任意车辆到任意地点：学习用于敏捷与自适应移动的通用动力学模型
AnyCar to Anywhere: Learning Universal Dynamics Model for Agile and Adaptive Mobility
AI总结：
提出基于transformer的通用动力学模型AnyCar，通过统一多模拟器数据与真实世界微调，实现多种轮式机器人在复杂环境下的敏捷自适应控制，结合MPC性能比专用模型提升达54%。
摘要：
机器人学习领域的近期研究已成功引入了通用模型，能够控制各种机器人本体执行导航和移动等广泛任务。然而，实现突破机器人性能极限的敏捷控制，仍依赖于需要大量参数调优的专用模型。为了利用通用模型的适应性和灵活性，同时达到专用模型级别的敏捷性，我们提出了 AnyCar，这是一种基于 transformer 的通用动力学模型，旨在实现各种轮式机器人的敏捷控制。为了收集训练数据，我们统一了多个模拟器，并利用不同的物理后端来模拟在多种地形上具有不同尺寸、比例和物理属性的车辆。通过鲁棒训练和真实世界微调，我们的模型能够实现对不同车辆的精确适应，即使在野外环境和存在较大状态估计误差的情况下也是如此。在真实世界实验中，AnyCar 在各种车辆和环境中展现了少样本和零样本泛化能力，我们的模型结合基于采样的 MPC，性能比专用模型高出多达 54%。这些结果代表了向构建敏捷轮式机器人控制基础模型迈出的关键一步。我们也将开源我们的框架以支持进一步的研究。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
