Optimal Robot Motion Planning in Constrained Workspaces Using Reinforcement Learning

被引：12

作者：

Rousseas, Panagiotis ^{[1
]}

Bechlioulis, Charalampos P. ^{[1
]}

Kyriakopoulos, Kostas J. ^{[1
]}

机构：

[1] Natl Tech Univ Athens, Sch Mech Engn, Control Syst Lab, Athens, Greece

来源：

2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) | 2020年

关键词：

TIME OBSTACLE AVOIDANCE; PIANO MOVERS PROBLEM; NAVIGATION;

D O I：

10.1109/IROS45743.2020.9341148

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this work, a novel solution to the optimal motion planning problem is proposed, through a continuous, deterministic and provably correct approach, with guaranteed safety and which is based on a parametrized Artificial Potential Field (APF). In particular, Reinforcement Learning (RL) is applied to adjust appropriately the parameters of the underlying potential field towards minimizing the Hamilton-Jacobi-Bellman (HJB) error. The proposed method, outperforms consistently a Rapidly-exploring Random Trees (RRT*) method and consists a fertile advancement in the optimal motion planning problem.

引用

页码：6917 / 6922

页数：6

共 50 条

[31] XCS-based reinforcement learning algorithm for motion planning of a spherical mobile robot
M. Roozegar
M. J. Mahjoob
M. J. Esfandyari
M. Shariat Panahi
Applied Intelligence, 2016, 45 : 736 - 746
[32] A General Framework of Motion Planning for Redundant Robot Manipulator Based on Deep Reinforcement Learning
Li, Xiangjian
Liu, Huashan
Dong, Menghua
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2022, 18 (08) : 5253 - 5263
[33] Motion planning of redundant robot manipulators using constrained optimization: a parallel approach
Chen, CL
Lin, CJ
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART I-JOURNAL OF SYSTEMS AND CONTROL ENGINEERING, 1998, 212 (I4) : 281 - 292
[34] XCS-based reinforcement learning algorithm for motion planning of a spherical mobile robot
Roozegar, M.
Mahjoob, M. J.
Esfandyari, M. J.
Panahi, M. Shariat
APPLIED INTELLIGENCE, 2016, 45 (03) : 736 - 746
[35] An Improved Approach for Inverse Kinematics and Motion Planning of an Industrial Robot Manipulator with Reinforcement Learning
Weber, Jan
Schmidt, Marco
2021 FIFTH IEEE INTERNATIONAL CONFERENCE ON ROBOTIC COMPUTING (IRC 2021), 2021, : 10 - 17
[36] Constrained Robot Motion Planning: Imbalanced Jacobian Algorithm vs. Optimal Control Approach
Janiak, Mariusz
Tchon, Krzysztof
2010 15TH INTERNATIONAL CONFERENCE ON METHODS AND MODELS IN AUTOMATION AND ROBOTICS (MMAR), 2010, : 25 - 30
[37] Constrained robot motion planning: Imbalanced jacobian algorithm vs. optimal control approach
Institute of Computer Engineering, Control and Robotics, Wroclaw Institute of Technology, Wroclaw, Poland
Int. Conf. Methods Models Autom. Rob., MMAR, (25-30):
[38] Task constrained motion planning in robot joint space
Stilman, Mike
2007 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-9, 2007, : 3080 - 3087
[39] Reactive motion planning of manipulator by distributed learning agents using reinforcement learning
Naruse, Keitarou
Kakazu, Yukinori
Nippon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C, 1995, 61 (581): : 131 - 137
[40] A direct variational method for planning monotonically optimal paths for redundant manipulators in constrained workspaces
Shukla, Ashwini
Singla, Ekta
Wahi, Pankaj
Dasgupta, Bhaskar
ROBOTICS AND AUTONOMOUS SYSTEMS, 2013, 61 (02) : 209 - 220

← 1 2 3 4 5 →