Scientists Built a Badminton-Playing Robot With AI-Powered Skills (arstechnica.com) 10
An anonymous reader quotes a report from Ars Technica: The robot built by [Yuntao Ma and his team at ETH Zurich] was called ANYmal and resembled a miniature giraffe that plays badminton by holding a racket in its teeth. It was a quadruped platform developed by ANYbotics, an ETH Zurich spinoff company that mainly builds robots for the oil and gas industries. "It was an industry-grade robot," Ma said. The robot had elastic actuators in its legs, weighed roughly 50 kilograms, and was half a meter wide and under a meter long. On top of the robot, Ma's team fitted an arm with several degrees of freedom produced by another ETH Zurich spinoff called Duatic. This is what would hold and swing a badminton racket. Shuttlecock tracking and sensing the environment were done with a stereoscopic camera. "We've been working to integrate the hardware for five years," Ma said.
Along with the hardware, his team was also working on the robot's brain. State-of-the-art robots usually use model-based control optimization, a time-consuming, sophisticated approach that relies on a mathematical model of the robot's dynamics and environment. "In recent years, though, the approach based on reinforcement learning algorithms became more popular," Ma told Ars. "Instead of building advanced models, we simulated the robot in a simulated world and let it learn to move on its own." In ANYmal's case, this simulated world was a badminton court where its digital alter ego was chasing after shuttlecocks with a racket. The training was divided into repeatable units, each of which required that the robot predict the shuttlecock's trajectory and hit it with a racket six times in a row. During this training, like a true sportsman, the robot also got to know its physical limits and to work around them.
The idea behind training the control algorithms was to develop visuo-motor skills similar to human badminton players. The robot was supposed to move around the court, anticipating where the shuttlecock might go next and position its whole body, using all available degrees of freedom, for a swing that would mean a good return. This is why balancing perception and movement played such an important role. The training procedure included a perception model based on real camera data, which taught the robot to keep the shuttlecock in its field of view while accounting for the noise and resulting object-tracking errors.
Once the training was done, the robot learned to position itself on the court. It figured out that the best strategy after a successful return is to move back to the center and toward the backline, which is something human players do. It even came with a trick where it stood on its hind legs to see the incoming shuttlecock better. It also learned fall avoidance and determined how much risk was reasonable to take given its limited speed. The robot did not attempt impossible plays that would create the potential for serious damage -- it was committed, but not suicidal. But when it finally played humans, it turned out ANYmal, as a badminton player, was amateur at best. The findings have been published in the journal Science Robotics.
You can watch a video of the four-legged robot playing badminton on YouTube.
Along with the hardware, his team was also working on the robot's brain. State-of-the-art robots usually use model-based control optimization, a time-consuming, sophisticated approach that relies on a mathematical model of the robot's dynamics and environment. "In recent years, though, the approach based on reinforcement learning algorithms became more popular," Ma told Ars. "Instead of building advanced models, we simulated the robot in a simulated world and let it learn to move on its own." In ANYmal's case, this simulated world was a badminton court where its digital alter ego was chasing after shuttlecocks with a racket. The training was divided into repeatable units, each of which required that the robot predict the shuttlecock's trajectory and hit it with a racket six times in a row. During this training, like a true sportsman, the robot also got to know its physical limits and to work around them.
The idea behind training the control algorithms was to develop visuo-motor skills similar to human badminton players. The robot was supposed to move around the court, anticipating where the shuttlecock might go next and position its whole body, using all available degrees of freedom, for a swing that would mean a good return. This is why balancing perception and movement played such an important role. The training procedure included a perception model based on real camera data, which taught the robot to keep the shuttlecock in its field of view while accounting for the noise and resulting object-tracking errors.
Once the training was done, the robot learned to position itself on the court. It figured out that the best strategy after a successful return is to move back to the center and toward the backline, which is something human players do. It even came with a trick where it stood on its hind legs to see the incoming shuttlecock better. It also learned fall avoidance and determined how much risk was reasonable to take given its limited speed. The robot did not attempt impossible plays that would create the potential for serious damage -- it was committed, but not suicidal. But when it finally played humans, it turned out ANYmal, as a badminton player, was amateur at best. The findings have been published in the journal Science Robotics.
You can watch a video of the four-legged robot playing badminton on YouTube.
Leisure too? (Score:3)
So now robots will do arts and enjoy leisure sports, while people will continue handling all the hard manual labor? Some anti-utopia that is.
EU (Score:1)
Has the EU fined Apple over this badmintonbot yet?
For future use (Score:3)
While this is just a game, learning to predict and react to everything involved will lead to future developments. This could easily lead to robots being used in any situation where it has to interact with humans while navigating an area.
With enough training and better software, robots could expand into other areas of life such as in Japan where they are developing robots for use by and care for senior citizens.
Here's one based on a picture I have up: road construction. Instead of having humans sweating it out in the middle of July and August, have trained robots paving roads.
Re: (Score:2)
I watched the video (It was pretty cool) and it appears that the narrow field of view definitely held this robot back. What it was doing was quite amazing and as you said, with more training, software, and hardware, it could do a lot more.
The future does sound pretty exciting if you ignore the people in charge and just focus on the science and technology progress.
Re: (Score:2)
> robots... care for senior citizens
The day I'm left to robot care is the day I check myself out.
Re: (Score:2)
If you have dementia, you probably won't have a choice.
Welcome (Score:3)
I, for one, welcome our new quadrupedal badminton-playing overlords!
As expected, it's very limited (Score:2)
Serious badminton players win with shots that have to be returned with an underhand stroke. This robot wasn't shown doing anything like that. It was just handling the simple case of an overhead volley. Thus beating this robot is trivial--just hit the shuttlecock softly just over the net. It's a win every time.
Badminton tournament play is indoors and the action is quite fast and fun! I haven't played indoors for many years. :( It would be nice to have a robot that could actually play well.
Without AI it would have been unnoticed (Score:2)
But just add AI to your product or project and it suddenly transforms into this magical entity that can ride with unicorns over the rainbow.