Just-in-Time Optimal Routing in the Presence of Non-Uniform and Time-Evolving Uncertainty
Source abstract
Abstract
Trajectory planning aims to compute an optimal path and velocity of an agent through the minimization of a cost function. This paper proposes a just-in-time routing method, incorporating the stochastic minimization of a cost function, which ingests the effect of the agent’s environment evolving in space and time. The environment is considered known at present, but the uncertainty increases when advancing in time. To compute the optimal routing in such an uncertain environment, Euler–Lagrange equations will be formulated in a stochastic setting, to obtain a probabilistic optimal planning. With the cost function approximated by using a surrogate modeling based on deep neural networks, a neural formulation of the stochastic Euler–Lagrange equations is proposed and employed.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Autonomous Vehicle Technology and Safety · Traffic control and management · Evacuation and Crowd Dynamics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Mechanical Engineering Department, University of North Florida, 1 UNF Drive, Jacksonville, FL 32224, USA
PIMM Research Laboratory, UMR 8006 CNRS-ENSAM-CNAM, Arts et Metiers Institute of Technology, 151 Boulevard de l’Hôpital, 75013 Paris, France
CNRS@CREATE 1 Create Way, #08-01 CREATE Tower, Singapore 138602, Singapore
Funding
National Research Foundation, Prime Minister Office, Singapore
References (28)
Show source-provided references
1. Sutton, R., and Barto, A. (2018). Reinforced Learning. An Introduction, The MIT Press.
2. Hierarchical Safe Reinforcement Learning Control for Leader-Follower Systems with Prescribed Performance10.1109/TASE.2025.3596912 ↗
3. Kim, H., Pyeon, H., Park, J.S., Hwang, J.Y., and Lim, S. (2020). Autonomous Vehicle Fuel Economy Optimization with Deep Reinforcement Learning. Electronics, 9.10.3390/electronics9111911 ↗
4. Optimal velocity planning based on the solution of the Euler-Lagrange equations with a neural network based velocity regression10.3934/dcdss.2023080 ↗
5. Ghnatios, C., Di Lorenzo, D., Champaney, V., Ammar, A., Cueto, E., and Chinesta, F. (2024). Optimal trajectory planning combining model-based and data-driven hybrid approaches. Adv. Model. Simul. Eng. Sci., 11.10.1186/s40323-024-00266-2 ↗
6. Tan, J., Xue, S., Guan, Q., Qu, K., and Cao, H. (2025). Finite-time safe reinforcement learning control of multi-player nonzero-sum game for quadcopter systems. Inf. Sci., 712.10.1016/j.ins.2025.122117 ↗
7. Fixed-time concurrent learning-based robust approximate optimal control10.1007/s11071-025-11235-8 ↗
8. Petrović, L., Peršić, J., Seder, M., and Marković, I. (2019, January 4–6). Stochastic Optimization for Trajectory Planning with Heteroscedastic Gaussian Processes. Proceedings of the 2019 European Conference on Mobile Robots (ECMR), Prague, Czech Republic.10.1109/ECMR.2019.8870970 ↗
9. Petrović, L., Peršić, J., Seder, M., and Marković, I. (2020). Cross-entropy based stochastic optimization of robot trajectories using heteroscedastic continuous-time Gaussian processes. Robot. Auton. Syst., 133.10.1016/j.robot.2020.103618 ↗
10. Ren, J., Huang, X., and Huang, R.N. (2022). Efficient Deep Reinforcement Learning for Optimal Path Planning. Electronics, 11.10.3390/electronics11213628 ↗
11. A reinforcement learning approach for widest path routing in software-defined networks10.1016/j.icte.2022.10.007 ↗
12. Introduction to Monte Carlo Simulation10.1063/1.3295638 ↗
13. Kalakrishnan, M., Chitta, S., Theodorou, E., Pastor, P., and Schaal, S. (2011, January 9–13). STOMP: Stochastic trajectory optimization for motion planning. Proceedings of the 2011 IEEE International Conference on Robotics and Automation, Shanghai, China.10.1109/ICRA.2011.5980280 ↗
14. Stress-oriented 3D printing path optimization based on image processing algorithms for reinforced load-bearing parts10.1016/j.cirp.2021.04.037 ↗
15. Yamamoto, K., Luces, J.V.S., Shirasu, K., Hoshikawa, Y., Okabe, T., and Hirata, Y. (2022). A novel single-stroke path planning algorithm for 3D printers using continuous carbon fiber reinforced thermoplastics. Addit. Manuf., 55.10.1016/j.addma.2022.102816 ↗
16. Reduced order modeling of selective laser melting: From calibration to parametric part distortion10.1007/s12289-021-01613-z ↗
17. Zhang, P., Yin, L., Zhou, Z., Tong, Y., and Feng, W. (2023). Modeling and Analyzing Layup Gaps in the Trajectory Planning for Automated Tape Placement. Comput.-Aided Des., 164.10.1016/j.cad.2023.103595 ↗
18. Trajectory optimization for automated tape placement on triangular mesh surfaces considering gap requirements
19. Reddy, J. (2006). Introduction to the Finite Element Method, McGraw-Hill. [3rd ed.].
20. Becker, M. (1964). The Principles and Applications of Variational Methods, MIT Press.
21. Liao, S., Xiao, W., and Wang, Y. (2025). Optimization of route planning based on active towed array sonar for underwater search and rescue. Ocean Eng., 330.10.1016/j.oceaneng.2025.121249 ↗
22. Xue, Q., Zheng, S.T., Han, X., and Jiang, R. (2025). A two-level framework for dynamic route planning and trajectory optimization of connected and automated vehicles in road networks. Phys. A Stat. Mech. Its Appl., 668.10.1016/j.physa.2025.130552 ↗
23. Wang, X., Lv, Y., Sun, H., Wang, X., and Zhu, C. (2025). Multi-modal travel route planning considering environmental preference under uncertainties: A distributionally robust optimization approach. Transp. Res. Part E Logist. Transp. Rev., 198.10.1016/j.tre.2025.104097 ↗
24. Xu, W., and Xie, N. (2025). Scheduling and route planning for forests rescue: Applications with a novel ant colony optimization algorithm. Eng. Appl. Artif. Intell., 155.10.1016/j.engappai.2025.111042 ↗
25. Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., and Devin, M. (2015). TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. arXiv.
26. Kingma, D.P., and Ba, J. (2017). Adam: A Method for Stochastic Optimization. arXiv.
27. Understanding the Metropolis-Hastings Algorithm10.1080/00031305.1995.10476177 ↗
28. (2025, June 19). Prefecture. Normales de Rose de Vent. Vent Horaire à 10 Mètres, Moyenné sur 10 Minutes. Available online: https://www.prefecturedepolice.interieur.gouv.fr/sites/default/files/media/ROSE_PARIS-MONTSOURIS.pdf.