Toward Asymptotically-Optimal Inspection Planning Via Efficient Near-Optimal Graph Search

Abstract

Inspection planning, the task of planning motions that allow a robot to inspect a set of points of interest, has applications in domains such as industrial, field, and medical robotics. Inspection planning can be computationally challenging, as the search space over motion plans grows exponentially with the number of points of interest to inspect. We propose a novel method, Incremental Random Inspection-roadmap Search (IRIS), that computes inspection plans whose length and set of successfully inspected points asymptotically converge to those of an optimal inspection plan. IRIS incrementally densifies a motion-planning roadmap using a sampling-based algorithm, and performs efficient near-optimal graph search over the resulting roadmap as it is generated. We demonstrate IRIS's efficacy on a simulated planar 5DOF manipulator inspection task and on a medical endoscopic inspection task for a continuum parallel surgical robot in cluttered anatomy segmented from patient CT data. We show that IRIS computes higher-quality inspection plans orders of magnitudes faster than a prior state-of-the-art method.

Creating Better Collision-Free Trajectory for Robot Motion Planning by Linearly Constrained Quadratic Programming

“…Base on this, Bogaerts et al (2018) propose the multiple gradient descent algorithm (MGDA) algorithm to decrease path length while maintaining sensor coverage, which can be used to handle inspection tasks for industrial robots. Similar research includes (Bogaerts et al, 2019;Fu et al, 2019). However, the above methods cannot meet the requirement of higher-order smooth trajectory for real robots.…”

A Comprehensive Review of Coverage Path Planning in Robotics Using Classical and Heuristic Algorithms

“…Then, it computes the shortest path to cover the POIs with a suitable graph search algorithm. The results [109,110] show that the approach can minimize coverage planning time by limiting the size of memory (number of nodes in the tree). Faghihi et al [111] introduced a random kinodynamic inspection tree (RKIT) algorithm, integrating the CPP problem and kinodynamic planning problem.…”

“…Then, the GA is used to find the shortest path to visit a sequence of POIs by dealing with the problem of TSP, following a return to the initial point. Similarly, [110] utilized an incremental random inspection roadmap search to optimize the number of POIs in the constructed graph. The tree is iteratively generated based on RRT, constructing the roadmap that induces the subset of the POIs.…”

Complexity of planning for connected agents

“…Some works use approximations of metric traveling salesman problem (TSP) to find solutions in the constructed graph [17,19]. Other works use A * search algorithms with suitable heuristics to compute approximate solutions [22].…”