用通用模型实现轮式机器人敏捷控制，实测性能超专用模型54%。
AnyCar to Anywhere: Learning Universal Dynamics Model for Agile and Adaptive Mobility
- 基于Transformer的通用动力学模型，统一多仿真器与物理引擎训练。
- 真实场景下零样本与少样本泛化，支持多种车辆与地形。
- 适合需要快速适配新机器人或复杂环境的研究者使用。
机器人学习领域已成功开发出可控制多种机器人形态的通用模型，适用于导航与移动等任务。然而，实现高敏捷性控制仍依赖需大量参数调优的专用模型。为兼顾通用模型的灵活性与专用模型的高性能，本文提出AnyCar——一种基于Transformer的通用动力学模型，用于各类轮式机器人的敏捷控制。通过统一多个仿真器并利用不同物理后端，模拟具有多样尺寸、规模和物理特性的车辆在多种地形上的行为，构建了大规模训练数据集。经过稳健训练与真实世界微调，该模型可在野外环境中精准适应不同车辆，即使存在较大状态估计误差亦表现良好。真实实验表明，AnyCar在多种车辆与环境下均展现出少样本与零样本泛化能力；结合采样型MPC时，其性能相比专用模型最高提升54%。这标志着迈向轮式机器人敏捷控制基础模型的重要一步。框架将开源以支持后续研究。
原文摘要 · Abstract (English)
Recent works in the robot learning community have successfully introduced generalist models capable of controlling various robot embodiments across a wide range of tasks, such as navigation and locomotion. However, achieving agile control, which pushes the limits of robotic performance, still relies on specialist models that require extensive parameter tuning. To leverage generalist-model adaptability and flexibility while achieving specialist-level agility, we propose AnyCar, a transformer-based generalist dynamics model designed for agile control of various wheeled robots. To collect training data, we unify multiple simulators and leverage different physics backends to simulate vehicles with diverse sizes, scales, and physical properties across various terrains. With robust training and real-world fine-tuning, our model enables precise adaptation to different vehicles, even in the wild and under large state estimation errors. In real-world experiments, AnyCar shows both few-shot and zero-shot generalization across a wide range of vehicles and environments, where our model, combined with a sampling-based MPC, outperforms specialist models by up to 54%. These results represent a key step toward building a foundation model for agile wheeled robot control. We will also open-source our framework to support further research.
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。