Skip to content

Event

GPU-Accelerated Incremental Euclidean Distance Transform for Online Motion Planning

1 reports · 1 sources

Yizhou Chen and other authors published a voxel mapping system that uses GPU parallel computation to simultaneously generate an occupancy grid map (OGM) and a Euclidean distance transform (EDT), and incrementally builds a global EDT to output high-frequency local distance information for online motion planning. The system first computes the EDT in parallel within a local volume, then continuously integrates new observations into the global EDT via a parallel wavefront algorithm while retaining historical observations. The authors report that in real deployments on aerial vehicles and ground vehicles, the system achieved real-time performance under limited onboard computational resources. The paper was published in RA-L 2022 and is the authors' accepted manuscript.

Report timeline

  1. GPU-Accelerated Incremental Euclidean Distance Transform for Online Motion Planning of Mobile Robots

    This paper proposes a voxel mapping system that uses parallel computing to simultaneously generate occupancy grid maps (OGMs) and Euclidean distance transforms (EDTs), and incrementally builds a global EDT to output high-frequency local distance information for online motion planning. The system uses GPU programming to compute EDT in parallel within local volumes, then continuously integrates new observations into the global EDT via a parallel wavefront algorithm while preserving historical observations.

    arXiv cs.RO ·

Related topics

Perception and localizationSoftware and compute systemsResearch papers

Interest trend

Current
3
Peak
4Nov 4 01:00
Past 24 hours
–

The trend compares participants observed throughout the same period, so its range may be smaller than the current interest count. Move or tap to inspect each hour; use the arrow keys on a keyboard.