Socially Aware Robot Crowd Navigation via Online Uncertainty-Driven Risk Adaptation

TL;DR

This paper introduces LR-MPC, a data-driven, uncertainty-aware navigation algorithm that enables robots to navigate crowded environments efficiently, safely, and socially aware by combining offline risk learning with online adaptive planning.

Contribution

The paper presents a novel LR-MPC framework that integrates risk prediction with uncertainty filtering for socially aware robot navigation in crowds.

Findings

LR-MPC outperforms baseline methods in success rate.

LR-MPC demonstrates high social awareness and adaptability.

The approach effectively balances safety and efficiency in complex crowds.

Abstract

Navigation in human-robot shared crowded environments remains challenging, as robots are expected to move efficiently while respecting human motion conventions. However, many existing approaches emphasize safety or efficiency while overlooking social awareness. This article proposes Learning-Risk Model Predictive Control (LR-MPC), a data-driven navigation algorithm that balances efficiency, safety, and social awareness. LR-MPC consists of two phases: an offline risk learning phase, where a Probabilistic Ensemble Neural Network (PENN) is trained using risk data from a heuristic MPC-based baseline (HR-MPC), and an online adaptive inference phase, where local waypoints are sampled and globally guided by a Multi-RRT planner. Each candidate waypoint is evaluated for risk by PENN, and predictions are filtered using epistemic and aleatoric uncertainty to ensure robust decision-making. The safest waypoint is selected as the MPC input for real-time navigation. Extensive experiments demonstrate that LR-MPC outperforms baseline methods in success rate and social awareness, enabling robots to navigate complex crowds with high adaptability and low disruption. A website about this work is available at https://sites.google.com/view/lr-mpc.