Good Weights: Proactive, Adaptive Dead Reckoning Fusion for Continuous and Robust Visual SLAM
Yanwei Du, Jing-Chen Peng, Patricio Vela
AI summary
Problem
Visual SLAM frequently loses track or diverges in texture-less or low-light conditions due to insufficient feature associations, while conventional multi-sensor fusion relies on fixed weights that cannot dynamically balance unreliable dead reckoning with degraded visual cues.
Approach
Good Weights dynamically modulates dead reckoning contribution using lightweight visual health indicators (feature counts), integrating this adaptive weighting across tracking, local mapping, and loop closing to maintain optimization stability.
Key results
- Prevents track loss in low-texture and degraded visual environments
- Integrates adaptive dead reckoning priors across all SLAM pipeline stages
- Maintains real-time operation without online calibration or complex uncertainty modeling
- Demonstrates improved trajectory accuracy and robustness on indoor datasets and mobile robots
Why it matters
Provides a practical, calibration-free framework for reliable robot navigation in visually challenging real-world settings.
Abstract
Given that Visual SLAM relies on appearance cues for localization and scene understanding, texture-less or visually degraded environments (e.g., plain walls or low lighting) lead to poor pose estimation and track loss. However, robots are typically equipped with sensors that provide some form of dead reckoning odometry with reasonable short-time performance but unreliable long-time performance. The Good Weights (GW) algorithm described here provides a framework to adaptively integrate dead reckoning (DR) with passive visual SLAM for continuous and accurate frame-level pose estimation. Importantly, it describes how all modules in a comprehensive SLAM system must be modified to incorporate DR into its design. Adaptive weighting increases DR influence when visual tracking is unreliable and reduces when visual feature information is strong, maintaining pose track without overreliance on DR. Good Weights yields a practical solution for mobile navigation that improves visual SLAM performance and robustness. Experiments on collected datasets and in real-world deployment demonstrate the benefits of Good Weights.