RPF-Search: Field-based Search for Robot Person Following in Unknown Dynamic Environments

2025-03-04

AI Summary

In unknown dynamic environments, robot human-following tasks suffer from frequent target loss due to static occlusions (e.g., corners) and dynamic occlusions (e.g., pedestrians). Method: This paper proposes a “simultaneous mapping and searching” heuristic framework. It integrates probabilistic mapping, potential-field modeling, heuristic search, multi-sensor fusion, and online environmental reasoning. Crucially, it introduces a novel belief-guided search field—coupled with a fluid field—to jointly address topological occlusion and dynamic interference, while fusing historical motion cues with real-time environmental observations for online search policy optimization. Contribution/Results: Extensive experiments in both simulation and real-world settings demonstrate significant improvements in target reacquisition success rate and search efficiency. The framework enhances the robustness and practicality of Robot-Person Following (RPF) systems in complex, unstructured open environments.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Heuristic Search
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Autonomous robot person-following (RPF) systems are crucial for personal assistance and security but suffer from target loss due to occlusions in dynamic, unknown environments. Current methods rely on pre-built maps and assume static environments, limiting their effectiveness in real-world settings. There is a critical gap in re-finding targets under topographic (e.g., walls, corners) and dynamic (e.g., moving pedestrians) occlusions. In this paper, we propose a novel heuristic-guided search framework that dynamically builds environmental maps while following the target and resolves various occlusions by prioritizing high-probability areas for locating the target. For topographic occlusions, a belief-guided search field is constructed and used to evaluate the likelihood of the target's presence, while for dynamic occlusions, a fluid-field approach allows the robot to adaptively follow or overtake moving occluders. Past motion cues and environmental observations refine the search decision over time. Our results demonstrate that the proposed method outperforms existing approaches in terms of search efficiency and success rates, both in simulations and real-world tests. Our target search method enhances the adaptability and reliability of RPF systems in unknown and dynamic environments to support their use in real-world applications. Our code, video, experimental results and appendix are available at https://medlartea.github.io/rpf-search/.

Problem

• Autonomous robot person-following systems face target loss in dynamic environments.
• Current methods are limited by reliance on static, pre-built maps.
• A novel search framework resolves occlusions and improves target re-finding.

Innovation

• Heuristic-guided search framework for dynamic mapping
• Belief-guided search field for topographic occlusions
• Fluid-field approach for dynamic occlusions adaptation