Multi-layer perceptron-particle swarm optimization: A lightweight optimization algorithm for the model predictive control local planner

The model predictive control trajectory planner is a popular and effective robot local motion planner. However, it is challenging to satisfy real-time requirements and implement them on embedded platforms due to their high complexity of solving and reliance on optimization solvers. This letter repor...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoqing Guan, Tao Hu, Ziang Zhang, Yixu Wang, Yifan Liu, You Wang, Jie Hao, Guang Li
Format: Article
Language:English
Published: SAGE Publishing 2024-11-01
Series:International Journal of Advanced Robotic Systems
Online Access:https://doi.org/10.1177/17298806241301581
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850138100026572800
author Xiaoqing Guan
Tao Hu
Ziang Zhang
Yixu Wang
Yifan Liu
You Wang
Jie Hao
Guang Li
author_facet Xiaoqing Guan
Tao Hu
Ziang Zhang
Yixu Wang
Yifan Liu
You Wang
Jie Hao
Guang Li
author_sort Xiaoqing Guan
collection DOAJ
description The model predictive control trajectory planner is a popular and effective robot local motion planner. However, it is challenging to satisfy real-time requirements and implement them on embedded platforms due to their high complexity of solving and reliance on optimization solvers. This letter reports a lightweight and efficient two-stage solving algorithm for the model predictive control planner. Firstly, the general form of the model predictive control local planning problem was specified and simplified by the motion primitives. Then, a two-stage solving method of multi-layer perceptron pre-solving and particle swarm optimization re-optimizing is developed after splitting the cost function into two pieces. An multi-layer perceptron neural network was designed and trained offline to learn the solution of the model predictive control local planner without considering obstacles after selecting the inputs and outputs. Next, to accomplish obstacle avoidance, the particle swarm optimization algorithm re-optimizes the trajectory based on the outputs of the neural network. The experiment results demonstrate that the multi-layer perceptron-particle swarm optimization algorithm can quickly and accurately solve local planning problems, guiding robots to complete global paths with the same efficiency as expert solvers. The average solving time has been reduced by over 90%, enabling the robot to increase its control frequency or adopt higher-quality complex motion primitives. The multi-layer perceptron-particle swarm optimization algorithm can also be used for various robots and motion primitives, with a wide range of potential applications.
format Article
id doaj-art-c8325ddaacab49aba78ea2afa4a4f614
institution OA Journals
issn 1729-8814
language English
publishDate 2024-11-01
publisher SAGE Publishing
record_format Article
series International Journal of Advanced Robotic Systems
spelling doaj-art-c8325ddaacab49aba78ea2afa4a4f6142025-08-20T02:30:39ZengSAGE PublishingInternational Journal of Advanced Robotic Systems1729-88142024-11-012110.1177/17298806241301581Multi-layer perceptron-particle swarm optimization: A lightweight optimization algorithm for the model predictive control local plannerXiaoqing Guan0Tao Hu1Ziang Zhang2Yixu Wang3Yifan Liu4You Wang5Jie Hao6Guang Li7 State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, , Hangzhou, China State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, , Hangzhou, China State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, , Hangzhou, China State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, , Hangzhou, China State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, , Hangzhou, China State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, , Hangzhou, China Rotunbot (Hangzhou) Technology Co. Ltd., Hangzhou, China State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, , Hangzhou, ChinaThe model predictive control trajectory planner is a popular and effective robot local motion planner. However, it is challenging to satisfy real-time requirements and implement them on embedded platforms due to their high complexity of solving and reliance on optimization solvers. This letter reports a lightweight and efficient two-stage solving algorithm for the model predictive control planner. Firstly, the general form of the model predictive control local planning problem was specified and simplified by the motion primitives. Then, a two-stage solving method of multi-layer perceptron pre-solving and particle swarm optimization re-optimizing is developed after splitting the cost function into two pieces. An multi-layer perceptron neural network was designed and trained offline to learn the solution of the model predictive control local planner without considering obstacles after selecting the inputs and outputs. Next, to accomplish obstacle avoidance, the particle swarm optimization algorithm re-optimizes the trajectory based on the outputs of the neural network. The experiment results demonstrate that the multi-layer perceptron-particle swarm optimization algorithm can quickly and accurately solve local planning problems, guiding robots to complete global paths with the same efficiency as expert solvers. The average solving time has been reduced by over 90%, enabling the robot to increase its control frequency or adopt higher-quality complex motion primitives. The multi-layer perceptron-particle swarm optimization algorithm can also be used for various robots and motion primitives, with a wide range of potential applications.https://doi.org/10.1177/17298806241301581
spellingShingle Xiaoqing Guan
Tao Hu
Ziang Zhang
Yixu Wang
Yifan Liu
You Wang
Jie Hao
Guang Li
Multi-layer perceptron-particle swarm optimization: A lightweight optimization algorithm for the model predictive control local planner
International Journal of Advanced Robotic Systems
title Multi-layer perceptron-particle swarm optimization: A lightweight optimization algorithm for the model predictive control local planner
title_full Multi-layer perceptron-particle swarm optimization: A lightweight optimization algorithm for the model predictive control local planner
title_fullStr Multi-layer perceptron-particle swarm optimization: A lightweight optimization algorithm for the model predictive control local planner
title_full_unstemmed Multi-layer perceptron-particle swarm optimization: A lightweight optimization algorithm for the model predictive control local planner
title_short Multi-layer perceptron-particle swarm optimization: A lightweight optimization algorithm for the model predictive control local planner
title_sort multi layer perceptron particle swarm optimization a lightweight optimization algorithm for the model predictive control local planner
url https://doi.org/10.1177/17298806241301581
work_keys_str_mv AT xiaoqingguan multilayerperceptronparticleswarmoptimizationalightweightoptimizationalgorithmforthemodelpredictivecontrollocalplanner
AT taohu multilayerperceptronparticleswarmoptimizationalightweightoptimizationalgorithmforthemodelpredictivecontrollocalplanner
AT ziangzhang multilayerperceptronparticleswarmoptimizationalightweightoptimizationalgorithmforthemodelpredictivecontrollocalplanner
AT yixuwang multilayerperceptronparticleswarmoptimizationalightweightoptimizationalgorithmforthemodelpredictivecontrollocalplanner
AT yifanliu multilayerperceptronparticleswarmoptimizationalightweightoptimizationalgorithmforthemodelpredictivecontrollocalplanner
AT youwang multilayerperceptronparticleswarmoptimizationalightweightoptimizationalgorithmforthemodelpredictivecontrollocalplanner
AT jiehao multilayerperceptronparticleswarmoptimizationalightweightoptimizationalgorithmforthemodelpredictivecontrollocalplanner
AT guangli multilayerperceptronparticleswarmoptimizationalightweightoptimizationalgorithmforthemodelpredictivecontrollocalplanner