DeepWalk: Omnidirectional Bipedal Gait by Deep Reinforcement Learning

06/01/2021
by   Diego Rodriguez, et al.
0

Bipedal walking is one of the most difficult but exciting challenges in robotics. The difficulties arise from the complexity of high-dimensional dynamics, sensing and actuation limitations combined with real-time and computational constraints. Deep Reinforcement Learning (DRL) holds the promise to address these issues by fully exploiting the robot dynamics with minimal craftsmanship. In this paper, we propose a novel DRL approach that enables an agent to learn omnidirectional locomotion for humanoid (bipedal) robots. Notably, the locomotion behaviors are accomplished by a single control policy (a single neural network). We achieve this by introducing a new curriculum learning method that gradually increases the task difficulty by scheduling target velocities. In addition, our method does not require reference motions which facilities its application to robots with different kinematics, and reduces the overall complexity. Finally, different strategies for sim-to-real transfer are presented which allow us to transfer the learned policy to a real humanoid robot.

READ FULL TEXT

page 1

page 6

research
03/08/2021

An Energy-Saving Snake Locomotion Gait Policy Using Deep Reinforcement Learning

Snake robots, comprised of sequentially connected joint actuators, have ...
research
03/15/2018

Feedback Control For Cassie With Deep Reinforcement Learning

Bipedal locomotion skills are challenging to develop. Control strategies...
research
02/25/2023

DeepCPG Policies for Robot Locomotion

Central Pattern Generators (CPGs) form the neural basis of the observed ...
research
11/19/2021

Reinforcement Learning with Adaptive Curriculum Dynamics Randomization for Fault-Tolerant Robot Control

This study is aimed at addressing the problem of fault tolerance of quad...
research
01/24/2018

Learning Symmetric and Low-energy Locomotion

Learning locomotion skills is a challenging problem. To generate realist...
research
01/24/2018

Learning Symmetry and Low-energy Locomotion

Learning locomotion skills is a challenging problem. To generate realist...
research
10/14/2022

Just Round: Quantized Observation Spaces Enable Memory Efficient Learning of Dynamic Locomotion

Deep reinforcement learning (DRL) is one of the most powerful tools for ...

Please sign up or login with your details

Forgot password? Click here to reset