AnyCar to Anywhere: Learning Universal Dynamics Model for Agile and Adaptive Mobility
Authors:
- Wenli XiaoWXWenli Xiao
- Haoru XueHXHaoru Xue
- Tony TaoTTTony Tao
- Dvij KalariaDKDvij Kalaria
- John M. DolanJDJohn M. Dolan
- Guanya ShiGSGuanya Shi
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation2024
- Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion2024
- Model Predictive Control for Aggressive Driving Over Uneven Terrain2024
- Improved Baselines with Visual Instruction Tuning2024
- Pay Attention to How You Drive: Safe and Adaptive Model-Based Reinforcement Learning for Off-Road Driving2024
- TartanDrive 2.0: More Modalities and Better Infrastructure to Further Self-Supervised Learning Research in Off-Road Driving Tasks2024
- Real-Time Neural MPC: Deep Learning Model Predictive Control for Quadrotors and Agile Robotic PlatformsIEEE Robotics and Automation Letters, 2023
- Neural-Fly enables rapid learning for agile flight in strong windsScience Robotics, 2022
- RMA: Rapid Motor Adaptation for Legged Robots2021
- Learning Model Predictive Control for Iterative Tasks. A Data-Driven Control FrameworkIEEE Transactions on Automatic Control, 2017