SHINE: Social Homology Identification for Navigation in Crowded Environments

2024-04-25

The international journal of robotics research

AI Summary

In dense human-robot coexistence scenarios, existing motion planners lack explicit modeling of high-level social behaviors—such as right-of-way conventions and yielding hierarchies—resulting in socially unintelligent navigation. To address this, we propose the first navigation framework integrating topological path classification with social behavior imitation. Our approach introduces homology-based topological representation to categorize socially compliant passage strategies; decouples high-level social decision-making—implemented via a deep behavioral classifier trained on real human trajectory data—from low-level optimization-based motion planning; and is fully integrated into a ROS-based real-time control architecture. Extensive simulation and physical robot experiments demonstrate that our method achieves an 18.7% higher prediction accuracy over state-of-the-art baselines, significantly outperforms prior work on social compliance benchmarks (e.g., PASS and SIDE), and ensures smooth, collision-free operation.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Model-Based Reasoning

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
• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web

Abstract

Navigating mobile robots in social environments remains a challenging task due to the intricacies of human-robot interactions. Most of the motion planners designed for crowded and dynamic environments focus on choosing the best velocity to reach the goal while avoiding collisions, but do not explicitly consider the high-level navigation behavior (avoiding through the left or right side, letting others pass or passing before others, etc.). In this work, we present a novel motion planner that incorporates topology distinct paths representing diverse navigation strategies around humans. The planner selects the topology class that imitates human behavior the best using a deep neural network model trained on real-world human motion data, ensuring socially intelligent and contextually aware navigation. Our system refines the chosen path through an optimization-based local planner in real time, ensuring seamless adherence to desired social behaviors. In this way, we decouple perception and local planning from the decision-making process. We evaluate the prediction accuracy of the network with real-world data. In addition, we assess the navigation capabilities in both simulation and a real-world platform, comparing it with other state-of-the-art planners. We demonstrate that our planner exhibits socially desirable behaviors and shows a smooth and remarkable performance.

Problem

• Navigating robots in crowded human environments effectively
• Incorporating human-like social behaviors in robot navigation
• Decoupling perception from decision-making for smoother navigation

Innovation

• Topology distinct paths for diverse navigation strategies
• Deep neural network trained on human motion data
• Optimization-based local planner for real-time refinement