Brain-Inspired Visual Topometric Localization Via Roadnetwork-Constraint Hidden Markov Model
Jinyu Li, Taiping Zeng, Bailu Si
AI summary
Problem
Accurate robot localization in GPS-denied environments remains difficult, as existing brain-inspired cognitive maps lack precise metric data while traditional metric SLAM demands excessive computation and storage.
Approach
The authors introduce the Roadnetwork-Constraint Hidden Markov Model (RC-HMM) to merge semi-metric cognitive maps with road network geometry, creating a topometric map that leverages grid and head-direction cell dynamics for precise localization.
Key results
- 95% reduction in Absolute Pose Error and 81% in Relative Pose Error versus semi-metric maps
- Monocular accuracy matches binocular ORB-SLAM3 (3.6 m APE, 1.4 m RPE)
- Cuts CPU usage by 96.7% and map storage by 77.7% compared to binocular SLAM
- Achieves 99% faster initial localization time in CARLA Town07 simulations
Why it matters
Provides a scalable, low-resource navigation solution for autonomous robots operating in complex, GPS-denied urban environments.
Abstract
Accurate localization in GPS-denied environments remains a critical challenge for autonomous robot navigation. Animals exhibit remarkable navigational abilities in complex, dynamic environments by relying on mental cognitive maps. Inspired by neural representations such as head direction cells and grid cells, numerous robotic cognitive mapping systems can efficiently cover large areas; however, they often lack the precise metric information required for accurate localization. To address this challenge, we propose a neurodynamically driven monocular visual topometric localization approach based on road network constraints. We introduce the Roadnetwork-Constraint Hidden Markov Model (RC-HMM) to enhance the semi-metric map by incorporating road network constraints, forming a coherent topometric map that maintains vertex relationships and improves localization accuracy. Experimental results in the CARLA Town07 environment demonstrate the remarkable efficiency of our topometric cognitive map. Compared to the semi-metric map, our approach achieves a 95% reduction in Absolute Pose Error (APE) and an 81% reduction in Relative Pose Error (RPE). Compared to binocular ORB-SLAM3, our monocular approach reduces CPU usage by 96.7% and map storage by 77.7%, with an APE of 3.6 m and RPE of 1.4 m — closely matching ORB-SLAM3’s 3.86 m APE and 0.96 m RPE. Furthermore, by leveraging neurodynamics of grid cells and head direction cells, our monocular topometric localization robustly delivers the localization accuracy of 3.86 meters, compa- rable to binocular ORB-SLAM3. This approach integrates road network metrics into topological maps, enhancing brain-inspired navigation with topometric maps in complex environments. A project webpage is available at https://brain-inspired-navigation. github.io/topometric-loc/.