用比赛录像训练机器人踢足球，让机器人学会走路、踢球和摔倒后爬起。
SoccerDiffusion: Toward Learning End-to-End Humanoid Robot Soccer from Gameplay Recordings
- 基于扩散模型，从视觉、本体感知等多模态数据中直接学控制动作
- 单步推理实现嵌入式设备实时运行，复现了走、踢、跌倒恢复等复杂动作
- 适合想快速部署足球机器人行为的开发者，尤其关注动作生成与落地
本文提出SoccerDiffusion，一种基于Transformer的扩散模型，可直接从真实比赛录像中学习人形机器人足球的端到端控制策略。利用RoboCup赛事采集的数据，模型从视觉、本体感知和比赛状态等多模态输入中预测关节指令轨迹。通过知识蒸馏技术，将多步扩散过程压缩为单步推理，实现在嵌入式平台上的实时运行。实验表明，该模型在仿真和真实机器人上均能有效复现行走、踢球及跌倒恢复等复杂运动行为。尽管高层次战术表现仍有限，但为后续强化学习或偏好优化方法提供了可靠基础。数据集、预训练模型与代码已开源：https://bit-bots.github.io/SoccerDiffusion。
原文摘要 · Abstract (English)
This paper introduces SoccerDiffusion, a transformer-based diffusion model designed to learn end-to-end control policies for humanoid robot soccer directly from real-world gameplay recordings. Using data collected from RoboCup competitions, the model predicts joint command trajectories from multi-modal sensor inputs, including vision, proprioception, and game state. We employ a distillation technique to enable real-time inference on embedded platforms that reduces the multi-step diffusion process to a single step. Our results demonstrate the model's ability to replicate complex motion behaviors such as walking, kicking, and fall recovery both in simulation and on physical robots. Although high-level tactical behavior remains limited, this work provides a robust foundation for subsequent reinforcement learning or preference optimization methods. We release the dataset, pretrained models, and code under: https://bit-bots.github.io/SoccerDiffusion
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。