Legibility of robot approach trajectories with minimum jerk path planning

When a robot approaches a person, the chosen trajectory ideally informs the person not only about the robot’s intended target location, but also its intended orientation. However, planning a straight line to the goal location does not guarantee a correct final orientation, potentially causing confusion as the robot eventually rotates towards its unsuspecting target. One method that could remedy this problem is minimum jerk path planning, which results in the smoothest possible path that ends in the pre-specified final orientation. The technique is already widely used in robotic arm motion planning, but existing work is lacking for regular path planning. The aim of the current study is to implement minimum jerk path planning for the Nao robot and to evaluate the potential benefit for human observers to infer the intended target of the robot. Results show that minimum jerk path planning significantly improves people’s recognition of the robot’s destination compared to straight line path planning. Meanwhile, the perceived likeability and human likeness of the robot remain the same, suggesting that implementing smooth robot path planning that includes the final orientation leads to more predictable robot approaching behaviour.

Keywords
Human-aware navigation Path planning Robot intention Human-robot interaction