Learning robust autonomous navigation and locomotion for wheeled-legged robots.

Autonomous wheeled-legged robots have the potential to transform logistics systems, improving operational efficiency and adaptability in urban environments. Navigating urban environments, however, poses unique challenges for robots, necessitating innovative solutions for locomotion and navigation. These challenges include the need for adaptive locomotion across varied terrains and the ability to navigate efficiently around complex dynamic obstacles. This work introduces a fully integrated system comprising adaptive locomotion control, mobility-aware local navigation planning, and large-scale path planning within the city. Using model-free reinforcement learning (RL) techniques and privileged learning, we developed a versatile locomotion controller. This controller achieves efficient and robust locomotion over various rough terrains, facilitated by smooth transitions between walking and driving modes. It is tightly integrated with a learned navigation controller through a hierarchical RL framework, enabling effective navigation through challenging terrain and various obstacles at high speed. Our controllers are integrated into a large-scale urban navigation system and validated by autonomous, kilometer-scale navigation missions conducted in Zurich, Switzerland, and Seville, Spain. These missions demonstrate the system's robustness and adaptability, underscoring the importance of integrated control systems in achieving seamless navigation in complex environments. Our findings support the feasibility of wheeled-legged robots and hierarchical RL for autonomous navigation, with implications for last-mile delivery and beyond. Editor's summary: Last-mile deliveries in urban areas lead to increasing traffic problems and supply chain issues. By converting to robotic deliveries, routes can move from the street to alternate pathways, but traditional legged robots lack the necessary efficiency and battery life. By augmenting a legged robot with wheels, Lee et al. used hybrid wheeled-legged locomotion to improve the cost of transport while rolling on flat surfaces yet still allowing for legged navigation over obstacles like stairs. Using various reinforcement learning techniques, the robot was trained to smoothly transition between walking and driving modes and to navigate challenging terrain and dynamic obstacles including pedestrians. The robot was tested for large-scale navigation through an autonomous trek of more than 10 kilometers in Zurich, Switzerland, and Seville, Spain. The hybrid wheeled-legged platform successfully addressed many challenges associated with robotic urban mobility. —Melisa Yashinski [ABSTRACT FROM AUTHOR]