Rapid Locomotion via Reinforcement Learning
- URL: http://arxiv.org/abs/2205.02824v1
- Date: Thu, 5 May 2022 17:55:11 GMT
- Title: Rapid Locomotion via Reinforcement Learning
- Authors: Gabriel B Margolis, Ge Yang, Kartik Paigwar, Tao Chen and Pulkit
Agrawal
- Abstract summary: We present an end-to-end learned controller that achieves record agility for the MIT Mini Cheetah.
This system runs and turns fast on natural terrains like grass, ice, and gravel and responds robustly to disturbances.
- Score: 15.373208553045416
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Agile maneuvers such as sprinting and high-speed turning in the wild are
challenging for legged robots. We present an end-to-end learned controller that
achieves record agility for the MIT Mini Cheetah, sustaining speeds up to 3.9
m/s. This system runs and turns fast on natural terrains like grass, ice, and
gravel and responds robustly to disturbances. Our controller is a neural
network trained in simulation via reinforcement learning and transferred to the
real world. The two key components are (i) an adaptive curriculum on velocity
commands and (ii) an online system identification strategy for sim-to-real
transfer leveraged from prior work. Videos of the robot's behaviors are
available at: https://agility.csail.mit.edu/
Related papers
- Impedance Matching: Enabling an RL-Based Running Jump in a Quadruped Robot [7.516046071926082]
We propose a new framework to mitigate the gap between simulated and real robots.
Our framework offers a structured guideline for parameter selection and the range for dynamics randomization in simulation.
Results are, to the best of our knowledge, one of the highest and longest running jumps demonstrated by an RL-based control policy in a real quadruped robot.
arXiv Detail & Related papers (2024-04-23T14:52:09Z) - Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control [106.32794844077534]
This paper presents a study on using deep reinforcement learning to create dynamic locomotion controllers for bipedal robots.
We develop a general control solution that can be used for a range of dynamic bipedal skills, from periodic walking and running to aperiodic jumping and standing.
This work pushes the limits of agility for bipedal robots through extensive real-world experiments.
arXiv Detail & Related papers (2024-01-30T10:48:43Z) - Generalized Animal Imitator: Agile Locomotion with Versatile Motion Prior [14.114972332185044]
This paper introduces the Versatile Motion prior (VIM) - a Reinforcement Learning framework designed to incorporate a range of agile locomotion tasks.
Our framework enables legged robots to learn diverse agile low-level skills by imitating animal motions and manually designed motions.
Our evaluations of the VIM framework span both simulation environments and real-world deployment.
arXiv Detail & Related papers (2023-10-02T17:59:24Z) - Barkour: Benchmarking Animal-level Agility with Quadruped Robots [70.97471756305463]
We introduce the Barkour benchmark, an obstacle course to quantify agility for legged robots.
Inspired by dog agility competitions, it consists of diverse obstacles and a time based scoring mechanism.
We present two methods for tackling the benchmark.
arXiv Detail & Related papers (2023-05-24T02:49:43Z) - Learning and Adapting Agile Locomotion Skills by Transferring Experience [71.8926510772552]
We propose a framework for training complex robotic skills by transferring experience from existing controllers to jumpstart learning new tasks.
We show that our method enables learning complex agile jumping behaviors, navigating to goal locations while walking on hind legs, and adapting to new environments.
arXiv Detail & Related papers (2023-04-19T17:37:54Z) - Learning fast and agile quadrupedal locomotion over complex terrain [0.3806109052869554]
We propose a robust controller that achieves natural and stably fast locomotion on a real blind quadruped robot.
The controller is trained in the simulation environment by model-free reinforcement learning.
Our controller has excellent anti-disturbance performance, and has good generalization ability to reach locomotion speeds it has never learned.
arXiv Detail & Related papers (2022-07-02T11:20:07Z) - Learning Semantics-Aware Locomotion Skills from Human Demonstration [35.996425893483796]
We present a framework that learns semantics-aware locomotion skills from perception for quadrupedal robots.
Our framework learns to adjust the speed and gait of the robot based on perceived terrain semantics, and enables the robot to walk over 6km without failure.
arXiv Detail & Related papers (2022-06-27T21:08:03Z) - Fast and Efficient Locomotion via Learned Gait Transitions [35.86279693549959]
We focus on the problem of developing efficient controllers for quadrupedal robots.
We devise a hierarchical learning framework, in which distinctive locomotion gaits and natural gait transitions emerge automatically.
We show that the learned hierarchical controller consumes much less energy across a wide range of locomotion speed than baseline controllers.
arXiv Detail & Related papers (2021-04-09T23:53:28Z) - Learning Quadrupedal Locomotion over Challenging Terrain [68.51539602703662]
Legged locomotion can dramatically expand the operational domains of robotics.
Conventional controllers for legged locomotion are based on elaborate state machines that explicitly trigger the execution of motion primitives and reflexes.
Here we present a radically robust controller for legged locomotion in challenging natural environments.
arXiv Detail & Related papers (2020-10-21T19:11:20Z) - Learning Agile Robotic Locomotion Skills by Imitating Animals [72.36395376558984]
Reproducing the diverse and agile locomotion skills of animals has been a longstanding challenge in robotics.
We present an imitation learning system that enables legged robots to learn agile locomotion skills by imitating real-world animals.
arXiv Detail & Related papers (2020-04-02T02:56:16Z) - Learning to Walk in the Real World with Minimal Human Effort [80.7342153519654]
We develop a system for learning legged locomotion policies with deep RL in the real world with minimal human effort.
Our system can automatically and efficiently learn locomotion skills on a Minitaur robot with little human intervention.
arXiv Detail & Related papers (2020-02-20T03:36:39Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.