CAFE Closed-loop autonomous task formulation and execution without explicit task input. MDCPP Prediction-driven multi-robot coverage planning for workload adaptation. Distributed Multi-Robot Active Gathering Decentralized active perception and tracking in non-uniform environments. Quadruped Robot Learning and Navigation Sim-to-real locomotion and long-range embodied navigation on Unitree GO2. Multimodal Point Cloud Completion Feature purification and multimodal feedback for damaged architectural point clouds. Humanoid Robot Soccer Motion learning, action retargeting, and closed-loop control for RoboCup 3D soccer.
