Following Is All You Need: Robot Crowd Navigation Using People As Planners

2025-04-15

AI Summary

Conventional robot navigation in crowded environments relies on complex autonomous planners that either model pedestrian dynamics or learn social norms from data—overlooking the potential of human intelligence as an implicit navigation resource. Method: We propose the “Human-as-Planner” paradigm: instead of predicting pedestrian behavior or embedding explicit social rules, the robot identifies and follows a suitable human leader selected via lightweight rule-based filtering, tracking only short-horizon sub-goals along their path. This eliminates predictive models and data-driven components, using a minimalistic path tracker to implicitly absorb social conventions through real-time leader following. Contribution/Results: Evaluated in simulation and real-world settings, our approach outperforms state-of-the-art planners in safety, navigation efficiency, and behavioral naturalness, while drastically reducing computational overhead and system complexity. It offers an interpretable, low-cost, human-aligned alternative for socially compliant navigation.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: The sharing economy

Abstract

Navigating in crowded environments requires the robot to be equipped with high-level reasoning and planning techniques. Existing works focus on developing complex and heavyweight planners while ignoring the role of human intelligence. Since humans are highly capable agents who are also widely available in a crowd navigation setting, we propose an alternative scheme where the robot utilises people as planners to benefit from their effective planning decisions and social behaviours. Through a set of rule-based evaluations, we identify suitable human leaders who exhibit the potential to guide the robot towards its goal. Using a simple base planner, the robot follows the selected leader through shorthorizon subgoals that are designed to be straightforward to achieve. We demonstrate through both simulated and real-world experiments that our novel framework generates safe and efficient robot plans compared to existing planners, even without predictive or data-driven modules. Our method also brings human-like robot behaviours without explicitly defining traffic rules and social norms. Code will be available at https://github.com/centiLinda/PeopleAsPlanner.git.

Problem

• Robot navigation in crowded environments using human planners
• Identifying suitable human leaders for robot guidance
• Achieving safe and efficient robot plans without predictive modules

Innovation

• Robot follows human leaders for navigation
• Rule-based evaluation selects suitable leaders
• Simple base planner achieves short-horizon subgoals