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

2025/06/17 by Zhirui Sun, Sun, Zhirui, Xingrong Diao +6 · 1 citation
Computer Science · Engineering · #Evacuation and Crowd Dynamics #FOS: Computer and information sciences #Mobile Crowdsensing and Crowdsourcing #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2506.14305

openalex publication_date 2025/06/17 · openalex created_date 2025/10/18 · openalex updated_date 2026/07/28

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.

Citations

• NAMR-RRT: Neural Adaptive Motion Planning for Mobile Robots in Dynamic Environments
• DR-MPC: Deep Residual Model Predictive Control for Real-world Social Navigation
• Learning to Refine Input Constrained Control Barrier Functions via Uncertainty-Aware Online Parameter Adaptation
• Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation
• IA-LSTM: Interaction-Aware LSTM for Pedestrian Trajectory Prediction
• A survey on socially aware robot navigation: Taxonomy and future challenges
• TBD Pedestrian Data Collection: Towards Rich, Portable, and Large-Scale Natural Pedestrian Data
• Multi-Risk-RRT: An Efficient Motion Planning Algorithm for Robotic Autonomous Luggage Trolley Collection at Airports
• Principles and Guidelines for Evaluating Social Robot Navigation Algorithms
• SACSoN: Scalable Autonomous Control for Social Navigation
• Bridging Active Exploration and Uncertainty-Aware Deployment Using Probabilistic Ensemble Neural Network Dynamics
• Multi-Tree Guided Efficient Robot Motion Planning
• Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph
• Robotic Autonomous Trolley Collection with Progressive Perception and Nonlinear Model Predictive Control
• Rule-Based Safety-Critical Control Design using Control Barrier Functions with Application to Autonomous Lane Change
• Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learning
• Online State-Time Trajectory Planning Using Timed-ESDF in Highly Dynamic Environments
• Safety-Critical Model Predictive Control with Discrete-Time Control Barrier Function
• Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning
• Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
• Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach
• Adam: A Method for Stochastic Optimization
• Social force model for pedestrian dynamics

Cited by

• Follow-Bench: A Unified Motion Planning Benchmark for Socially-Aware Robot Person Following

Related

• Risk-Sensitive Sequential Action Control with Multi-Modal Human Trajectory Forecasting for Safe Crowd-Robot Interaction
• Integrating Predictive Motion Uncertainties with Distributionally Robust Risk-Aware Control for Safe Robot Navigation in Crowds
• Towards Generalizable Safety in Crowd Navigation via Conformal Uncertainty Handling
• Disentangling Uncertainty for Safe Social Navigation using Deep Reinforcement Learning
• Deep Reinforcement Learning-Based Mapless Crowd Navigation with Perceived Risk of the Moving Crowd for Mobile Robots