Learning Robust Autonomous Navigation and Locomotion for Wheeled-legged Robots

In our new Science Robotics paper, we introduce an autonomous navigation system developed for our wheeled-legged quadrupeds, designed for fast and efficient navigation within large urban environments. Driven by neural network policies, our simple, unified control system enables smooth gait transitions, smart navigation planning, and highly responsive obstacle avoidance in populated urban environments. With the Swiss-Mile prototype robot, we have conducted kilometer-scale missions for months and proved the feasibility of our system for real-world applications. Project website: Paper link: