TY - JOUR
T1 - Deep Reinforcement Learning Based Trajectory Planning Under Uncertain Constraints
AU - Chen, Lienhung
AU - Jiang, Zhongliang
AU - Cheng, Long
AU - Knoll, Alois C.
AU - Zhou, Mingchuan
N1 - Publisher Copyright:
Copyright © 2022 Chen, Jiang, Cheng, Knoll and Zhou.
PY - 2022/5/2
Y1 - 2022/5/2
N2 - With the advance in algorithms, deep reinforcement learning (DRL) offers solutions to trajectory planning under uncertain environments. Different from traditional trajectory planning which requires lots of effort to tackle complicated high-dimensional problems, the recently proposed DRL enables the robot manipulator to autonomously learn and discover optimal trajectory planning by interacting with the environment. In this article, we present state-of-the-art DRL-based collision-avoidance trajectory planning for uncertain environments such as a safe human coexistent environment. Since the robot manipulator operates in high dimensional continuous state-action spaces, model-free, policy gradient-based soft actor-critic (SAC), and deep deterministic policy gradient (DDPG) framework are adapted to our scenario for comparison. In order to assess our proposal, we simulate a 7-DOF Panda (Franka Emika) robot manipulator in the PyBullet physics engine and then evaluate its trajectory planning with reward, loss, safe rate, and accuracy. Finally, our final report shows the effectiveness of state-of-the-art DRL algorithms for trajectory planning under uncertain environments with zero collision after 5,000 episodes of training.
AB - With the advance in algorithms, deep reinforcement learning (DRL) offers solutions to trajectory planning under uncertain environments. Different from traditional trajectory planning which requires lots of effort to tackle complicated high-dimensional problems, the recently proposed DRL enables the robot manipulator to autonomously learn and discover optimal trajectory planning by interacting with the environment. In this article, we present state-of-the-art DRL-based collision-avoidance trajectory planning for uncertain environments such as a safe human coexistent environment. Since the robot manipulator operates in high dimensional continuous state-action spaces, model-free, policy gradient-based soft actor-critic (SAC), and deep deterministic policy gradient (DDPG) framework are adapted to our scenario for comparison. In order to assess our proposal, we simulate a 7-DOF Panda (Franka Emika) robot manipulator in the PyBullet physics engine and then evaluate its trajectory planning with reward, loss, safe rate, and accuracy. Finally, our final report shows the effectiveness of state-of-the-art DRL algorithms for trajectory planning under uncertain environments with zero collision after 5,000 episodes of training.
KW - collision avoidance
KW - neural networks
KW - reinforcement learning
KW - robotics
KW - trajectory planning
KW - uncertain environment
UR - http://www.scopus.com/inward/record.url?scp=85130018027&partnerID=8YFLogxK
U2 - 10.3389/fnbot.2022.883562
DO - 10.3389/fnbot.2022.883562
M3 - Article
AN - SCOPUS:85130018027
SN - 1662-5218
VL - 16
JO - Frontiers in Neurorobotics
JF - Frontiers in Neurorobotics
M1 - 883562
ER -