TY - JOUR
T1 - Robot-Assisted Pedestrian Regulation Based on Deep Reinforcement Learning
AU - Wan, Zhiqiang
AU - Jiang, Chao
AU - Fahad, Muhammad
AU - Ni, Zhen
AU - Guo, Yi
AU - He, Haibo
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2020/4
Y1 - 2020/4
N2 - Pedestrian regulation can prevent crowd accidents and improve crowd safety in densely populated areas. Recent studies use mobile robots to regulate pedestrian flows for desired collective motion through the effect of passive human-robot interaction (HRI). This paper formulates a robot motion planning problem for the optimization of two merging pedestrian flows moving through a bottleneck exit. To address the challenge of feature representation of complex human motion dynamics under the effect of HRI, we propose using a deep neural network to model the mapping from the image input of pedestrian environments to the output of robot motion decisions. The robot motion planner is trained end-to-end using a deep reinforcement learning algorithm, which avoids hand-crafted feature detection and extraction, thus improving the learning capability for complex dynamic problems. Our proposed approach is validated in simulated experiments, and its performance is evaluated. The results demonstrate that the robot is able to find optimal motion decisions that maximize the pedestrian outflow in different flow conditions, and the pedestrian-accumulated outflow increases significantly compared to cases without robot regulation and with random robot motion.
AB - Pedestrian regulation can prevent crowd accidents and improve crowd safety in densely populated areas. Recent studies use mobile robots to regulate pedestrian flows for desired collective motion through the effect of passive human-robot interaction (HRI). This paper formulates a robot motion planning problem for the optimization of two merging pedestrian flows moving through a bottleneck exit. To address the challenge of feature representation of complex human motion dynamics under the effect of HRI, we propose using a deep neural network to model the mapping from the image input of pedestrian environments to the output of robot motion decisions. The robot motion planner is trained end-to-end using a deep reinforcement learning algorithm, which avoids hand-crafted feature detection and extraction, thus improving the learning capability for complex dynamic problems. Our proposed approach is validated in simulated experiments, and its performance is evaluated. The results demonstrate that the robot is able to find optimal motion decisions that maximize the pedestrian outflow in different flow conditions, and the pedestrian-accumulated outflow increases significantly compared to cases without robot regulation and with random robot motion.
KW - Deep reinforcement learning (DRL)
KW - human-robot interaction (HRI)
KW - pedestrian flow regulation
UR - http://www.scopus.com/inward/record.url?scp=85057148773&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85057148773&partnerID=8YFLogxK
U2 - 10.1109/TCYB.2018.2878977
DO - 10.1109/TCYB.2018.2878977
M3 - Article
C2 - 30475740
AN - SCOPUS:85057148773
SN - 2168-2267
VL - 50
SP - 1669
EP - 1682
JO - IEEE Transactions on Cybernetics
JF - IEEE Transactions on Cybernetics
IS - 4
M1 - 8540942
ER -