Deep Learning Based Local Path Planning Method for Moving Robots

doi:10.16182/j.issn1004731x.joss.22-1546

Abstract

Abstract:

In order to integrate visual information into the robot navigation process, improve the robot's recognition rate of various types of obstacles, and reduce the occurrence of dangerous events, a local path planning network based on two-dimensional CNN and LSTM is designed, and a local path planning approach based on deep learning is proposed. The network uses the image from camera and the global path to generate the current steering angle required for obstacle avoidance and navigation. A simulated indoor scene is built for training and validating the network. A path evaluation method that uses the total length and the average curvature change rate of path and the distance between robot and obstacle as metrics is also proposed. Experiments show that the proposed approach has good local path generation capability in both simulated and real scenes.

Key words: robot navigation, path planning, real-time obstacle avoidance, deep learning

CLC Number:

TP391.9

Liu Zesen, Bi Sheng, Guo Chuanhong, Wang Yankui, Dong Min. Deep Learning Based Local Path Planning Method for Moving Robots[J]. Journal of System Simulation, 2024, 36(5): 1199-1210.

Figures/Tables 13

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Fig. 8

Fig. 9

Fig. 10

Table 1

Fig. 11

Fig. 12

References 19

1	Hornung Armin, Phillips M, Gil Jones E, et al. Navigation in Three-dimensional Cluttered Environments for Mobile Manipulation[C]//2012 IEEE International Conference on Robotics and Automation. Piscataway, NJ, USA: IEEE, 2012: 423-429.
2	晋晓飞, 王浩, 宗卫佳, 等. 自主移动机器人避障技术研究现状[J]. 传感器与微系统, 2018, 37(5): 5-9.
	Jin Xiaofei, Wang Hao, Zong Weijia, et al. Research Status of Obstacle Avoidance Technologies for Autonomous Mobile Robots[J]. Transducer and Microsystem Technologies, 2018, 37(5): 5-9.
3	Lee H Y, Ho H W, Zhou Y. Deep Learning-based Monocular Obstacle Avoidance for Unmanned Aerial Vehicle Navigation in Tree Plantations[J]. Journal of Intelligent & Robotic Systems, 2021, 101(1): 5.
4	Sina Sharif Mansouri, Karvelis Petros, Kanellakis Christoforos, et al. Vision-based MAV Navigation in Underground Mine Using Convolutional Neural Network[C]//IECON 2019-45th Annual Conference of the IEEE Industrial Electronics Society. Piscataway, NJ, USA: IEEE, 2019: 750-755.
5	Manderson Travis, Juan Camilo Gamboa Higuera, Cheng Ran, et al. Vision-based Autonomous Underwater Swimming in Dense Coral for Combined Collision Avoidance and Target Selection[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway, NJ, USA: IEEE, 2018: 1885-1891.
6	Loquercio Antonio, Maqueda Ana I, del-Blanco Carlos R, et al. DroNet: Learning to Fly by Driving[J]. IEEE Robotics and Automation Letters, 2018, 3(2): 1088-1095.
7	Tai Lei, Li Shaohua, Liu Ming. A Deep-network Solution Towards Model-less Obstacle Avoidance[C]//2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway, NJ, USA: IEEE, 2016: 2759-2764.
8	Liu Canglong, Zheng Bin, Wang Chunyang, et al. CNN-based Vision Model for Obstacle Avoidance of Mobile Robot[C]//2017 3rd International Conference on Mechanical, Electronic and Information Technology Engineering. France: EDP Sciences, 2017: 7.
9	金彦亮, 朱容廷. 机器人端到端视觉避障方法研究[J]. 工业控制计算机, 2019, 32(9): 77-79.
	Jin Yanliang, Zhu Rongting. Research on Robot End-to-end Visual Obstacle Avoidance Method[J]. Industrial Control Computer, 2019, 32(9): 77-79.
10	Michels J, Saxena A, Ng A Y. High Speed Obstacle Avoidance Using Monocular Vision and Reinforcement Learning[C]//Proceedings of the 22nd International conference on Machine learning. New York, NY, USA: Association for Computing Machinery, 2005: 593-600.
11	Xie L, Wang S, Markham A, et al. Towards Monocular Vision Based Obstacle Avoidance Through Deep Reinforcement Learning[C]//Robotics: Science and Systems (RSS 2017) Workshop. Boston, MA, USA: MIT, 2017: 1-6.
12	Guldenring Ronja, Görner Michael, Hendrich Norman, et al. Learning Local Planners for Human-aware Navigation in Indoor Environments[C]//2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway, NJ, USA: IEEE, 2020: 6053-6060.
13	Craig Coulter R. Implementation of the Pure Pursuit Path Tracking Algorithm: CMU-RI-TR-92-01[R]. Pittsburgh, PA, USA: Carnegie Mellon University, 1992: 1-15.
14	Zhang Chao, Yang Zichao, He Xiaodong, et al. Multimodal Intelligence: Representation Learning, Information Fusion, and Applications[J]. IEEE Journal of Selected Topics in Signal Processing, 2020, 14(3): 478-493.
15	Hochreiter Sepp, Schmidhuber Jürgen. Long Short-term Memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
16	Koenig N, Howard A. Design and Use Paradigms for Gazebo, an Open-source Multi-robot Simulator[C]//2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway, NJ, USA: IEEE, 2004: 2149-2154.
17	Liu Yuzhou, Novotny Georg, Smirnov Nikita, et al. Mobile Delivery Robots: Mixed Reality-based Simulation Relying on ROS and Unity 3D[C]//2020 IEEE Intelligent Vehicles Symposium (IV). Piscataway, NJ, USA: IEEE, 2020: 15-20.
18	Katara Pushkal, Khanna Mukul, Nagar Harshit, et al. Open Source Simulator for Unmanned Underwater Vehicles Using ROS and Unity3D[C]//2019 IEEE Underwater Technology (UT). Piscataway, NJ, USA: IEEE, 2019: 1-7.
19	Konrad A. Simulation of Mobile Robots with Unity and Ros: A Case-study and a Comparison with Gazebo[D]. Trollhättan, Sweden: University West, 2019.

指标	测试路线1		测试路线2		测试路线3		测试路线4		测试路线5
指标	TEB	DL	TEB	DL	TEB	DL	TEB	DL	TEB	DL
长度/m	7.35	7.91	5.77	6.23	6.71	7.25	4.52	4.29	2.86	2.54
平均曲率变化率	0.29	0.41	0.37	0.40	0.18	0.37	0.26	0.26	0.33	0.39
最近障碍物/m	0.44	0.36	0.42	0.30	0.42	0.90	n/a	n/a	n/a	n/a

[1]	Lei Xu, Chen Jingyi, Chen Xiaoyang. Research on Path Planning of Warehouse Robot with Improved Harris Hawks Algorithm [J]. Journal of System Simulation, 2024, 36(5): 1081-1092.
[2]	Xiao Peng, Xie Feng, Ni Haihong, Zhang Min, Tang Zhili, Li Ni. Research on Collaborative Optimization Method of Multi-UAV Task Allocation and Path Planning [J]. Journal of System Simulation, 2024, 36(5): 1141-1151.
[3]	Wang Xiaokang, Ji Jie, Liu Yang, He Qing. Path Planning of Unmanned Delivery Vehicle Based on Improved Q-learning Algorithm [J]. Journal of System Simulation, 2024, 36(5): 1211-1221.
[4]	Jiang Zhaozhen, Wang Wenlong, Sun Wenqi. Path Planning Rapid Algorithm Based on Modified RRT* for Unmanned Surface Vessel [J]. Journal of System Simulation, 2024, 36(4): 888-900.
[5]	Zhang Rui, Zhou Li, Liu Zhengyang. Dynamic Path Planning for Mobile Robot Based on RRT* and Dynamic Window Approach [J]. Journal of System Simulation, 2024, 36(4): 957-968.
[6]	Wei Jinyang, Wang Keping, Yang Yi, Fei Shumin. Incremental Image Dehazing Algorithm Based on Multiple Transfer Attention [J]. Journal of System Simulation, 2024, 36(4): 969-980.
[7]	Li Gaoyang, Li Xiangfeng, Zhao Kang, Jin Yuchao, Yi Zhidong, Zuo Dunwen. Three-Dimensional Path Planning of UAV Based on All Particles Driving Wild Horse Optimizer Algorithm [J]. Journal of System Simulation, 2024, 36(3): 595-607.
[8]	Yu Xiang, Jiang Chen, Duan Sirui, Deng Qianrui. Path Planning for Improvement of A* Algorithm and Artificial Potential Field Method [J]. Journal of System Simulation, 2024, 36(3): 782-794.
[9]	Tang Yunchao, Qi Shaojun, Zhu Lixue, Zhuo Xianrong, Zhang Yunqi, Meng Fan. Obstacle Avoidance Motion in Mobile Robotics [J]. Journal of System Simulation, 2024, 36(1): 1-26.
[10]	Li Chen, He Ming, Dong Chen, Li Wei. Action Recognition Model of Directed Attention Based on Cosine Similarity [J]. Journal of System Simulation, 2024, 36(1): 67-82.
[11]	Chen Dejun, Fang Zihao, Zeng Yunxiu, Xu Kai. Deceptive Path Planning in Fog of War [J]. Journal of System Simulation, 2023, 35(9): 1895-1908.
[12]	Li Wenjing, Luo Yanlin, Wang Yuhui, Zhu Li. Virtual Navigation Path Planning Based on Octree Potential Field for Endonasal Endoscope [J]. Journal of System Simulation, 2023, 35(9): 2054-2063.
[13]	Zhang Fengquan, Cao Duo, Ma Xiaohan, Chen Baijun, Zhang Jiangxiao. Style Transfer Network for Generating Opera Makeup Details [J]. Journal of System Simulation, 2023, 35(9): 2064-2076.
[14]	Junqiang Lin, Hongjun Wang, Xiangjun Zou, Po Zhang, Chengen Li, Yipeng Zhou, Shujie Yao. Obstacle Avoidance Path Planning and Simulation of Mobile Picking Robot Based on DPPO [J]. Journal of System Simulation, 2023, 35(8): 1692-1704.
[15]	Laiyi Yang, Jing Bi, Haitao Yuan. Intelligent Path Planning for Mobile Robots Based on SAC Algorithm [J]. Journal of System Simulation, 2023, 35(8): 1726-1736.