Peter Du

Papers

Total Citations

H-Index

About

Peter Du is a robotics researcher whose work centers on safe human-robot interaction, autonomous vehicle perception, and mobile robot navigation in unstructured environments. His most cited paper, "Online Monitoring for Safe Pedestrian-Vehicle Interactions" (2020, 21 citations), tackles the critical challenge of ensuring safety when autonomous vehicles operate in pedestrian zones. Du proposes a monitoring framework that enables small autonomous vehicles to navigate dynamically around people, addressing fundamental questions about real-time safety assurance. In "CoCAtt: A Cognitive-Conditioned Driver Attention Dataset" (2022, 11 citations), he advances driver attention prediction—a key technology for preventing collisions—by introducing a dataset that models cognitive states. His more recent work, "W-RIZZ: A Weakly-Supervised Framework for Relative Traversability Estimation in Mobile Robotics" (2024, 5 citations), develops a novel approach for predicting terrain traversability in unstructured domains, helping robots avoid hazards and obstacles without extensive labeled data. Du’s research bridges theoretical safety frameworks with practical perception systems, contributing to the deployment of autonomous systems in human-centered environments. His work has direct implications for autonomous driving, service robotics, and field robotics, making him a notable emerging voice in safe robotic autonomy.