Learning Locomotion Skills in Evolvable Robots

10/19/2020 ∙ by Gongjin Lan, et al. ∙ 0 ∙ share

The challenge of robotic reproduction – making of new robots by recombining two existing ones – has been recently cracked and physically evolving robot systems have come within reach. Here we address the next big hurdle: producing an adequate brain for a newborn robot. In particular, we address the task of targeted locomotion which is arguably a fundamental skill in any practical implementation. We introduce a controller architecture and a generic learning method to allow a modular robot with an arbitrary shape to learn to walk towards a target and follow this target if it moves. Our approach is validated on three robots, a spider, a gecko, and their offspring, in three real-world scenarios.

READ FULL TEXT

Learning Directed Locomotion in Modular Robots with Evolvable Morphologies

We generalize the well-studied problem of gait learning in modular robot...
01/21/2020 ∙ by Gongjin Lan, et al. ∙ 5 ∙ share

read it
Learning to Walk in the Real World with Minimal Human Effort

Reliable and stable locomotion has been one of the most fundamental chal...
02/20/2020 ∙ by Sehoon Ha, et al. ∙ 27 ∙ share

read it
Learning Agile Robotic Locomotion Skills by Imitating Animals

Reproducing the diverse and agile locomotion skills of animals has been ...
04/02/2020 ∙ by Xue Bin Peng, et al. ∙ 0 ∙ share

read it
Learning Generalizable Locomotion Skills with Hierarchical Reinforcement Learning

Learning to locomote to arbitrary goals on hardware remains a challengin...
09/26/2019 ∙ by Tianyu Li, et al. ∙ 0 ∙ share

read it
PPMC Training Algorithm: A Robot Independent Rough Terrain Deep Learning Based Path Planner and Motion Controller

Robots can now learn how to make decisions and control themselves, gener...
03/02/2020 ∙ by Tamir Blum, et al. ∙ 0 ∙ share

read it
PPMC RL Training Algorithm: Rough Terrain Intelligent Robots through Reinforcement Learning

Robots can now learn how to make decisions and control themselves, gener...
03/02/2020 ∙ by Tamir Blum, et al. ∙ 0 ∙ share

read it
Zero-Shot Terrain Generalization for Visual Locomotion Policies

Legged robots have unparalleled mobility on unstructured terrains. Howev...
11/11/2020 ∙ by Alejandro Escontrela, et al. ∙ 0 ∙ share

read it

Learning Locomotion Skills in Evolvable Robots

Authors

Learning Directed Locomotion in Modular Robots with Evolvable Morphologies

Learning to Walk in the Real World with Minimal Human Effort

Learning Agile Robotic Locomotion Skills by Imitating Animals

Learning Generalizable Locomotion Skills with Hierarchical Reinforcement Learning

PPMC Training Algorithm: A Robot Independent Rough Terrain Deep Learning Based Path Planner and Motion Controller

PPMC RL Training Algorithm: Rough Terrain Intelligent Robots through Reinforcement Learning

Zero-Shot Terrain Generalization for Visual Locomotion Policies

This week in AI