首页|New Findings from University of Alicante in the Area of Robotics and Automation Reported (Geo-localization Based On Dynamically Weighted Factor-graph)
New Findings from University of Alicante in the Area of Robotics and Automation Reported (Geo-localization Based On Dynamically Weighted Factor-graph)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Robotics - Robotics an d Automation is the subject of a report. According to news reporting originating from Alicante, Spain, by NewsRx correspondents, research stated, “Feature-based geo-localization relies on associating features extracted from aerial imagery w ith those detected by the vehicle’s sensors. This requires that the type of land marks must be observable from both sources.” Financial support for this research came from Regional Valencian Community Gover nment. Our news editors obtained a quote from the research from the University of Alica nte, “This lack of variety of feature types generates poor representations that lead to outliers and deviations produced by ambiguities and lack of detections, respectively. To mitigate these drawbacks, in this letter, we present a dynamica lly weighted factor graph model for the vehicle’s trajectory estimation. The wei ght adjustment in this implementation depends on information quantification in t he detections performed using a LiDAR sensor. Also, a prior (GNSS-based) error e stimation is included in the model. Then, when the representation becomes ambigu ous or sparse, the weights are dynamically adjusted to rely on the corrected pri or trajectory, mitigating outliers and deviations in this way. We compare our me thod against state-of-the-art geo-localization ones in a challenging and ambiguo us environment, where we also cause detection losses.” According to the news editors, the research concluded: “We demonstrate mitigatio n of the mentioned drawbacks where the other methods fail.”
AlicanteSpainEuropeRobotics and Au tomationRoboticsUniversity of Alicante
NETL
NSTL
