移動ロボットが選択する将来の軌道が歩行者に与える影響を考慮した歩行者軌道予測

Abstract

In environments where humans coexist with mobile robots, there is a desire to improve both safety and efficiency of movement. If the impact of a robot’s actions on humans can be anticipated in advance, mobile robots should be able to intentionally choose the optimal actions for both themselves and humans. In this paper, we propose a machine learning approach to predict how pedestrians’ trajectories change based on the future paths selected by mobile robots.