Your browser does not support JavaScript!

Author: Tronserve admin

Thursday 29th July 2021 10:29 AM

Robots Made Out of Branches Use Deep Learning to Walk


image cap
147 Views

Creating robots is a finicky process, needing an exhaustive amount of thought and care. It’s commonly important to have a very clear idea of what you want your robot to do and how you want it to do it, and then you build a prototype, discover everything that’s wrong with it, build something different and better, and repeat until you run out of time and/or money.

 

But robots don’t necessarily have to be this confusing, as long as your expectations for what they should be able to do are correspondingly low. In a paper offered at a NeurIPS workshop last December, a group of professionals from the University of Tokyo and Preferred Networks experimented with building mobile robots out of a couple of generic servos plus stuff you can find on the ground, like tree branches.

 

These robots figure out how to walk in simulation first, through deep reinforcement understanding. The way this is implemented in the paper is by selecting up some sticks, weighing and 3D scanning them, simulating the entire robot, and then rewarding gaits that result in the farthest movement. There’s also some hand-tuning involved to avoid habits that might (for example) “cause stress and wear in the real robot.”

 

Overall, this is maybe not the kind of strategy that you’d be able to use for most applications, but we can meditate about how robots like these could become a little bit more practical at some point. The idea of being able to create a mobile robot out of whatever is lying around (plus some servos and maybe a sensor or two) is a compelling one, and it appears like you could develop a gait from scratch on the physical robot using trial and error and feedback from some basic sensors, since we’ve seen similar things done on other robotic platforms.

 

Found materials robots like these are not likely to be as able as regular robotic designs, so they’d likely only be useful under unique circumstances. Not having to stress about transporting structural items would be nice, as would being able to generate a variety of designs as necessary using one generalized hardware set. And building a robot out of locally offered materials means that anything you put together will be really easy to fix, even if you do have to teach it to move all over again.



This article is originally posted on IEEESPECTRUM.com


Share this post:


This is the old design: Please remove this section after work on the functionalities for new design

Posted on : Thursday 29th July 2021 10:29 AM

Robots Made Out of Branches Use Deep Learning to Walk


none
Posted by  Tronserve admin
image cap

Creating robots is a finicky process, needing an exhaustive amount of thought and care. It’s commonly important to have a very clear idea of what you want your robot to do and how you want it to do it, and then you build a prototype, discover everything that’s wrong with it, build something different and better, and repeat until you run out of time and/or money.

 

But robots don’t necessarily have to be this confusing, as long as your expectations for what they should be able to do are correspondingly low. In a paper offered at a NeurIPS workshop last December, a group of professionals from the University of Tokyo and Preferred Networks experimented with building mobile robots out of a couple of generic servos plus stuff you can find on the ground, like tree branches.

 

These robots figure out how to walk in simulation first, through deep reinforcement understanding. The way this is implemented in the paper is by selecting up some sticks, weighing and 3D scanning them, simulating the entire robot, and then rewarding gaits that result in the farthest movement. There’s also some hand-tuning involved to avoid habits that might (for example) “cause stress and wear in the real robot.”

 

Overall, this is maybe not the kind of strategy that you’d be able to use for most applications, but we can meditate about how robots like these could become a little bit more practical at some point. The idea of being able to create a mobile robot out of whatever is lying around (plus some servos and maybe a sensor or two) is a compelling one, and it appears like you could develop a gait from scratch on the physical robot using trial and error and feedback from some basic sensors, since we’ve seen similar things done on other robotic platforms.

 

Found materials robots like these are not likely to be as able as regular robotic designs, so they’d likely only be useful under unique circumstances. Not having to stress about transporting structural items would be nice, as would being able to generate a variety of designs as necessary using one generalized hardware set. And building a robot out of locally offered materials means that anything you put together will be really easy to fix, even if you do have to teach it to move all over again.



This article is originally posted on IEEESPECTRUM.com

Tags:
robotics robots made out of branches neurips workshop