Oral Presentation: Crowd Navigation for Mobile Robots with Focused Risk Perception, by Mr. Hafiq Anas (Universiti Brunei Darussalam)

Current state-of-the-art crowd navigation approaches are mainly deep reinforcement learning (DRL)-based but often struggle to generalize to unseen crowd behaviors and to scale efficiently with crowd density. We propose a DRL method that incorporates risk perception directly into the observation space: collision probability is used to identify the K most hazardous obstacles, whose relative positions and velocities are exposed to the policy, yielding a compact, density-invariant representation that focuses learning on the most safety-critical interactions; in addition, local waypoints are added to the reward to densify the learning signal and accelerate convergence. Trained once in the Gazebo simulator with a non-cooperative randomized crowd, our model is evaluated on four crowd-behavior scenarios against a 2D-laser DRL baseline, a human-aware social planner, and two classical planners. Our approach achieves higher success rates and social safety across all settings, generalizes to unseen crowd behaviors without fine-tuning, and is further validated through real-world tests on a physical robot platform.