Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning

• URL: http://arxiv.org/abs/2304.13653v2
• Date: Thu, 11 Apr 2024 09:50:07 GMT
• Title: Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning
• Authors: Tuomas Haarnoja, Ben Moran, Guy Lever, Sandy H. Huang, Dhruva Tirumala, Jan Humplik, Markus Wulfmeier, Saran Tunyasuvunakool, Noah Y. Siegel, Roland Hafner, Michael Bloesch, Kristian Hartikainen, Arunkumar Byravan, Leonard Hasenclever, Yuval Tassa, Fereshteh Sadeghi, Nathan Batchelor, Federico Casarini, Stefano Saliceti, Charles Game, Neil Sreendra, Kushal Patel, Marlon Gwira, Andrea Huber, Nicole Hurley, Francesco Nori, Raia Hadsell, Nicolas Heess,
• Abstract summary: Deep Reinforcement Learning (Deep RL) is able to synthesize sophisticated and safe movement skills for a low-cost, miniature humanoid robot. We used Deep RL to train a humanoid robot with 20 actuated joints to play a simplified one-versus-one (1v1) soccer game. The resulting agent exhibits robust and dynamic movement skills such as rapid fall recovery, walking, turning, kicking and more.
• Score: 26.13655448415553
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate whether Deep Reinforcement Learning (Deep RL) is able to synthesize sophisticated and safe movement skills for a low-cost, miniature humanoid robot that can be composed into complex behavioral strategies in dynamic environments. We used Deep RL to train a humanoid robot with 20 actuated joints to play a simplified one-versus-one (1v1) soccer game. The resulting agent exhibits robust and dynamic movement skills such as rapid fall recovery, walking, turning, kicking and more; and it transitions between them in a smooth, stable, and efficient manner. The agent's locomotion and tactical behavior adapts to specific game contexts in a way that would be impractical to manually design. The agent also developed a basic strategic understanding of the game, and learned, for instance, to anticipate ball movements and to block opponent shots. Our agent was trained in simulation and transferred to real robots zero-shot. We found that a combination of sufficiently high-frequency control, targeted dynamics randomization, and perturbations during training in simulation enabled good-quality transfer. Although the robots are inherently fragile, basic regularization of the behavior during training led the robots to learn safe and effective movements while still performing in a dynamic and agile way -- well beyond what is intuitively expected from the robot. Indeed, in experiments, they walked 181% faster, turned 302% faster, took 63% less time to get up, and kicked a ball 34% faster than a scripted baseline, while efficiently combining the skills to achieve the longer term objectives.

Related papers

• SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experience [19.817578964184147]
  Parkour poses a significant challenge for legged robots, requiring navigation through complex environments with agility and precision based on limited sensory inputs. We introduce a novel method for training end-to-end visual policies, from depth pixels to robot control commands, to achieve agile and safe quadruped locomotion. We demonstrate the effectiveness of our method on a real Solo-12 robot, showcasing its capability to perform a variety of parkour skills such as walking, climbing, leaping, and crawling.
  arXiv  Detail & Related papers  (2024-09-20T17:39:20Z)
• DexDribbler: Learning Dexterous Soccer Manipulation via Dynamic Supervision [26.9579556496875]
  Joint manipulation of moving objects and locomotion with legs, such as playing soccer, receive scant attention in the learning community. We propose a feedback control block to compute the necessary body-level movement accurately and using the outputs as dynamic joint-level locomotion supervision. We observe that our learning scheme can not only make the policy network converge faster but also enable soccer robots to perform sophisticated maneuvers.
  arXiv  Detail & Related papers  (2024-03-21T11:16:28Z)
• 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)
• 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)
• Hierarchical Reinforcement Learning for Precise Soccer Shooting Skills using a Quadrupedal Robot [76.04391023228081]
  We address the problem of enabling quadrupedal robots to perform precise shooting skills in the real world using reinforcement learning. We propose a hierarchical framework that leverages deep reinforcement learning to train a robust motion control policy. We deploy the proposed framework on an A1 quadrupedal robot and enable it to accurately shoot the ball to random targets in the real world.
  arXiv  Detail & Related papers  (2022-08-01T22:34:51Z)
• Adaptation of Quadruped Robot Locomotion with Meta-Learning [64.71260357476602]
  We demonstrate that meta-reinforcement learning can be used to successfully train a robot capable to solve a wide range of locomotion tasks. The performance of the meta-trained robot is similar to that of a robot that is trained on a single task.
  arXiv  Detail & Related papers  (2021-07-08T10:37:18Z)
• Learning Bipedal Robot Locomotion from Human Movement [0.791553652441325]
  We present a reinforcement learning based method for teaching a real world bipedal robot to perform movements directly from motion capture data. Our method seamlessly transitions from training in a simulation environment to executing on a physical robot. We demonstrate our method on an internally developed humanoid robot with movements ranging from a dynamic walk cycle to complex balancing and waving.
  arXiv  Detail & Related papers  (2021-05-26T00:49:37Z)
• Learning Agile Locomotion via Adversarial Training [59.03007947334165]
  In this paper, we present a multi-agent learning system, in which a quadruped robot (protagonist) learns to chase another robot (adversary) while the latter learns to escape. We find that this adversarial training process not only encourages agile behaviors but also effectively alleviates the laborious environment design effort. In contrast to prior works that used only one adversary, we find that training an ensemble of adversaries, each of which specializes in a different escaping strategy, is essential for the protagonist to master agility.
  arXiv  Detail & Related papers  (2020-08-03T01:20:37Z)
• 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)

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.