CLeAR Lab, National University of Singapore
Date:
CLeAR lab in National University of Singapore seeks to improve people’s lives through intelligent robotics. The central focus of the lab is on developing physical and social skills for robots.
Role:
Implemented real-world demonstrations of LTLDoG: Satisfying Temporally-Extended Symbolic Constraints for Safe Diffusion-Based Planning. Using LTLDoG as a global planner, we conducted navigation experiments with a Unitree Go2 robot. The work was published in IEEE Robotics and Automation Letters (RA-L) in 2024.
Developed a ROS 2/Gazebo simulation tool that uses LLMs to generate social navigation scenarios with varied human behaviors and contexts for benchmarking navigation algorithms and identifying failure cases. The initial paper, Towards Automated Scenario Testing of Social Navigation Algorithms, was presented at the RSS 2024 workshop on Unsolved Problems in Social Navigation. The expanded journal paper, SocRATES: Language-Driven Scenario Generation for Evaluating Social Navigation Algorithms, was published in IEEE Robotics and Automation Letters (RA-L) in 2026.
