Alvin Tan
Papers
1
Total Citations
7
H-Index
1
About
Alvin Tan is a rising researcher at the intersection of reinforcement learning and social robotics, with a primary focus on developing safe, adaptive navigation systems for robots operating in human-populated environments. His most-cited work, "Stranger Danger! Identifying and Avoiding Unpredictable Pedestrians in RL-based Social Robot Navigation" (2024, 7 citations), addresses a critical vulnerability in learning-based navigation: the performance degradation of RL models when faced with unfamiliar or erratic pedestrian behaviors. Tan’s key contribution lies in designing frameworks that enable robots to detect and proactively avoid "unpredictable" agents—those whose motion patterns deviate from training distributions—thereby enhancing robustness and safety in real-world deployments. By integrating anomaly detection with policy optimization, his approach pushes beyond standard crowd navigation benchmarks, tackling the open problem of distributional shift in social robotics. Though early in his career, Tan’s work has already garnered attention for its practical relevance to autonomous delivery robots, assistive devices, and service robots. His research underscores a growing need for AI systems that can gracefully handle edge cases, marking him as a promising voice in the quest for trustworthy human-robot interaction.
Research Focus
Key Achievements
Top Papers
- 1