HiCrowd: Hierarchical Crowd Flow Alignment for Dense Human Environments

2026-02-05

AI Summary

This work addresses the “freezing problem” that often impedes safe and efficient navigation of mobile robots in dense crowds. The authors propose a hierarchical decision-making framework that treats pedestrian motion not merely as obstacles but as navigational cues. By leveraging reinforcement learning for long-term path planning and integrating model predictive control (MPC) for short-term safe execution, the robot naturally aligns itself with compatible crowd flows. Evaluated on both real-world and synthetic crowd datasets, the approach significantly outperforms existing baselines, simultaneously enhancing navigation efficiency and safety while effectively mitigating the freezing phenomenon.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Navigating through dense human crowds remains a significant challenge for mobile robots. A key issue is the freezing robot problem, where the robot struggles to find safe motions and becomes stuck within the crowd. To address this, we propose HiCrowd, a hierarchical framework that integrates reinforcement learning (RL) with model predictive control (MPC). HiCrowd leverages surrounding pedestrian motion as guidance, enabling the robot to align with compatible crowd flows. A high-level RL policy generates a follow point to align the robot with a suitable pedestrian group, while a low-level MPC safely tracks this guidance with short horizon planning. The method combines long-term crowd aware decision making with safe short-term execution. We evaluate HiCrowd against reactive and learning-based baselines in offline setting (replaying recorded human trajectories) and online setting (human trajectories are updated to react to the robot in simulation). Experiments on a real-world dataset and a synthetic crowd dataset show that our method outperforms in navigation efficiency and safety, while reducing freezing behaviors. Our results suggest that leveraging human motion as guidance, rather than treating humans solely as dynamic obstacles, provides a powerful principle for safe and efficient robot navigation in crowds.

Problem

• crowd navigation
• freezing robot problem
• dense human environments
• mobile robots
• human-robot interaction

Innovation

• hierarchical crowd navigation
• reinforcement learning
• model predictive control
• crowd flow alignment
• freezing robot problem