Statistical analysis of influencing factors for heuristic grip determination in random bin picking

The determination of collision free grips is an important aspect of random bin picking, which describes the separation of unordered workpieces stored in bins by an industrial robot. Heuristic search algorithms are an appropriate approach to this problem. In this paper, we analyze the influence of relative height and lateral position of workpieces as well as orientation of tool center points on finding valid grips. From these results, we deduce heuristic functions, which can be used to improve the aforementioned heuristic search algorithms. Being able to reduce the calculation time for grip determination reduces overall cycle time and therefore makes bin picking more applicable for the producing industry.