Robust Visual Teach-and-Repeat Navigation with Flexible Topo-metric Graph Map Representation

2025-10-10

AI Summary

To address the insufficient robustness of vision-based teaching-and-replay navigation in dynamic and unknown environments, this paper proposes a robust navigation system integrating topological and metric information. Methodologically: (1) it constructs a scalable, topology-metric hybrid graph with adaptive node expansion to accommodate environmental changes; (2) it introduces a keyframe clustering mechanism coupled with cross-temporal matching between frames and local maps to enhance pose estimation stability; and (3) it incorporates long-term goal management and candidate optimization for local trajectory control to ensure navigation continuity. Experimental results demonstrate that, under dynamic conditions—including illumination variations and object removal/addition—the proposed system achieves an average 23.6% improvement in trajectory replay success rate and a 41.2% reduction in localization error compared to state-of-the-art baselines, significantly enhancing navigation robustness and effectiveness in complex, unstructured environments.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Natural Language Processing: Safety and Robustness

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

Visual Teach-and-Repeat Navigation is a direct solution for mobile robot to be deployed in unknown environments. However, robust trajectory repeat navigation still remains challenged due to environmental changing and dynamic objects. In this paper, we propose a novel visual teach-and-repeat navigation system, which consists of a flexible map representation, robust map matching and a map-less local navigation module. During the teaching process, the recorded keyframes are formulated as a topo-metric graph and each node can be further extended to save new observations. Such representation also alleviates the requirement of globally consistent mapping. To enhance the place recognition performance during repeating process, instead of using frame-to-frame matching, we firstly implement keyframe clustering to aggregate similar connected keyframes into local map and perform place recognition based on visual frame-tolocal map matching strategy. To promote the local goal persistent tracking performance, a long-term goal management algorithm is constructed, which can avoid the robot getting lost due to environmental changes or obstacle occlusion. To achieve the goal without map, a local trajectory-control candidate optimization algorithm is proposed. Extensively experiments are conducted on our mobile platform. The results demonstrate that our system is superior to the baselines in terms of robustness and effectiveness.

Problem

• Developing robust visual navigation for mobile robots in changing environments
• Enhancing place recognition through keyframe clustering and map matching
• Achieving map-less navigation with local trajectory optimization algorithms

Innovation

• Flexible topo-metric graph map representation for navigation
• Visual frame-to-local map matching for place recognition
• Map-less local trajectory-control optimization algorithm