A Hybrid Approach to Indoor Social Navigation: Integrating Reactive Local Planning and Proactive Global Planning

2025-06-03

AI Summary

This work addresses the social navigation problem for robots operating in high-dynamic, high-density, and space-constrained indoor environments, where safe and efficient goal-reaching amid free-moving pedestrians is critical. We propose a novel global–local collaborative framework: a global planner integrates human motion prediction with soft-constraint cost functions to generate conservative yet feasible paths; a local controller employs deep reinforcement learning (e.g., PPO or SAC) for real-time collision avoidance and complex maneuvering. Our method unifies classical path planning (A*/RRT variants), explicit pedestrian modeling, and a custom-built 2D indoor social navigation simulation benchmark. Evaluated on this new benchmark, our approach achieves an 18.7% higher navigation success rate and a 23.4% improvement in average passage efficiency compared to TEB, DWA, and pure RL baselines, demonstrating significantly enhanced robustness in dense pedestrian scenarios.

Technology Category

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

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Social networks and social learning

Abstract

We consider the problem of indoor building-scale social navigation, where the robot must reach a point goal as quickly as possible without colliding with humans who are freely moving around. Factors such as varying crowd densities, unpredictable human behavior, and the constraints of indoor spaces add significant complexity to the navigation task, necessitating a more advanced approach. We propose a modular navigation framework that leverages the strengths of both classical methods and deep reinforcement learning (DRL). Our approach employs a global planner to generate waypoints, assigning soft costs around anticipated pedestrian locations, encouraging caution around potential future positions of humans. Simultaneously, the local planner, powered by DRL, follows these waypoints while avoiding collisions. The combination of these planners enables the agent to perform complex maneuvers and effectively navigate crowded and constrained environments while improving reliability. Many existing studies on social navigation are conducted in simplistic or open environments, limiting the ability of trained models to perform well in complex, real-world settings. To advance research in this area, we introduce a new 2D benchmark designed to facilitate development and testing of social navigation strategies in indoor environments. We benchmark our method against traditional and RL-based navigation strategies, demonstrating that our approach outperforms both.

Problem

• Indoor robot navigation amidst freely moving humans
• Handling unpredictable human behavior and crowd densities
• Combining global and local planning for reliable navigation

Innovation

• Hybrid reactive and proactive planning integration
• DRL-powered local collision avoidance
• Soft cost global waypoint planning