IEICE TRANSACTIONS on Information
SPSD: Semantics and Deep Reinforcement Learning Based Motion Planning for Supermarket Robot
Summary :
Robot motion planning is an important part of the unmanned supermarket. The challenges of motion planning in supermarkets lie in the diversity of the supermarket environment, the complexity of obstacle movement, the vastness of the search space. This paper proposes an adaptive Search and Path planning method based on the Semantic information and Deep reinforcement learning (SPSD), which effectively improves the autonomous decision-making ability of supermarket robots. Firstly, based on the backbone of deep reinforcement learning (DRL), supermarket robots process real-time information from multi-modality sensors to realize high-speed and collision-free motion planning. Meanwhile, in order to solve the problem caused by the uncertainty of the reward in the deep reinforcement learning, common spatial semantic relationships between landmarks and target objects are exploited to define reward function. Finally, dynamics randomization is introduced to improve the generalization performance of the algorithm in the training. The experimental results show that the SPSD algorithm is excellent in the three indicators of generalization performance, training time and path planning length. Compared with other methods, the training time of SPSD is reduced by 27.42% at most, the path planning length is reduced by 21.08% at most, and the trained network of SPSD can be applied to unfamiliar scenes safely and efficiently. The results are motivating enough to consider the application of the proposed method in practical scenes. We have uploaded the video of the results of the experiment to https://www.youtube.com/watch?v=h1wLpm42NZk.
- Publication
- IEICE TRANSACTIONS on Information Vol.E106-D No.5 pp.765-772
- Publication Date
- 2023/05/01
- Publicized
- 2022/09/15
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2022DLP0057
- Type of Manuscript
- Special Section PAPER (Special Section on Deep Learning Technologies: Architecture, Optimization, Techniques, and Applications)
- Category
- Positioning and Navigation
Authors
Jialun CAI
Peking University
Weibo HUANG
Peking University
Yingxuan YOU
Peking University
Zhan CHEN
Peking University
Bin REN
University of Trento
Hong LIU
Peking University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Jialun CAI, Weibo HUANG, Yingxuan YOU, Zhan CHEN, Bin REN, Hong LIU, "SPSD: Semantics and Deep Reinforcement Learning Based Motion Planning for Supermarket Robot" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 5, pp. 765-772, May 2023, doi: 10.1587/transinf.2022DLP0057.
Abstract: Robot motion planning is an important part of the unmanned supermarket. The challenges of motion planning in supermarkets lie in the diversity of the supermarket environment, the complexity of obstacle movement, the vastness of the search space. This paper proposes an adaptive Search and Path planning method based on the Semantic information and Deep reinforcement learning (SPSD), which effectively improves the autonomous decision-making ability of supermarket robots. Firstly, based on the backbone of deep reinforcement learning (DRL), supermarket robots process real-time information from multi-modality sensors to realize high-speed and collision-free motion planning. Meanwhile, in order to solve the problem caused by the uncertainty of the reward in the deep reinforcement learning, common spatial semantic relationships between landmarks and target objects are exploited to define reward function. Finally, dynamics randomization is introduced to improve the generalization performance of the algorithm in the training. The experimental results show that the SPSD algorithm is excellent in the three indicators of generalization performance, training time and path planning length. Compared with other methods, the training time of SPSD is reduced by 27.42% at most, the path planning length is reduced by 21.08% at most, and the trained network of SPSD can be applied to unfamiliar scenes safely and efficiently. The results are motivating enough to consider the application of the proposed method in practical scenes. We have uploaded the video of the results of the experiment to https://www.youtube.com/watch?v=h1wLpm42NZk.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022DLP0057/_p
Copy
@ARTICLE{e106-d_5_765,
author={Jialun CAI, Weibo HUANG, Yingxuan YOU, Zhan CHEN, Bin REN, Hong LIU, },
journal={IEICE TRANSACTIONS on Information},
title={SPSD: Semantics and Deep Reinforcement Learning Based Motion Planning for Supermarket Robot},
year={2023},
volume={E106-D},
number={5},
pages={765-772},
abstract={Robot motion planning is an important part of the unmanned supermarket. The challenges of motion planning in supermarkets lie in the diversity of the supermarket environment, the complexity of obstacle movement, the vastness of the search space. This paper proposes an adaptive Search and Path planning method based on the Semantic information and Deep reinforcement learning (SPSD), which effectively improves the autonomous decision-making ability of supermarket robots. Firstly, based on the backbone of deep reinforcement learning (DRL), supermarket robots process real-time information from multi-modality sensors to realize high-speed and collision-free motion planning. Meanwhile, in order to solve the problem caused by the uncertainty of the reward in the deep reinforcement learning, common spatial semantic relationships between landmarks and target objects are exploited to define reward function. Finally, dynamics randomization is introduced to improve the generalization performance of the algorithm in the training. The experimental results show that the SPSD algorithm is excellent in the three indicators of generalization performance, training time and path planning length. Compared with other methods, the training time of SPSD is reduced by 27.42% at most, the path planning length is reduced by 21.08% at most, and the trained network of SPSD can be applied to unfamiliar scenes safely and efficiently. The results are motivating enough to consider the application of the proposed method in practical scenes. We have uploaded the video of the results of the experiment to https://www.youtube.com/watch?v=h1wLpm42NZk.},
keywords={},
doi={10.1587/transinf.2022DLP0057},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - SPSD: Semantics and Deep Reinforcement Learning Based Motion Planning for Supermarket Robot
T2 - IEICE TRANSACTIONS on Information
SP - 765
EP - 772
AU - Jialun CAI
AU - Weibo HUANG
AU - Yingxuan YOU
AU - Zhan CHEN
AU - Bin REN
AU - Hong LIU
PY - 2023
DO - 10.1587/transinf.2022DLP0057
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2023
AB - Robot motion planning is an important part of the unmanned supermarket. The challenges of motion planning in supermarkets lie in the diversity of the supermarket environment, the complexity of obstacle movement, the vastness of the search space. This paper proposes an adaptive Search and Path planning method based on the Semantic information and Deep reinforcement learning (SPSD), which effectively improves the autonomous decision-making ability of supermarket robots. Firstly, based on the backbone of deep reinforcement learning (DRL), supermarket robots process real-time information from multi-modality sensors to realize high-speed and collision-free motion planning. Meanwhile, in order to solve the problem caused by the uncertainty of the reward in the deep reinforcement learning, common spatial semantic relationships between landmarks and target objects are exploited to define reward function. Finally, dynamics randomization is introduced to improve the generalization performance of the algorithm in the training. The experimental results show that the SPSD algorithm is excellent in the three indicators of generalization performance, training time and path planning length. Compared with other methods, the training time of SPSD is reduced by 27.42% at most, the path planning length is reduced by 21.08% at most, and the trained network of SPSD can be applied to unfamiliar scenes safely and efficiently. The results are motivating enough to consider the application of the proposed method in practical scenes. We have uploaded the video of the results of the experiment to https://www.youtube.com/watch?v=h1wLpm42NZk.
ER -
English
