We present an innovative approach that integrates radar data with high-definition (HD) maps to generate a robust perception module suitable for cost-map generation. While radars are essential for perception through instant velocity measurement, high range, and their robustness to weather conditions, they often introduce errors such as false alarms and clutters that could mislead the cost-map generation. Through a detailed analysis of these errors, including their typical spatial patterns on the HD map, we developed a precise classifier capable of removing these misdetections from actual objects. Experimental validation of our methodology is conducted on a dataset collected using our autonomous shuttle-bus, WATonoBus, under various weather conditions. Find a sample of our work's performance by visiting MVS-lab channel, where the perception output is put into a cost-map.
Robust Radar Object Detection Using HD Map Likelihoods and Information
24.09.2024
1147990 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Stereo reconstruction using high-order likelihoods
British Library Online Contents | 2014
|Gibbs likelihoods for Bayesian tracking
IEEE | 2004
|Gibbs Likelihoods for Bayesian Tracking
British Library Conference Proceedings | 2004
|