Toward Real-World Cooperative and Competitive Soccer with Quadrupedal Robot Teams

• URL: http://arxiv.org/abs/2505.13834v1
• Date: Tue, 20 May 2025 02:20:54 GMT
• Title: Toward Real-World Cooperative and Competitive Soccer with Quadrupedal Robot Teams
• Authors: Zhi Su, Yuman Gao, Emily Lukas, Yunfei Li, Jiaze Cai, Faris Tulbah, Fei Gao, Chao Yu, Zhongyu Li, Yi Wu, Koushil Sreenath,
• Abstract summary: We present a hierarchical multi-agent reinforcement learning (MARL) framework that enables fully autonomous and decentralized quadruped robot soccer.<n>First, a set of highly dynamic low-level skills is trained for legged locomotion and ball manipulation, such as walking, dribbling, and kicking.<n>On top of these, a high-level strategic planning policy is trained with Multi-Agent Proximal Policy Optimization (MAPPO) via Fictitious Self-Play.
• Score: 25.885025521590414
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Achieving coordinated teamwork among legged robots requires both fine-grained locomotion control and long-horizon strategic decision-making. Robot soccer offers a compelling testbed for this challenge, combining dynamic, competitive, and multi-agent interactions. In this work, we present a hierarchical multi-agent reinforcement learning (MARL) framework that enables fully autonomous and decentralized quadruped robot soccer. First, a set of highly dynamic low-level skills is trained for legged locomotion and ball manipulation, such as walking, dribbling, and kicking. On top of these, a high-level strategic planning policy is trained with Multi-Agent Proximal Policy Optimization (MAPPO) via Fictitious Self-Play (FSP). This learning framework allows agents to adapt to diverse opponent strategies and gives rise to sophisticated team behaviors, including coordinated passing, interception, and dynamic role allocation. With an extensive ablation study, the proposed learning method shows significant advantages in the cooperative and competitive multi-agent soccer game. We deploy the learned policies to real quadruped robots relying solely on onboard proprioception and decentralized localization, with the resulting system supporting autonomous robot-robot and robot-human soccer matches on indoor and outdoor soccer courts.

Related papers

• Multi-Robot Collaboration through Reinforcement Learning and Abstract Simulation [3.5253513747455303]
  We investigate the extent to which so-called abstract simulators can be used for multi-agent reinforcement learning.<n>An abstract simulator models the robot's target task at a high-level of abstraction and discards many details of the world that could impact optimal decision-making.<n> Policies are trained in an abstract simulator then transferred to the physical robot by making use of separately-obtained low-level perception and motion control modules.
  arXiv  Detail & Related papers  (2025-03-07T02:23:24Z)
• VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play [26.51145484716405]
  We present VolleyBots, a novel robot sports testbed where multiple drones cooperate and compete in the sport of volleyball under physical dynamics.<n>VolleyBots integrates three features within a unified platform: competitive and cooperative gameplay, turn-based interaction structure, and agile 3D maneuvering.
  arXiv  Detail & Related papers  (2025-02-04T02:07:23Z)
• 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)
• Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning [26.13655448415553]
  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.
  arXiv  Detail & Related papers  (2023-04-26T16:25:54Z)
• Robust and Versatile Bipedal Jumping Control through Reinforcement Learning [141.56016556936865]
  This work aims to push the limits of agility for bipedal robots by enabling a torque-controlled bipedal robot to perform robust and versatile dynamic jumps in the real world. We present a reinforcement learning framework for training a robot to accomplish a large variety of jumping tasks, such as jumping to different locations and directions. We develop a new policy structure that encodes the robot's long-term input/output (I/O) history while also providing direct access to a short-term I/O history.
  arXiv  Detail & Related papers  (2023-02-19T01:06:09Z)
• Creating a Dynamic Quadrupedal Robotic Goalkeeper with Reinforcement Learning [18.873152528330063]
  We present a reinforcement learning (RL) framework that enables quadrupedal robots to perform soccer goalkeeping tasks in the real world. Soccer goalkeeping using quadrupeds is a challenging problem, that combines highly dynamic locomotion with precise and fast non-prehensile object (ball) manipulation. We deploy the proposed framework on a Mini Cheetah quadrupedal robot and demonstrate the effectiveness of our framework for various agile interceptions of a fast-moving ball in the real world.
  arXiv  Detail & Related papers  (2022-10-10T04:54:55Z)
• 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)
• From Motor Control to Team Play in Simulated Humanoid Football [56.86144022071756]
  We train teams of physically simulated humanoid avatars to play football in a realistic virtual environment. In a sequence of stages, players first learn to control a fully articulated body to perform realistic, human-like movements. They then acquire mid-level football skills such as dribbling and shooting. Finally, they develop awareness of others and play as a team, bridging the gap between low-level motor control at a timescale of milliseconds.
  arXiv  Detail & Related papers  (2021-05-25T20:17:10Z)
• 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)
• Real-World Human-Robot Collaborative Reinforcement Learning [6.089774484591287]
  We present a real-world setup of a human-robot collaborative maze game, designed to be non-trivial and only solvable through collaboration. We use deep reinforcement learning for the control of the robotic agent, and achieve results within 30 minutes of real-world play. We present results on how co-policy learning occurs over time between the human and the robotic agent resulting in each participant's agent serving as a representation of how they would play the game.
  arXiv  Detail & Related papers  (2020-03-02T19:34:07Z)

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.