Abstract
This work proposed an improved Gaussian pseudospectral optimization data-driven neural network trajectory planning algorithm to shorten the planning time and improve the speed of obstacle avoidance trajectory. Firstly, the obstacle avoidance trajectory planning optimal control problem is established by deriving the kinematics model of unmanned vehicle and obstacle model. Gaussian pseudospectral optimization is then derived in detail to tackle the infinite time optimal control problem (OCP) and obtain the obstacle avoidance optimization data. By using the neural network training data set, an intelligent planning method for on-line calculation of obstacle avoidance trajectory is designed. Simulation results show that the proposed method can efficiently decrease trajectory planning time.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wang H, Wang B, Liu B et al (2016) Pedestrian recognition and tracking using 3D LiDAR for autonomous vehicle. Robot Auton Syst 88:71–78
Shi P, Liu Z, Liu G (2022) Local path planning of unmanned vehicles based on improved RRT algorithm. In: Presented at the 2022 4th Asia Pacific information technology conference
Oleksak K, Wu Y, Abella M et al (2021) Trajectory optimization of unmanned aerial vehicles for wireless communication with ground terminals. In: AIAA Scitech 2021 forum, Shanghai
Shibata K, Shibata N, Nonaka K et al (2018) Model predictive obstacle avoidance control for vehicles with automatic velocity suppression using artificial potential field. IFAC-PapersOnLine 51(20):313–318
Li Y, Chen W, Yang L (2021) Multistage linear Gauss pseudospectral method for piecewise continuous nonlinear optimal control problems. IEEE Trans Aerosp Electron Syst 57(4):2298–2310
Wei K (2010) Rate of convergence for the Legendre pseudospectral optimal control of feedback linearizable systems. J Control Theory Appl 8(4):391–405
Xu Z, Shi P, Zhao Y (2015) Optimal reconfiguration control of electromagnetic spacecraft formation using Gauss pseudospectral method. In: 2015 2nd international conference on information science and control engineering, Virtual Event
Kang CM, Lee SH, Chung CC (2018) Multirate lane-keeping system with kinematic vehicle model. IEEE Trans Veh Technol 67(10):9211–9222
Long X, Jiong Y, Xinggao L et al (2017) An effective simultaneous approach with variable time nodes for dynamic optimization problems. Eng Optim 49(10):1761–1776
Loxton R, Teo KL, Rehbock V (2011) Robust suboptimal control of nonlinear systems. Appl Math Comput 217(14):6566–6576
Acknowledgements
This work was supported by the National key R&D program (No. 2022YFE0101000).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, T., Tan, C., Liu, P., Bian, M. (2023). Gaussian Pseudospectral Optimization-Driven Neural Network Planning of Obstacle Avoidance Trajectory. In: Park, J.S., Yang, L.T., Pan, Y., Park, J.H. (eds) Advances in Computer Science and Ubiquitous Computing. CUTECSA 2022. Lecture Notes in Electrical Engineering, vol 1028. Springer, Singapore. https://doi.org/10.1007/978-981-99-1252-0_3
Download citation
DOI: https://doi.org/10.1007/978-981-99-1252-0_3
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1251-3
Online ISBN: 978-981-99-1252-0
eBook Packages: EngineeringEngineering (R0)