Benchmark tools for evaluating AGVs at industrial environments

The paper addresses the problem of evaluating AGVs with different degrees of autonomy by defining benchmark tools to grade the performance of each approach. Based on the proposed benchmark, different experiments have been performed from manual driving to autonomous navigation, at different velocities and a scenario containing wide and narrow corridors, small and large isles, rooms, slalom-like parts requiring zig-zag maneuvering and static objects. However, this benchmark is also applicable to dynamic environments, including moving objects and other vehicles. In particular, experiments have been used for evaluating the performance of AGVs, in terms of robustness, efficiency, safety and comfortability. The underlying objective is to evaluate the potential advantages of manual-assisted driving as well as autonomous navigation against standard manual driving. To obtain valid and significant results, more than 180 experiments have been carried out on each approach.