot can fit through tight spaces, it doesn't typically get stuck on anything, and isn't bothered by sharp objects. Once a camera is attached to the front, it's ideal for applications like archeology. The robot was actually taken to Peru to investigate some very narrow shafts.

We were examining an archeological site in the Andes Mountains of Peru, built between 1,500 and 500 BC. This ancient temple had numerous underground spaces. The archeologists were trying to understand the purpose of these spaces and what the people who built them intended to do with them. There were giant rooms called galleries and small ducts or tunnels branching off from these rooms. The ducts were too small for a person to enter. We successfully used the vine robot to explore three tunnels that couldn't have been seen through other means, which was super exciting. We captured video inside the entire tunnels and provided it to the archeology team.

Intubation is the process of putting a tube into a patient to breathe for them when they aren't breathing. Traditionally, a highly-trained medical professional uses a laryngoscope to locate the trachea and then passes a tube inside. This process can take a couple of minutes and requires significant effort. In emergencies, every second counts. By using a miniature version of the vine robot, researchers hope to make intubation faster and safer. Even someone with no training could insert this device, aim towards the nose, and intubate with just a little bit of pressurization.

=> 00:12:41

Vine robots, inspired by plants, can navigate complex environments and have potential applications from medical procedures to space exploration.

The vine robot essentially finds the opening, showcasing a neat example of passive intelligence or mechanical intelligence. This technology allows the robot to find its path even if the exact shape is unknown beforehand. While this has not been tested on a real person, it has been successfully demonstrated in a cadaver lab, moving from an idealized version to an actual in vivo situation to successfully intubate a patient.

Another intriguing application is burrowing into sand or soil. By blowing compressed air into materials like sand, it fluidizes and becomes like a liquid, allowing the vine robot to grow into granular materials. This concept is similar to trying to stick an umbrella pole into the ground at the beach, which is difficult without fluidization. When air is turned on, the sand loosens up, reducing the force and allowing the robot to make its way through by tip extension.

This technology makes vine robots an attractive option for NASA to study the surfaces of other planets. For instance, during the Mars InSight mission, a burrowing robot got stuck due to the cohesive material it encountered. The advantage of the vine robot's tip extension is that it can extend its way down without relying on the interaction with the surrounding material, unlike the Mars probe that failed due to insufficient friction.

What is fascinating about vine robots is how a plant inspired this simple yet elegant design. The basic design is so straightforward that one could build a vine robot in as little as a minute, with instructions available online. From this basic design, a variety of robots have emerged with applications ranging from archeology and search and rescue to intubation and space exploration.

=> 00:15:49

Innovative vine robots could clear landmines, seal spacecraft, and even save lives in emergency medical situations.

We love to hear your ideas, especially about crazy ideas that we hadn't thought of. So keep 'em coming. One idea that stood out was for clearing landmines. The concept involved running a vine robot through the field to detonate the landmines, creating a safe path for civilians. I thought that was a really cool idea. The plan was to put explosives in the vine to detonate the landmines themselves. Additionally, you could enhance this by adding metal detector sensors to the vine robot to identify where the mines are.

Another fascinating idea was for space applications of docking. When two spacecraft dock together, they need to make an airtight seal. The idea was to use a vine robot to achieve this. You can imagine two tubes coming together, not sealed, and then the vine robot growing through to make the seal.

Regarding updates on the vine robot, we recently conducted a trial with emergency medical practitioners using our device. After just five minutes of training, they were about 90% successful in intubating within a rapid 20 seconds. The advantage of our device is its speed; if it fails, it does so quickly, allowing for another attempt without significant time loss. This rapid and easy process is crucial, especially in pre-hospital settings where conditions are less controlled than in an operating room.

=> 00:18:47

Defibrillators could save more lives if they helped with breathing too.

Defibrillators are becoming ubiquitous, but one issue remains: there's no way to help the person breathe. Possibly, if we can make this thing so simple, it could be packaged with an AED, allowing you to both get the heart going and intubate to get oxygen in. I think we're close; it's pretty easy. You'll have to come back for another video where we'll let you intubate a cadaver. That'll be fun.

We've kind of answered this question, but are these robots, vine robots, still being worked on? We have a project right now on anchoring, which we're especially interested in. If you think of a plant root, pulling out a small shrub is incredibly hard despite its small stem. One of the coolest things is that a hundred pounds of anchoring force was created with almost no initial reaction force. There was a seed that slowly grew down into the ground. It's like all these little tendrils, and the friction sums over all of those.

When you're trying to go into the soil, the thing resisting you is the surface area of the tip. What's giving you the anchoring force is the surface area on the sides. If you clump them together, the area in the tips doesn't change, but the surface area of the sides goes down. You basically want to split them up into as many as practically possible. We're using that concept now to make these anchors and are working with NASA on one as well. It's a deployable anchor, very light, which you could throw or drop, and then the roots grow down. There are four roots that grow into the ground, and it takes something like a hundred Newtons of force to pull it out.

It sounds like a very sci-fi type thing, where you could throw the root pack down, and then the roots grow out, locking the anchor in. Absolutely, absolutely.

After seeing the unstoppable robot, we returned to Elliot's lab a few years later to see a robot that has conquered a totally different specialty: the art of jumping. This tiny robot weighs less than a tennis ball and can jump higher than anything in the world. In the competitive world of jumping robots, the previous record was 3.7 meters, enough to leap a single-story building. This jumper can reach 31 meters, higher than a 10-story building. It could jump all the way from the Statue of Liberty's feet up to eye level.

=> 00:21:52

Jump higher by maximizing muscle strength, just like the bush baby with 30% of its muscle mass dedicated to jumping.

In the realm of physics, no mass can be lost. This principle means that rockets constantly ejecting burnt fuel are not considered to be jumping, and neither is an arrow launched from a bow. For an action to count as a jump, the bow would have to accompany the arrow. Many animals, ranging from sand fleas to grasshoppers to kangaroos, exhibit the ability to jump. They launch their bodies into the air with a single stroke of their muscles. The amount of energy delivered in that single stroke determines the jump height. To jump higher, one must maximize the strength of the muscle.

The best jumper in the animal kingdom is the galago, or bush baby, which dedicates 30% of its entire muscle mass to jumping. This allows the squirrel-sized primate to jump over two meters from a standstill. It has very small arms and upper body but possesses huge jumping legs. The galago doesn't have better muscles; it simply has more of them.

There are also some clever jumping toys. For instance, poppers store energy in their deformed shape, effectively becoming a spring. When released, they apply a large force to the ground, launching themselves into the air. All elastic jumpers follow the same principle of storing energy in a spring and releasing that energy in a single stroke to jump. However, none of the jumping toys could compare to a tiny robot designed for jumping. This robot is particularly challenging to film because it is so small, accelerates rapidly, and travels a huge distance on each jump. Each takeoff happens faster than one can register.

Engineered jumpers could be perfect for exploring other worlds, particularly where the atmosphere is thin or non-existent. On the moon, with one-sixth the gravity of Earth, this robot could leap 125 meters high and half a kilometer forward. While rovers may struggle with steep cliffs and deep craters, jumpers could hop in and out, fetching samples to bring back to the rover. Additionally, jumping conserves energy. If kinetic energy could be stored back in the spring upon landing, the efficiency could be near perfect. The team has already started building an entire fleet of jumping robots. Some can right themselves after landing to take off again immediately, while others are steerable with three adjustable legs that allow the jumper to launch in any direction.

=> 00:25:22

This robot jumper stores energy gradually to achieve record-breaking heights with incredible efficiency.

The mechanism is connected to the bottom of the robot. When the motor is turned on, it winds up the string, compressing the robot and storing energy in the carbon fiber and rubber bands. After about a minute and a half, the structure reaches maximum compression. To know when to put it down, you wait until the bottom sticks inward and it can stand up; otherwise, it would roll over. As soon as it can stand, you can put it down.

At this point, a trigger releases the latch holding the string on the axle, causing all the string to unspool at once and releasing the energy stored in the spring. The jumper goes from a standstill to over a hundred kilometers an hour in only nine milliseconds, giving an acceleration of over 300 Gs, which would be enough to kill basically any living creature.

The jumper's exceptional performance is due to three special design features. First, it is incredibly light, weighing just 30 grams, achieved by employing a tiny motor and battery. Its entire structure, made of lightweight carbon fiber and rubber, doubles as the spring. Natural latex rubber can store more energy per unit mass than nearly any other elastic material, at 7,000 joules per kilogram. The design of the spring is also ideal for its purpose. Initially, they tried using only rubber bands connected to hinged aluminum rods, but this design had a force profile that peaked and then decreased during compression. Another design using only carbon fiber slats required a lot of initial force, which then increased linearly. The ultimate design is a hybrid of these two approaches, providing a nearly flat force profile over the entire range of compression, thus doubling the energy storage of a typical spring.

However, there are occasional issues, such as the string snapping or not releasing when supposed to, requiring restringing. Despite these challenges, the design is highly efficient. Adding weight to the jumper can also improve its performance. By adding a chunk of steel to the top, the jumper can achieve higher jumps. This is because the body, the part that's moving, should weigh at least as much as the foot for efficient energy transfer. => 00:28:38

Engineered jumpers achieve incredible heights by storing energy over time, unlike biological jumpers that rely on a single muscle stroke.

The real secret to how this jumper can achieve such heights is through something the researchers call work multiplication. Unlike an animal, which can only jump using a single stroke of its muscle, an engineered jumper can store up the energy from many strokes, or in this case, many revolutions of its motor. This is how the motor can be so small; it doesn't have to deliver the energy all at once but builds it up gradually over a few minutes. The trade-off is kind of like time for energy.

This is possible because there is a latch under tension preventing the spring from unspooling until the robot is fully compressed. Interestingly, biological organisms do use latches. For example, the sand flea, which can jump incredibly high for its body size, has a muscle that is attached inside of the pivot point. As it contracts that muscle, the leg doesn't extend but closes more. Then, a second muscle pulls it out, shifting the muscle slightly outside the pivot point, creating a torque reversal mechanism that allows it to shoot.

Even though the biological world has latches, no organism has developed work multiplication for a jump from standstill, at least not internally. Spider monkeys have been observed pulling back a branch hand over hand using multiple muscle strokes stored in the bend of the branch to catapult themselves forward. Similarly, a spider called the slingshot spider shoots out a silky string, which they pull back multiple times to slingshot themselves to another location.

I tried jumping in moon boots to see if they would help me go higher. It certainly felt like they did, but Elliot pointed out that from a standing start, they don't actually help much. Only if you jump a few times before can you store up some of the previous jumps' energy in the elastic bands, and then that energy helps launch you higher on the following jump.

For years, engineered jumping was developed to mimic biological jumping. But with work multiplication, it gained an advantage. If you can generate a large burst of energy simply by running a motor for a long time, the power of the motor is no longer the limiting factor; the spring is. So, you can focus on making the most powerful spring possible. This jumper has nearly maximized the achievable height with this spring. Assuming an infinitely light motor with infinite time to wind up, the highest possible jump with this compression spring is only around 19% higher than what they've achieved.

=> 00:31:48

Scaling up a jumper robot by 10 times can lead to record-breaking jumps due to increased inertia overcoming air drag.

Another way to send the jumper higher is to make it 10 times isometrically larger, leading to a 15 to 20% higher jump. We are currently in an intermediate scale where we still experience air drag, but it’s not as severe as it is for a flea. If we scaled the jumper up 10 times, we could actually avoid air drag completely. This works because if the jumper is scaled up 10 times on all sides, the cross-sectional area increases by a hundred, which increases the drag force, but the jumper's mass increases by a thousand. This results in much more inertia, meaning the drag force affects it less.

The entire concept of work multiplication could bring robots to the next level. Currently, motors and robots have to be relatively small to remain portable. However, the simple principle of building up the energy from multiple turns of a motor over time would allow robots to store and then release huge amounts of energy, potentially setting some world records in the process. When we visited you, we were looking at 110 feet, which was the record holder. My question is, is that still the record as far as you know?

• It is. I also challenge all the viewers to beat it because it is beatable. I hope someone in the next few years will beat it, and if not, we'll beat our own record because it's beatable. I will say that much.

Are there more developments happening with the jumping robots?

• We have a whole other project on jumping, which we also think will beat the current record, and it doesn’t even use a spring. I won't give away our secrets yet, but keep an eye out for that one too, because that's going to be fun.

So you have another jumping robot with a totally novel design?

• Yep.

And you think it's going to be better than the one you had before?

• Correct.

Wow, that's extreme. And in terms of making these things applicable?

• Yes, we have a project with NASA. Our work with NASA moves pretty slowly because they prioritize reliability. If they’re going to send it to the moon, it can't mess up. So, that's a slow-going process, but the goal is still to get it to the moon.

It would be like the next Mars helicopter or something.

• I think that's a really good analogy. The Mars helicopter has been doing awesome, acting as a scout that can get nice views of where the rover might need to go or maybe gather some samples. You can't have a helicopter on the moon, but you can jump. We believe we can achieve similar performance in terms of height and other metrics with jumping on the moon compared to the helicopter. So, yes, that's a great analogy.

Are there any interesting emails that came about from the jumping robot video?

=> 00:34:46

Years of failure can lead to groundbreaking success.

In engineering, safety factors are crucial, but in our project, we had none, meaning everything was near its failure limit, making the task incredibly challenging. Currently, we are working on a tutorial to build a robot that can jump 20 or 30 feet. This will be a fun way for people to build one themselves and try it out. However, if you push the limits, wear safety glasses and gloves due to the risk of carbon fiber shards.

When asked about the biggest lesson learned from building the jumping robot, it was clear how many things can go wrong when creating something innovative. This project involved years of repeated failures before achieving success. Despite suggestions to model or simulate the springs beforehand, we did incorporate modeling and simulation. The challenge was the numerous configurations we tried, from ball shapes to stick-like robots with rubber bands, making it a complex search over a vast space with various trade-offs.

The jumper robot can achieve such heights because it is constructed from rubber and carbon fiber, with a tiny body and massive legs, designed for one physical purpose. Specialization in robots is common in academic research to isolate and understand specific abilities, which may later be integrated into more complex robots. Unlike the humanoid robots from Boston Dynamics, our focus is on mechanical design rather than controls, vision, or AI. This preference stems from my personal joy in mechanical design.

When asked about a favorite robot, I can't choose among them, as it's like picking amongst children. However, the jumper robot stands out due to the extensive learning from failures and the satisfaction of finally getting it to work.

=> 00:38:01

From a simple email to a groundbreaking collaboration, the power of persistence and attention to detail can lead to incredible achievements.

And so, when we finally got that one working, I think that was really satisfying. From your perspective, how did our collaboration come to be in the first place? Oh, wow. Okay. That's a fun story. So you sent me an email, I don't know how many years ago, maybe five years ago, something like this, and I ignored it. And I went into the lab one day, I just mentioned to my student, I was like, oh, some guy emailed about making a video. And he is like, "Yeah, who was it? Maybe I could help out or something." So I forwarded it to him, he's like, "Do you know who this is?" So then we responded. And we appreciated the effort you put in to the details in getting the story right. I forget how long we had this call. I had this call with Emily, it was maybe four hours or something. We went through the details of jumping theory. 'Cause she wanted to get everything just right for that jumping video. As an academic, we care about that stuff and we want it to be right.

But the most specialized, perfected match between a robot's build and its abilities comes from one competition that's been refining this for nearly 50 years. Micromouse is the oldest robotics competition in the world. It's like the Formula 1 of robotics, but you have to see their speed to believe it. This tiny robot mouse can finish this maze in just six seconds. Every year around the world, people compete in the oldest robotics race. The goal is simple: get to the end of the maze as fast as possible. The person who came second lost by 20 milliseconds. But competition has grown fierce. When somebody saw my design, they said, you're crazy. Why is there so much tension? What's riding on it? Honor? Honor.

In 1952, mathematician Claude Shannon constructed an electronic mouse named Theseus that could solve a maze. The trick to making the mouse intelligent was hidden in a computer built into the maze itself, made of telephone relay switches. The mouse was just a magnet on wheels essentially, following an electromagnet controlled by the position of the relay switches. He is now exploring the maze using a rather involved strategy of trial and error. As he finds the correct path, he registers the information in his memory. Later, I can put him down in any part of the maze that he's already explored and he'll be able to go directly to the goal without making a single false turn. Theseus is often referred to as one of the first examples of machine learning. A director at Google recently said that it inspired the whole field of AI.

=> 00:41:14

From a simple rumor to a global phenomenon, Micromouse competitions prove that innovation thrives on curiosity and competition.

25 years later, editors at the Institute of Electrical and Electronics Engineers, or IEEE, caught wind of a contest for electronic mice, or le mouse electronique, as they had heard. They were ecstatic. Were these the successors Theseus? But something had been lost in translation. These mice were just batteries in cases, not robots capable of intelligent behavior. But the misunderstanding stuck with them, and they wondered, why couldn't we hold that competition ourselves? In 1977, the announcement for IEEE's amazing Micromouse Maze Contest attracted over 6,000 entrants. However, the number of successful competitors dwindled rapidly. Eventually, just 15 entrants reached the finals in 1979. By this point, the contest had garnered enough public interest to be broadcast nationwide on the evening news. And just like the rumor that inspired the competition, Micromouse began to spread across the world.

Even people in the top two or three, you can see them trying to set their mice up, and they can barely find the buttons to press because it's absolutely nerve-wracking. It doesn't matter what it was. It could be horse racing, it could be motor racing, it could be mouse racing. If you have a shred of competitiveness in you, you wanna win, right?

Just like a real mouse, a micromouse has to be fully autonomous, no internet connection, no GPS or remote control, and no nudging it to help it get unstuck. It has to fit all its computing, motors, sensors, and power supply in a frame no longer or wider than 25 centimeters. There isn't a limit on the height of the mouse, but the rules don't allow climbing, flight, or any forms of combustion. So rocket propulsion, for example, is out of the equation. The maze itself is a square about three meters on each side, subdivided by walls into corridors only 18 centimeters across.

In 2009, the half-size Micromouse category was introduced, with mice smaller than 12 and a half centimeters per side, and paths just nine centimeters across. The final layout of the maze is only revealed at the start of each competition, after which competitors are not allowed to change the code in their mice. The big three competitions, all Japan, Taiwan, and USA's APEC, usually limit the time mice get in the maze to seven or 10 minutes, and mice are only allowed five runs from the start to the goal.

So if you spend a lot of time searching, that's a penalty. Makes sense. The strategy for most micromice is to spend their first run carefully learning the maze and looking for the best path to the goal, while not wasting too much time. Then they use their remaining tries to sprint down that path for the fastest runtime possible. Solving a maze may sound simple enough, though it's important to remember that with only a few infrared sensors for eyes, the view from inside the maze is a lot less clear than what we see from above.

=> 00:45:34

Optimism and adaptability lead to success: the flood-fill strategy shows that even when you hit walls, updating your path can still get you to your goal efficiently.

Still, you can solve a maze with your eyes closed. If you just put one hand along one wall, you will eventually reach the end of most common mazes, and that's exactly what some initial Micromouse competitors realized too. After a simple wall-following mouse took home gold in the first finals, the goal of the maze was moved away from the edges and freestanding walls were added, which would leave a simple wall-following mouse searching forever.

Your next instinct might be to run through the maze, taking note of every fork in the road. Whenever you reach a dead end or a loop, you can go back to the last intersection and try a different path. If your last left turn got you nowhere, you'd come back to that intersection and go right instead. You can think of this strategy as the one a headstrong mouse might use, running as deep into the maze as it can and turning back only when it can't go any further. This search strategy, known as depth-first search, will eventually get the mouse to the goal. The problem is, it might not be the shortest route, because the mouse only turns back when it needs to, so it may have missed a shortcut that it never tried.

The sibling to this search algorithm, breadth-first search, would find the shortest path. With this strategy, the mouse runs down one branch of an intersection until it reaches the next one, and then it goes back to check the path it skipped before moving on to the next layer of intersections. So the mouse checks every option it reaches, but all that backtracking means that it's rerunning paths dozens of times. At this point, even searching the whole maze often takes less time. So why not just do that? A meticulous mouse could search all 256 cells of the maze, testing every turn and corner to ensure it has definitely found the shortest path. But searching so thoroughly isn't necessary either.

Instead, the most popular Micromouse strategy is different from all of these techniques. It's a search algorithm known as flood-fill. This mouse's plan is to make optimistic journeys through the maze, so optimistic in fact, that on their first journey their map of the maze doesn't have any walls at all. They simply draw the shortest path to the goal and go. When their optimistic plan inevitably hits a wall that wasn't on their map, they simply mark it down and update their new shortest path to the goal. Running, updating, running, updating, always bee-lining for the goal.

Under the hood of the algorithm, what the micromouse is marking on their map is the distance from every square in the maze to the goal. To travel optimistically, the mouse follows the trail of decreasing numbers down to zero. Whenever they hit a wall, they update the numbers on their map to reflect the new shortest distance to the goal. This strategy of following the numerical path of least resistance gives the flood-fill algorithm its name. The process resembles flooding the maze with water and updating values based on the flow.

=> 00:48:28

Winning isn't just about finding the shortest path; it's about finding the fastest one.

Once the mouse reaches the goal, it can smooth out the path it took and get a solution to the maze. However, it may look back and imagine an even shorter uncharted path it could've taken. The mouse might not be satisfied that it's found the shortest path just yet. While this algorithm isn't guaranteed to find the best path on the first pass, it takes advantage of the fact that micromice need to return to the start to begin their next run. So, if the mouse treats its return as a new journey, it can use the return trip to search the maze as well. Between these two attempts, both optimized to find the shortest path from start to finish, it's extremely likely that the mouse will discover it, and the mouse will have done it efficiently, often leaving irrelevant areas of the maze entirely untouched.

Flood-fill offers both an intelligent and practical way for micromice to find the shortest path through the maze. Once there was a clear strategy to find the shortest path, and once the microcontrollers and sensors required to implement it became common, some people believed Micromouse had run its course. As a paper published in IEEE put it, "At the end of the 1980s, the Micromouse Contest had outlived itself. The problem was solved and did not provide any new challenges."

In the 2017 all-Japan Micromouse competition, both the bronze and silver placing mice found the shortest path to the goal. And once they did, they were able to zip along it as quick as 7.4 seconds. (spectators applauding) But Masakazu Utsunomiya's winning mouse, Red Comet, did something entirely different. This is the shortest path to the goal, the one that everyone took. This is the path that Red Comet took. It's a full five and a half meters longer. That's because micromice aren't actually searching for the shortest path, they're searching for the fastest path, and Red Comet's search algorithm figured out that this path had fewer turns to slow it down. So even though the path was longer, it could end up being faster. So it took that risk. (spectators applauding) It won by 131 milliseconds.

Differing routes at competition are now more common than not, and even just getting to the goal remains difficult, whether due to a mysterious algorithm or a quirk of the physical maze. - [Announcer] On the corner, it's a little bit like a, whoa. - [Derek] Micromice don't always behave as you'd expect. Micromouse is far from solved, because it's not just a software problem or a hardware problem, it's both, it's a robotics problem. Red Comet didn't win because it had a better search algorithm, or because it had faster motors. Its cleverness came from how the brains and body of the mouse interacted together.

So it turns out solving the maze is not the problem, it never was the problem, right? But it's actually about navigation, and it's about going fast. Every year, the robots get smaller, faster, lighter. There is still plenty of innovation left. And there's a small group of devotees in Japan busy building quarter-sized micromouse, which would sit on a quarter. - [Derek] Nearly 50 years on, Micromouse is bigger than ever. (spectators applauding)

=> 00:52:25

Dick Fosbury revolutionized the high jump by thinking outside the box, just like Mitee 3 changed Micromouse competitions with diagonal moves.

Competitions have appeared solved at first glance before. The high jump has been an Olympic sport since 1896, with competitors refining their jumps using variations like the scissor, the western roll, and the straddle over the decades with diminishing returns. However, once foam padding became standard in competition, Dick Fosbury rewrote the sport in 1968 by becoming the first Olympian to jump over the pole backwards. Now, almost every high jumper uses what's known as the Fosbury Flop.

If Micromouse had indeed stopped in the 1980s, the competition would've missed its own Fosbury flops—two innovations that completely changed how micromice ran. After all, a lot can change in a sport where competitors can solder on any upgrade they can imagine. The first Fosbury flop was one of the earliest innovations in Micromouse and had nothing to do with technology. It was simply a way of thinking outside the box, or rather, cutting through the box. Every mouse used to turn corners in a conventional manner, but everything changed with the mouse, Mitee 3.

The Mitee mouse three implemented diagonals for the first time, which turned out to be a much better idea than initially thought. Maze designers often put diagonals into the maze now, making it a frequent benefit. To pull off diagonals, the chassis of the mouse had to be reduced to less than 11 centimeters wide, or just five centimeters for half-size Micromouse. The sensors and software of the mouse had to change too. When running between parallel walls, maintaining an equal distance between left and right infrared readings is sufficient. However, a diagonal requires an entirely new algorithm, one that essentially guides the mouse as if it had blinders on.

Normally, if you're going along the side of a wall, you can see the wall all the time, which helps guide yourself and know when you're getting off course. But in the diagonal situation, you just see these walls coming at you. Veering even a tiny bit off course can be less forgiving than sliding against a wall, making diagonals one of the biggest sources of crashes in competition today. However, in exchange, a jagged path of turns transforms into one narrow straightaway.

These days, nearly every competitive micromouse is designed to take this risk. Cutting diagonals opened up room for even more ideas. Around the same time, mice were applying similar strategies to turning. Instead of stopping and pivoting through two right turns, a mouse could sweep around in a single U-turn motion. Once the possibility of diagonals was added, the total number of possible turns opened up exponentially. The maze was no longer just a grid of square hallways. With so many more options to weigh, figuring out the best path became more complex than ever. But the payoff was dramatic. What was once a series of stops and starts could now be a single fluid snaking motion. How micromice imagined and moved through the maze had changed completely.

=> 00:55:35

Micromice revolutionized maze navigation by using propellers to vacuum themselves to the ground, ensuring speed and control.

Available technology was getting upgrades over the years as well. Tall and unwieldy arms that were used to find walls were replaced by a smaller array of infrared sensors onboard the mouse. Precise stepper motors were traded in for continuous DC motors and encoders.

The DC motors give you more power for less size and weight. So, we were interested in doing that. Then you have to have a servo; you have to actually have feedback on the motor to make it do the right thing. Gyroscopes added an extra sense of orientation, like a compass. They came about because of mobile phones, really. So, the technology provides people with things which weren't there before. All of the turning is done based on the gyro, rather than counting pulses off the wheels, because it's much more reliable.

But even with all the mechanical upgrades, the biggest physical issue for micromice went unaddressed for decades. One thing you'll see almost every competitor holding is a roll of tape. Once you know to look for it, you'll see it everywhere. This tape isn't for repairs or reattaching fallen parts; it's to gather specks of dust off the wheels in between rounds. At the speed and precision these robots are operating, that tiny change in friction is enough to ruin a run.

If you want to turn while driving fast, you need centripetal force to accelerate you into the turn. The faster you're moving, the more force you need to keep you on the track. The only centripetal force for a car turning on flat ground is friction, which is determined by two things: the road pushing up the weight of the car, or the normal force, multiplied by the static coefficient of friction, which is the friction of the interface between the tire and road surface. This is why racetracks have banked turns. The steep angles help cars turn with less friction because part of the normal force itself now points in to contribute to the centripetal force required. If the bank turn is steep enough, cars can actually make the turn without any friction at all. The inward component of the normal force alone is enough to provide the centripetal force required to stay on track.

Micromice are no different, and they don't have banked turns to help. As they got faster and faster, by the early 2000s, their limiting factor was no longer speed but control of that speed. They had to set their center of gravity low and slow down during turns to avoid slipping into a wall or flipping over. But unlike race cars, there wasn't anything in the rules to stop Micromouse competitors from solving this problem by engineering an entirely new mechanism.

Micromouse's second Fosbury flop was almost considered a gimmick when the mouse Mokomo08 first used it in competition. You might be staring at the video to try to see it, but you won't. Instead, it's something you'll hear. That isn't the mouse revving its engines; it's spinning up a propeller. While flying over the walls is against the rules, there's nothing in the rules against a mouse vacuuming itself to the ground to prevent slipping.

=> 00:58:36

Micromouse: A simple maze-solving challenge that turns into an engineering obsession.

The first time a vacuum fan was used in a Micromouse competition, it wasn't something you could see in the video, but rather something you could hear. The sound wasn't the mouse revving its engines; it was the propeller spinning up. While flying over the walls is against the rules, there's nothing in the rules against a mouse vacuuming itself to the ground to prevent slipping.

Dave Otten was the first person I saw put a fan on a mouse. He used a ducted fan and was likely looking at the reaction force, blowing the mouse down. He had a skirt around it, but it wasn't terribly effective. The idea is to let as little air in as possible. Like your vacuum cleaner, when you block it, the motor unloads and speeds up, causing the current to drop. However, if you let too much air in, the current remains very high. These are just quadcopter motors, and they draw a lot of current.

At the scale of Micromouse, a vacuum fan, often built from handheld drone parts, is enough to generate a downward force five times the mouse's weight. That's impressive, considering the car weighs about 130 grams. If you listen closely, you can hear the motors slow down and load up. With that much friction, micromice today can turn corners with a centripetal acceleration approaching 6 Gs, the same as F1 cars. Once nearly everyone equipped fans, the added control allowed builders to push the speed limit on micromice. When allowed to, it can out-accelerate a Tesla Roadster, though not for very far, and they can zip along at up to seven meters per second, faster than most people can run.

Every feature now standard on the modern micromouse was once an experiment, and the next Fosbury flop might not be far off. The first four-wheeled micromouse to win the all-Japan competition did so in 1988, but it took another 22 years of the winning mouse growing and losing appendages before four-wheeled mice became the norm. With micromice still experimenting in six and eight-wheeled designs, omnidirectional movement, and even computer vision, who knows what the next paradigm shift will be.

Your time on the maze actually begins only when you leave the start square, so there's no penalty for the initial time spent. If you want to get started with Micromouse, you don't need to worry about wheel count, vacuum fans, or even diagonals. It is the perfect combination of all the major disciplines needed for robotics, engineering, programming, and embedded systems, all wrapped up in one accessible bundle that you can do in your living room without needing a laboratory. You come along because you're curious, think you can do it, and then you're hooked. If it sucks you in, it turns into quite the journey.

=> 01:02:31

Robots of the future won't be all-purpose humanoids but specialized tools tailored to specific tasks.

At its core, Micromouse is just about a mouse trying to solve a maze. Nearly 50 years later, it's a simple problem that serves as a good reminder that there is no such thing as a simple problem.

A humanoid robot built for all the same tasks a human does sacrifices specialization in any one skill in order to be a generalist. If it performs all tasks semi-well, and these tasks are what humans are already doing, then those robots are just overlapping with us, copying our capacities rather than expanding them. Therefore, robots are perhaps likely to enter our lives not as multipurpose humanoids but rather as precise tools we can pick and choose. Instead of one Swiss army knife robot, you'd end up with something like a personalized toolbox of specialized robots.

Big futuristic questions like how to bring robots into our daily lives require all sorts of practical and creative skills. But perhaps the most important one is actually something that anyone can build: problem solving. If you want to hone your own ability to problem solve, you can get started on that right now, for free, with today's sponsor, Brilliant. Brilliant will make you a better critical thinker while helping you build real skills in everything from technology and programming to math, data science, and whatever you're curious about. On Brilliant, you'll learn through discovery by trying things yourself. You'll not only gain knowledge of key concepts but learn to apply them to real-world situations, all while building your intuition. This gives you the tools to solve whatever problems come your way.

We've been partnering with Brilliant for years, and I still find new things to learn all the time, like this course on how to maximize the value of an electric car. Brilliant has thousands of interactive lessons, and because each one is bite-sized, you can do it in just minutes. So no matter where you are, you can always be building a quicker, sharper mind right on your phone. To try everything Brilliant has to offer for free for 30 days, visit brilliant.org/veritasium, or you can scan this QR code, or click that link down in the description. You'll also get 20% off an annual premium subscription. I want to thank Brilliant for sponsoring this part of the video, and now, let's dive into a surprising trait we're starting to build into robots.

Elliot's vine robot and jumping robot are just two cases where the robots that might save our lives or explore new planets don't look much like traditional robots at all. But soft robots in particular are an entire field of study. So why are so many researchers trying to build the robots of the future with soft materials? For one, trading out fragmented metal frames for single flexible bodies might be how we make robots more reliable and precise.

=> 01:05:14

Flexibility in machines isn't a flaw—it's a game-changer for precision and reliability, even safeguarding nuclear weapons.

For single flexible bodies, the focus might be on how we make robots more reliable and precise. These bendy gear boards are so predictable that they were commissioned by the US government to secure nuclear weapons, ensuring that no random motions could accidentally set them off. But predictability is just one of eight reasons that machines that bend are better.

What do this satellite thruster, plastic tool, and micro mechanical switch have in common? Well, they all contain components that bend, so-called compliant mechanisms. It has always been considered bad to have flexibility in your machines. However, we've tried to take that thing that everybody hates and is trying to avoid and say, how can we use flexibility to our advantage? How can we use that to do cool stuff?

Professor Howell literally wrote the book on compliant mechanisms. It's the most cited book in the field, but he's pretty nonchalant about his work. Just watch how he introduces this mechanism he developed to prevent nuclear weapons from going off accidentally. He mentions, "Actually the safing and arming of nuclear weapons." This is crucial because if there's anything in the world that you want to be safe, it is nuclear weapons, ensuring they do not accidentally go off.

To understand how this device works, we need to delve into why compliant mechanisms are best suited to this task. Probably the first compliant mechanism Professor Howell ever designed was a gripper. This gripper, a compliant mechanism, can exert a really high force. For example, it can break a piece of chalk. When asked what would happen if you put your finger in there and squeezed it, Professor Howell humorously suggests that you would scream in pain, which Derek confirms by trying it himself and finding it incredibly painful, akin to having his finger in a vice.

This gripper looks suspiciously like vice grips but with flexible components where the hinges are. During the visit with Professor Howell, it became clear that compliant mechanisms have several advantages over traditional mechanisms. To remember these advantages, Derek came up with the eight P's of compliant mechanisms.

=> 01:08:05

Compliant mechanisms simplify design by reducing part count, making them cheaper, more durable, and precise.

The first of these is part count. Compliant mechanisms have a reduced part count because they have bendy parts instead of hinges, bearings, and separate springs. This gripper is just a single piece of plastic but achieves a similar result to the much more complicated vice grips. Compliant mechanisms have a reduced part count because they incorporate bendy parts instead of traditional components like hinges, bearings, and separate springs. For instance, this gripper is just a single piece of plastic but achieves a similar result to the much more complicated vice grips. It can amplify force significantly, achieving about 30 to 1, meaning 1 pound of force in results in 30 pounds out. This makes it really inexpensive to produce. While this particular gripper was made in a shop, it could also be injection molded, costing mere cents. Its shape allows for different production processes, such as extrusion and chopping, further lowering the price.

These switches, for example, achieve in one piece of plastic what is normally done with springs, hinges, and many rigid plastic pieces. They also make for a good fidget device. In terms of durability, compliant mechanisms can last a long time; fatigue testing has shown they can go over a million cycles without failure.

In a demonstration, Derek is quizzed on the motion of a dot on an elephant model when pressure is applied. He guesses that the dot will move up and in, but it turns out that the design causes the dot to rotate in space without moving. This mechanism is modeled after those used in wind tunnels, where controlling the angle of a model without displacing it is crucial. This demonstrates that compliant mechanisms can produce very precise motion, which is counterintuitive given their flexible parts. However, they don't suffer from backlash, which occurs in traditional hinges and causes wear and requires lubricant. This is why compliant mechanisms often have better performance than their traditional counterparts.

=> 01:11:02

Compliant mechanisms outperform traditional ones because they eliminate backlash, reduce wear, and don't need lubricants.

Compliant mechanisms offer several advantages over traditional mechanisms, primarily because they don't suffer from backlash. Backlash occurs when a hinge, which is essentially a pin in a hole, moves in one direction and then reverses. This reversal doesn't happen instantaneously due to some give in the hinge, causing wear and requiring lubricant. This is why compliant mechanisms have better performance than their traditional counterparts.

One particularly pleasing example of compliant mechanisms was inspired by work at the microscopic level, where compliant mechanisms were built on chips. These mechanisms had to be made out of silicon, which is as brittle as glass. Designing something like this out of glass is extremely challenging, but once the design was figured out, it could be made from materials like PLA, even though it's not the ideal material for compliant mechanisms. You can find the files to make this yourself on our website, and a link will be provided in the description.

Another advantage of compliant mechanisms is that they can be made with significantly smaller proportions due to production processes like photolithography. This allows for motion at the microscopic level, making them much more portable and lightweight, which is perfect for space applications. For instance, a project with NASA involved making a hinge that could replace bearings for deploying solar panels. This hinge was made from 3D-printed titanium, which can bend plus-minus 90 degrees, achieving a 180-degree deflection.

One particularly impressive example is a titanium device designed for a thruster application with NASA. This device uses two motor inputs to direct a thruster in any direction, all through bending without pinch points for fuel or electrical lines. This single piece of titanium allows for the use of one thruster in place of two, demonstrating the innovative potential of compliant mechanisms.

=> 01:14:21

A single piece of titanium can replace two thrusters by using centripetal force to engage a drum, similar to a chainsaw mechanism.

Here, this single piece of titanium allows you to use one thruster in place of two. Okay, that is a clutch. The idea is, if you spin it up really fast, because it's flexible, this outer part will actually start coming outwards. And then, if there's a drum around it, it'll contact with that drum and spin that thing. Oh, so this like kind of, oh, that kind of comes out like so. Then it gets spinning really fast, and then you essentially engage this outer drum. This is like the way that a chainsaw would work, or something like that, because you get it spinning fast enough and then it engages the chain, and then it turns it over and then, yeah. The centripetal force. Yeah. Wow, that's cool.

So here, this is made in plastic so that you can see it. But in reality, it's gotta be a lot stiffer. So here it is made in steel. What? So hang on, you're saying that that thing, which is made of steel, you spin it up to a certain speed, and then it expands and engages a drum that's around it? Yep, yep. So it'll idle with no motion, but then at a certain speed, what we designed it for, it'll speed up to that RPM. You speed it up and it engage? Yep. I had no idea. Like I have learned something today.

So let's come back to the safing and arming device for nuclear weapons. Its purpose is to ensure that no random vibrations, say, from an earthquake, inadvertently disable safeties and arm the nuclear weapon. Now, one of the requirements was that this device be made as small as possible. They made those as small as they possibly could using traditional methods, even using things like what the Swiss watch manufacturers were using. With compliant mechanisms, they produced a device out of hardened stainless steel where some components were the size of a human hair.

This is high speed video. Here, the device is operating at 72 hertz, meaning this little hole makes two complete revolutions each second. The way it's meant to work is an arming laser shines on the rotor wheel, and when the proper input is given to the system, the wheel rotates a notch. If all the proper inputs are given, then the hole lines up with a laser beam and crazy things happen from there. So it is essential that this device's performance is perfectly predictable, even if it sits unused in a silo for decades. So are these now being used on nuclear weapons? You know, it turns out they don't tell us what they do with their nuclear weapons. And so, we designed them, we made prototypes, we tested them, and then it goes what they call behind the fence where it's all classified, and you know, we don't know what happens, so.

=> 01:17:15

Soft robots are the future of safe, adaptable technology for humans and hazardous environments.

But these soft components by themselves aren't truly robots. It's only once you combine them with computers that you get robots which can autonomously form crazy shapes or new styles of movement, all because they bend. But how do they work, and why would you want a soft robot in the first place? To explore these questions, I visited Stanford to meet Zach Hammond and his soft robot.

Upon meeting Zach, he demonstrated the robot's unique movement. Punctuated rolling locomotion allows the robot to roll around in any environment by tipping over from one face to another, moving its center of gravity. This movement is achieved when the center of gravity exits the support polygon or base, causing the robot to tip over one of its edges.

Another intriguing soft robot, made out of flexible tubing, mimics the way a turtle walks, with diagonally opposite legs moving together. This robot is powered entirely by compressed air and requires no electronics, making it suitable for environments like mines, where electronics could spark explosions, or around MRI machines with strong magnetic fields.

One of the key advantages of soft robots is their safety. Zach demonstrated this by encouraging me to take a whack at the robot, showing its compliance and compressive nature. Soft robots are inherently safe to operate around humans because their fundamental structure limits the maximum force they can exert. This makes them ideal for applications where human interaction is necessary.

Zach and I even tested the robot's safety by having it fall with me inside it. The experience was surprisingly gentle, and Zach showed me how the robot could open up to allow a quick exit. This robot, built by Zach and another grad student in about a month, features fabric tubes inflated with air. The red tubes are made of nylon fabric with an internal polyethylene tube for air tightness, inflated to about six PSI above atmospheric pressure.

=> 01:20:23

Soft robots: inflatable, adaptable, and friendly!

Members of this robot are fabric tubes inflated with air. These red tubes are made of nylon fabric, and internally there is a polyethylene tube that provides the air tightness. The tubes are inflated to about six PSI above atmospheric pressure, which is almost one and a half atmospheres. Each tube passes through pairs of rollers connected to a motor. The rollers pinch the tube so it bends, kind of like a pinched straw.

The rods have a high friction material wrapped around them. This, coupled with the pressurized tube pushing the membrane into the rollers, prevents slipping. By driving the motor, it changes the lengths of the tubes, similar to when a clown creates a twist in a balloon and folds it into a balloon animal. However, unlike the clown's balloon, there is some passage of air between adjacent segments of the tube, so the robot does not pressurize the segments as it moves around.

This robot is made of four inflated tubes, each connected to a pair of motors, forming triangular sides. They resemble sausage links when put together, which is why the robots are named after different sausages: Polish, Chorizo, Linguica, and Kielbasa. The overall shape of the robot is an octahedron. If you drew lines between the kinematic joints, it would create an octahedron shape.

Driving the motors together allows the robot to dramatically change shape. It can become very tall or short and squat. However, since the tubes themselves do not change in length, the overall perimeter of the robot, the length of all the edges combined, does not change. Therefore, the robot is considered isoperimetric.

The Boston Dynamics robots are strong and precise, but they are also heavy and cannot change their volume as dramatically. In contrast, this robot, despite being soft, is still capable of carrying a heavy load. A GUI in MATLAB enables the user to input the positions for the robots to move in inches and send them out. There is also some stored functionality for configurations.

=> 01:23:19

Robots that can change shape and fit into tight spaces are the future of space exploration.

These robots have the advantage of shape changing. They can become tall to go over obstacles or short to fit under obstructions. For example, if there's some rock that it didn't see, or that it wanted to roll over, it could simply do that, and the compliance of the tubes would simply bend around that disturbance.

Robots like this could be used in space. One of the nice things about these types of structures is that they can shrink down their volume very drastically. Since volume on rockets is such an expensive premium, being able to have a robot that can pack down small for transport is very valuable. NASA was at one point looking into trust robots for exactly that reason. They have contacted us since we've made this robot to explore different ideas for space exploration projects. One of the things that they're thinking about doing is deploying robots underneath a sheet of ice. They plan to drill through this sheet of ice and then deposit a robot through what is kind of a small diameter hole. If you can have a robot that can change its volume very drastically, or be disassembled and then reassembled to form a much larger structure, then you can have large robots that are able to fit through these tight spaces and be deployed in difficult-to-access areas.

There is some connection to an octopus because they use their shape-changing ability and their compliance to squeeze through tight passageways and wrap their body around objects. For example, they can open jars with their tentacles. One of the things that we want to use this robot for is grasping and manipulating objects. This robot is even capable of picking objects up off the ground. Because of the compliance of the tubes, it has a natural ability to grasp and manipulate objects. As it does so, the tubes bend ever so slightly, which increases the contact area and distributes evenly the forces that are exerted on that object.

A significant risk is if the robot pops. You obviously need the compressed air for your structure, and if you have a leak, then you don't have a robot. Some things that you could do to mitigate that would be to have onboard a small compressor, which isn't there to provide power to the robot but would help you maintain pressure if there were any small leaks.

When you tell someone you're working on a robot and they see this, it often defies expectations. They have no idea what it is I'm talking about until I show them a video or a picture. Most people's conception of soft robots was really expanded by the movie "Big Hero 6." They did a great job in showcasing what a soft robot can do and why they're useful, and kind of just popularizing the notion. It's really great to have compliance built into any mechanical system, especially as we want robots to work closer and closer with humans. So I think we'll definitely see more soft robots in the future.

Robots might enter our daily lives sooner than we think, just not in multipurpose humanoid form. In fact, one specialty robot is already becoming widespread, the glorious Roomba, built for maximum vacuuming. The way that robots integrate themselves into our lives might not be as a humanoid robot in your house, but as specialized little things that we don't even think of as robots. They might slowly infiltrate, like things just start getting smarter, whether it's your shoes, your watch, your car, or your thermostat, and then before you know it, your maid shows up as a robot.

By dropping the human model of a robot, we can choose the best possible shapes and materials that maximize specific abilities. With this method, we've already built robots that can save your life, leap tall buildings in a single bound, move with super speed, protect your valuables, and shapeshift. Come to think of it, they'd make a pretty good superhero team.