Open AccessReal-Robot Friendly Passing Motion Planner for Autonomous Navigation in Crowds
Author(s) -
Shun Niijima,
Yoko Sasaki,
Hiroshi Mizoguchi
Publication year - 2022
Publication title -
transactions on machine learning and artificial intelligence
Language(s) - English
Resource type - Journals
ISSN - 2054-7390
DOI - 10.14738/tmlai.101.11616
Subject(s) - crowds , computer science , robot , computer vision , artificial intelligence , acceleration , mobile robot , motion (physics) , feature (linguistics) , planner , mobile robot navigation , pedestrian , simulation , real time computing , human–computer interaction , robot control , engineering , linguistics , philosophy , physics , computer security , classical mechanics , transport engineering
This study proposes a real‐robot friendly passing motion planner to be used in crowds. The proposed method learns to pass pedestrians with smooth acceleration and deceleration by using passing motion learning. A key feature of the proposed method is that it is trained on a simple crowd simulation with both dynamic and stationary pedestrians. The learned passing behaviour can be used directly in autonomous navigation. Evaluations using the crowd simulations indicate that the proposed method outperforms the existing ones in terms of success rate, arrival time, and keeping a certain distance from the pedestrians. The proposed navigation framework is implemented on a mobile robot and demonstrated its successful navigation between pedestrians in a science museum.