首页|New Findings in Robotics Described from Czech Technical University (Rms: Redunda ncy-minimizing Point Cloud Sampling for Real-time Pose Estimation)
New Findings in Robotics Described from Czech Technical University (Rms: Redunda ncy-minimizing Point Cloud Sampling for Real-time Pose Estimation)
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 – Investigators publish new report on Ro botics. According to news originating from Prague, Czech Republic, by NewsRx cor respondents, research stated, “The typical point cloud sampling methods used in state estimation for mobile robots preserve a high level of point redundancy. Th is redundancy unnecessarily slows down the estimation pipeline and may cause dri ft under real-time constraints.” Financial support for this research came from CTU. Our news journalists obtained a quote from the research from Czech Technical Uni versity, “Such undue latency becomes a bottleneck for resource-constrained robot s (especially UAVs), requiring minimal delay for agile and accurate operation. W e propose a novel, deterministic, uninformed, and single-parameter point cloud s ampling method named RMS that minimizes redundancy within a 3D point cloud. In c ontrast to the state of the art, RMS balances the translation-space observabilit y by leveraging the fact that linear and planar surfaces inherently exhibit high redundancy propagated into iterative estimation pipelines. We define the concep t of gradient flow, quantifying the local surface underlying a point. We also sh ow that maximizing the entropy of the gradient flow minimizes point redundancy f or robot egomotion estimation. We integrate RMS into the point-based KISS-ICP a nd feature-based LOAM odometry pipelines and evaluate experimentally on KITTI, H ilti-Oxford, and custom datasets from multirotor UAVs.”
PragueCzech RepublicEuropeEmerging TechnologiesMachine LearningNano-robotRoboticsCzech Technical Universit y
NETL
NSTL
