Shangqun Yu

As robots increase in agility and encounter fast- moving objects, dynamic object detection and avoidance become notably challenging. Traditional RGB cameras, burdened by motion blur and high latency, often act as the bottleneck. Event cameras have recently emerged as a promising solution for the challenges related to rapid movement. In this paper, we introduce a dynamic object avoidance framework that integrates both event and RGBD cameras. Specifically, this framework first estimates and compensates for the event’s motion to detect dynamic objects. Subsequently, depth data is combined to derive a 3D trajectory. When initiating from a static state, the robot adjusts its height based on the predicted collision point to avoid the dynamic obstacle. Through real-world experiments with the Mini-Cheetah, our approach successfully circumvents dynamic objects at speeds up to 5 m/s, achieving an 83% success rate. Supplemental video:

We propose a novel parameterized skill-learning algorithm that aims to learn transferable parameterized skills and synthesize them into a new action space that supports efficient learning in long-horizon tasks. We propose to leverage off-policy Meta-RL combined with a trajectory-centric smoothness term to learn a set of parameterized skills. Our agent can use these learned skills to construct a three-level hierarchical framework that models a Temporally-extended Parameterized Action Markov Decision Process. We empirically demonstrate that the proposed algorithms enable an agent to solve a set of highly difficult long-horizon (obstacle-course and robot manipulation) tasks.