Xiao Li

Research

My research interest lies at the intersection of formal methods, reinforcement learning and robotics. Namely, how to use logic and graph based reasoning tools that formal methods provide to learn complex robotic skills. My goal is to develop useful integrations of high-level symbolic reasoning with low-level motor learning. Below are selected highlights of my current and past research.

Temporal Logic Guided Safe Reinforcement Learning Using Control Barrier Functions

paper

Hierarchical Temporal Logic Guided Reinforcement Learning

paper

Automata Guided Reinforcement Learning With Demonstration

paper

Reinforcement Learning With Temporal Logic Rewards

paper

Task Frame Estimation During Model-Based Teleoperation For Satellite Servicing

paper

Parameter Estimation And Anomaly Detection While Cutting Insulation During Telerobotic Satellite Servicing

paper