A novel clustering-based algorithm for solving spatially-constrained robotic task sequencing problems

The robotic task sequencing problem (RTSP) appears in various forms across many industrial applications and consists of developing an optimal sequence of motions to visit a set of target points defined in a task space. Developing solutions to problems involving complex spatial constraints remains challenging due to the existence of multiple inverse kinematic solutions and the requirements for collision avoidance. So far existing studies have been limited to relaxed RTSPs involving a small number of target points and relatively uncluttered environments. When extending existing methods to problems involving greater spatial constraints and large sets of target points, they either require substantially long planning times or are unable to obtain high-quality solutions. To this end, this paper presents a clustering-based algorithm to efficiently address spatially-constrained RTSPs involving several hundred to thousands of points. Through a series of benchmarks, we show that the proposed algorithm outperforms the state-of-the-art in terms of solution quality and planning efficiency for large, complex problems, achieving up to 60% reduction in task execution time and 91% reduction in computation time.