Hao-Tien Lewis Chiang
Papers
18
Total Citations
635
H-Index
12
About
Hao-Tien Lewis Chiang is a leading researcher in robot navigation, focusing on enabling autonomous systems to operate safely and effectively in dynamic, human-populated environments. His core contributions span reinforcement learning, motion planning, and social navigation. Chiang pioneered the use of AutoRL to learn end-to-end navigation behaviors that avoid moving obstacles, a work that has garnered over 230 citations. He also developed stochastic reachable set-based potential fields for hybrid dynamic obstacle avoidance, a key contribution cited over 169 times. More recently, he has explored using large language models to translate natural language into reward functions for robotic skill synthesis. Chiang’s work is notable for its rigorous evaluation; he co-authored principles and guidelines for benchmarking social robot navigation algorithms, addressing a critical need for fair comparison in the field. His research on leveraging human pose for trajectory prediction further advances robot perception in crowded spaces. With a publication record that includes highly cited papers on deep reinforcement learning and formal methods for obstacle avoidance, Chiang’s work is foundational for deploying robots in homes, offices, and other unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1Learning Navigation Behaviors End-to-End With AutoRL230 citations · 2019
- 2
- 3Language to Rewards for Robotic Skill Synthesis38 citations · 2023
- 4
- 5Robots That Can See: Leveraging Human Pose for Trajectory Prediction25 citations · 2023
- 6
- 7
- 8
- 9Principles and Guidelines for Evaluating Social Robot Navigation Algorithms15 citations · 2023
- 10