FLAF: Focal Line and Feature-constrained Active View Planning for Visual Teach and Repeat

2024-09-05

arXiv.org

AI Summary

To address the critical challenge of feature tracking failure in texture-deficient regions of man-made environments—thereby limiting the practicality of visual navigation—this paper proposes an active viewpoint planning method that jointly leverages focus-line geometry and feature discriminability constraints, integrated into a feature-based visual teaching–reproduction system. For the first time, focus-line geometric constraints and map-point discriminability are co-modeled to enable task-specific, proactive viewpoint control during both teaching and reproduction phases, overcoming the robustness limitations of conventional passive-viewpoint tracking in low-texture areas. The method integrates PTU (pan-tilt-unit) control, feature-based VSLAM, focus-line projection geometry modeling, discriminability quantification, and online optimization. Experiments demonstrate a 32% improvement in mapping completeness and a reproduction localization success rate exceeding 96%, significantly enhancing navigation reliability in real-world complex environments.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This paper presents FLAF, a focal line and feature-constrained active view planning method for tracking failure avoidance in feature-based visual navigation of mobile robots. Our FLAF-based visual navigation is built upon a feature-based visual teach and repeat (VT&R) framework, which supports many robotic applications by teaching a robot to navigate on various paths that cover a significant portion of daily autonomous navigation requirements. However, tracking failure in feature-based visual simultaneous localization and mapping (VSLAM) caused by textureless regions in human-made environments is still limiting VT&R to be adopted in the real world. To address this problem, the proposed view planner is integrated into a feature-based visual SLAM system to build up an active VT&R system that avoids tracking failure. In our system, a pan-tilt unit (PTU)-based active camera is mounted on the mobile robot. Using FLAF, the active camera-based VSLAM operates during the teaching phase to construct a complete path map and in the repeat phase to maintain stable localization. FLAF orients the robot toward more map points to avoid mapping failures during path learning and toward more feature-identifiable map points beneficial for localization while following the learned trajectory. Experiments in real scenarios demonstrate that FLAF outperforms the methods that do not consider feature-identifiability, and our active VT&R system performs well in complex environments by effectively dealing with low-texture regions.

Problem

• Avoid tracking failure in visual navigation
• Enhance feature-based visual SLAM
• Improve VT&R in low-texture environments

Innovation

• Focal line view planning
• Feature-constrained navigation
• Active VT&R system