Tackling the Kidnapped Robot Problem via Sparse Feasible Hypothesis Sampling and Reliable Batched Multi-Stage Inference

2025-11-02

AI Summary

This paper addresses the Kidnapped Robot Problem (KRP)—global relocalization from an unknown initial pose within a known occupancy grid map. We propose an efficient, passive 2D relocalization framework that operates on a single LiDAR scan. Our method integrates sparse feasible hypothesis sampling with batched, multi-stage inference: uniformly distributed pose hypotheses are generated via RRT in the reachable space; candidates are rapidly ranked using the SMAD coarse-filtering metric; and pose evaluation proceeds in stages—first optimizing orientation via the TAM alignment metric, then refining full 6-DoF pose estimation—with support for early termination. The framework robustly mitigates localization degradation caused by non-panoramic scans and environmental changes. Evaluated on real-world datasets and resource-constrained platforms, it achieves higher relocalization success rates and superior computational efficiency compared to state-of-the-art methods, particularly under narrow-field-of-view LiDAR conditions.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

This paper addresses the Kidnapped Robot Problem (KRP), a core localization challenge of relocalizing a robot in a known map without prior pose estimate when localization loss or at SLAM initialization. For this purpose, a passive 2-D global relocalization framework is proposed. It estimates the global pose efficiently and reliably from a single LiDAR scan and an occupancy grid map while the robot remains stationary, thereby enhancing the long-term autonomy of mobile robots. The proposed framework casts global relocalization as a non-convex problem and solves it via the multi-hypothesis scheme with batched multi-stage inference and early termination, balancing completeness and efficiency. The Rapidly-exploring Random Tree (RRT), under traversability constraints, asymptotically covers the reachable space to generate sparse, uniformly distributed feasible positional hypotheses, fundamentally reducing the sampling space. The hypotheses are preliminarily ordered by the proposed Scan Mean Absolute Difference (SMAD), a coarse beam-error level metric that facilitates the early termination by prioritizing high-likelihood candidates. The SMAD computation is optimized for non-panoramic scans. And the Translation-Affinity Scan-to-Map Alignment Metric (TAM) is proposed for reliable orientation selection at hypothesized positions and accurate final pose evaluation to mitigate degradation in conventional likelihood-field metrics under translational uncertainty induced by sparse hypotheses, as well as non-panoramic LiDAR scan and environmental changes. Real-world experiments on a resource-constrained mobile robot with non-panoramic LiDAR scan demonstrate that the proposed framework outperforms existing methods in both global relocalization success rate and computational efficiency.

Problem

• Solves robot relocalization without prior pose in known maps
• Generates sparse feasible hypotheses under traversability constraints
• Mitigates metric degradation under translational uncertainty and environmental changes

Innovation

• Sparse feasible hypothesis sampling via traversability-constrained RRT
• Batched multi-stage inference with early termination
• Translation-Affinity Scan-to-Map Alignment Metric for pose evaluation