Coverage Path Planning using Path Primitive Sampling and Primitive Coverage Graph for Visual Inspection

Abstract

Planning the path to gather the surface information of the target objects is crucial to improve the efficiency of and reduce the overall cost, for visual inspection applications with Unmanned Aerial Vehicles (UAVs). Coverage Path Planning (CPP) problem is often formulated for these inspection applications because of the coverage requirement. Traditionally, researchers usually plan and optimize the viewpoints to capture the surface information first, and then optimize the path to visit the selected viewpoints. In this paper, we propose a novel planning method to directly sample and plan the inspection path for a camera-equipped UAV to acquire visual and geometric information of the target structures as a video stream setting in complex 3D environment. The proposed planning method first generates via-points and path primitives around the target object by using sampling methods based on voxel dilation and subtraction. A novel Primitive Coverage Graph (PCG) is then proposed to encode the topological information, flying distances, and visibility information, with the sampled via-points and path primitives. Finally graph search is performed to find the resultant path in the PCG to complete the inspection task with the coverage requirements. The effectiveness of the proposed method is demonstrated through simulation and field tests in this paper.

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

“…In the current research review, the combination of fusion-based algorithms provides better solutions, utilizing various algorithms' advantages. For instance, sampling-based planning with frontier-based exploration methods could optimize local and global searchability [149,323]. In addition, the combined receding horizon NBV and frontier-based exploration approach could reduce the computational complexity of gain estimation from inversely quartic growth to inversely linear growth, providing the overall complexity as ( ) ( )…”

“…Furthermore, Jing et al [149] proposed a novel CPP framework, including viewpoint generation, path primitive generation, visibility estimation, primitive coverage graph encoder formulation, and coverage graph search. The computation of an iterative adaptation of uniform could provide full coverage by generating viewpoint in high fidelity mesh model following point-to-point connecting based on RRT* [150].…”

Multi-Domain Informative Coverage Path Planning for a Hybrid Aerial Underwater Vehicle in Dynamic Environments

“…To efficiently grasp information from the environment, Jing. et al [31] directly planned and optimized paths via a video stream gathered by a UAV. Vidal E. et al proposed a novel algorithm based on Octree to achieve full coverage of unknown environments [32].…”

Combining Local and Global Viewpoint Planning for Fruit Coverage

“…The authors use a utility function that evaluates the viewpoint candidates based on the number of visible object voxels and apply a traveling salesman problem solver to compute the smallest tour of view poses that cover all observable object voxels. Similarly, Jing et al [4] generate viewpoints based on the maximum sensor range and compute viewing directions from the surface normals of all target voxels within a certain range. Afterward, the authors proposed to randomly sample a set of points and connect nearby points with a local planner to construct a graph.…”