Learning Social Heuristics for Human-Aware Path Planning

2025-09-02

AI Summary

This work addresses socially acceptable navigation for robots operating in human crowds, specifically focusing on learning and adhering to prototypical social norms such as queuing. We propose Human-Prior Learned Social Value (HPLSV), the first method to explicitly embed a data-driven, human-learned social value function—as a heuristic term—into path planning algorithms, enabling interpretable modeling and generalization of complex social constraints. HPLSV integrates social distance modeling, human motion prediction, and reinforcement-learning-based optimization of the social value function, thereby encoding social norms as transferable cost priors. Experiments demonstrate that HPLSV significantly improves the naturalness and human-consistency of robot queue-joining behavior, while maintaining real-time planning efficiency and enhancing social acceptability. The approach establishes a novel, interpretable, and scalable paradigm for socially grounded navigation in embodied intelligence.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• 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
• Economics, Online Markets and Human Computation: Social networks and social learning
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Social robotic navigation has been at the center of numerous studies in recent years. Most of the research has focused on driving the robotic agent along obstacle-free trajectories, respecting social distances from humans, and predicting their movements to optimize navigation. However, in order to really be socially accepted, the robots must be able to attain certain social norms that cannot arise from conventional navigation, but require a dedicated learning process. We propose Heuristic Planning with Learned Social Value (HPLSV), a method to learn a value function encapsulating the cost of social navigation, and use it as an additional heuristic in heuristic-search path planning. In this preliminary work, we apply the methodology to the common social scenario of joining a queue of people, with the intention of generalizing to further human activities.

Problem

• Learning social norms for robot navigation in human environments
• Developing heuristic planning with learned social value function
• Enabling robots to join queues and generalize social activities

Innovation

• Learning social value function for navigation
• Using learned heuristic in path planning
• Applying method to queue joining scenario