Adap-RPF: Adaptive Trajectory Sampling for Robot Person Following in Dynamic Crowded Environments
Weixi Situ, Hanjing Ye, Jianwei Peng, Yu Zhan, Hong Zhang
AI summary
Problem
Existing robot person following methods rely on fixed-point tracking or sparse candidate selection, causing frequent target occlusions and collisions in dynamic, crowded environments.
Approach
The framework generates dense candidate following points within socially aware zones around the target, evaluates them using a multi-objective cost function, and executes tracking via a prediction-aware MPPI controller that anticipates pedestrian motion.
Key results
- Outperforms state-of-the-art baselines in smoothness, safety, robustness, and human comfort
- Proactively avoids dynamic occlusions using predicted pedestrian trajectories
- Generates dense, socially compliant candidate points via target-centric Sobol sampling
- Validated through extensive simulations and real-world mobile robot deployments
Why it matters
Advances practical human-robot interaction by enabling safe, socially compliant, and robust person-following in complex real-world settings.
Abstract
Robot person following (RPF) is a core capability in human–robot interaction, enabling robots to assist users in daily activities, collaborative work, and other service scenarios. However, achieving practical RPF remains challenging due to frequent occlusions, particularly in dynamic and crowded environments. Existing approaches often rely on fixed-point following or sparse candidate-point selection with oversimplified heuristics, which cannot adequately handle complex occlusions caused by moving obstacles such as pedestrians. To address these limitations, we propose an adaptive trajectory sampling method that generates dense candidate points within socially aware zones and evaluates them using a multi-objective cost function. Based on the optimal point, a person-following tra- jectory is estimated relative to the predicted motion of the target. We further design a prediction-aware model predictive path integral (MPPI) controller that simultaneously tracks this trajectory and proactively avoids collisions using pre- dicted pedestrian motions. Extensive experiments show that our method outperforms state-of-the-art baselines in smoothness, safety, robustness, and human comfort, with its effectiveness further demonstrated on a mobile robot in real-world scenarios.