arXiv Robotics — research abstracts· Kry\v{s}tof P\v{s}eni\v{c}ka, Stefan Edelkamp·2026-10-20 04:00 UTC· 13 hours agoSignalEditorial score82

A GPU-Resident Pipeline for Multi-Robot 3D Inspection with Limited Perception

Summary

This research introduces a complete, GPU-resident pipeline for multi-robot 3, D inspection of underwater structures. The pipeline computes 6-DOF trajectories for a fleet of robots with limited cameras, minimizing a makespan/total-cost objective. It decomposes the NP-hard problem into five core stages, including visibility computation, set cover, and routing optimization, with GPU-accelerated implementations and experimental validation on 14 meshes.

Editorial context

This paper presents a GPU-accelerated pipeline for multi-robot 3D inspection of underwater structures, addressing the challenge of covering a target surface area with limited robot perception. The approach combines visibility computation, set cover, and routing optimization to minimize makespan and total cost, with experimental validation on complex meshes.

Source: arXiv Robotics — research abstracts · Read original article ↗

Loading article text…

Source：arXiv Robotics — research abstracts · arxiv.org

#Research #Sim-to-real #Reinforcement learning #World models