Creating Autonomous Multi-Object Safe Control via Different Forms of Neural Constraints of Dynamic Programming
Abstract
:1. Introduction
1.1. State of Knowledge
1.2. Study Objectives
- Synthesis of safe multi-object control using dynamic programming;
- Experimental comparative analysis of a safe object trajectory with various forms of constraints to control the dynamic optimization process;
- Using the sensitivity characteristics of optimal control in assessing the form of process state constraints.
- Mapping the motion of other encountered objects using neural constraints on the state of the control process;
- Development of an algorithm for determining the safe trajectory of an object in relation to a larger number of other objects encountered.
1.3. Article Content
2. Safe Multi-Object Control Process
2.1. Object 0 State Equations
2.2. Objects j Constraints
3. Optimization of Safe Trajectory
3.1. Bellman’s Optimality Principle
3.2. Algorithm
Algorithm 1: Hexagon, ellipse, parabola, and circle domains calculation |
Begin
|
4. Computer Simulation
5. Conclusions
- It is possible to formulate an adequate model of the actual multi-object control process, which allows for its optimization while maintaining safe traffic conditions;
- Optimization using the Bellman optimality principle in a non-linear model of the control process correctly reproduces the kinematics and dynamics of moving objects;
- The limitations of the optimality principle allow for an adequate representation of the actual control process;
- By formulating various forms of limitations in the over-approach areas, it is possible to select their best form ensuring the least sensitivity to changes in the parameters of the control process;
- The optimality principle algorithm allows us to consider a larger number of objects whose data come from ARPA anti-collision radar systems;
- The stability of safe control is ensured in the real facility by the heading change PID controller with selected optimal settings, for example, according to the Ziegler–Nichols stability criterion.
- The effect of the developed method of optimizing the object’s trajectory is the current mapping of the collision risk through the size of the neural areas of prohibited maneuvers;
- The advantage of the dynamic programming algorithm compared to the second basic optimization method is that the maximum principle is its computational efficiency in real time of the control process; thus, the more state constraints assigned to each encountered object, the shorter the time to determine its safe trajectory.
- Other forms of process state constraints;
- Adapting the final conditions of the trajectory optimization task to the course of the actual control process;
- A comparison of the results of object trajectory optimization according to the optimality principle with optimization results obtained using other static, dynamic, and game optimization methods.
Funding
Data Availability Statement
Conflicts of Interest
References
- Bellman, R.E. Dynamic Programming; Dover Publication: Mineola, NY, USA, 2003; ISBN 0-486-42809-5. [Google Scholar]
- Miretti, F.; Misul, D.; Spessa, E. DynaProg: Deterministic Dynamic Programming solver for finite horizon multi-stage decision problems. SoftwareX 2021, 14, 100690. [Google Scholar] [CrossRef]
- Sundström, O.; Guzzella, L. A generic dynamic programming Matlab function. In Proceedings of the 2009 IEEE Control Applications (CCA) & Intelligent Control (ISIC), St. Petersburg, Russia, 8–10 July 2009; pp. 1625–1630. [Google Scholar] [CrossRef]
- Mikolajczak, B.; Rumbut, J.T. Distributed dynamic programming using concurrent object-orientedness with actors visualized by high-level Petri nets. Comput. Math. Appl. 1999, 37, 23–34. [Google Scholar] [CrossRef]
- Luus, R. Dynamic Programming: Optimal Control Applications. In Encyclopedia of Optimization; Floudas, C., Pardalos, P., Eds.; Springer: Boston, MA, USA, 2008. [Google Scholar] [CrossRef]
- Rempel, M.; Shiell, N.; Tessier, K. An approximate dynamic programming approach to tackling mass evacuation operations. In Proceedings of the 2021 IEEE Symposium Series on Computational Intelligence (SSCI), Orlando, FL, USA, 5–7 December 2021; pp. 1–8. [Google Scholar] [CrossRef]
- Gong, Z.; He, B.; Liu, G.; Zhang, X. Solution for Pursuit-Evasion Game of Agents by Adaptive Dynamic Programming. Electronics 2023, 12, 2595. [Google Scholar] [CrossRef]
- Szuster, M.; Gierlak, P. Globalized Dual Heuristic Dynamic Programming in Control of Robotic Manipulator. Appl. Mech. Mater. 2016, 817, 150–161. [Google Scholar] [CrossRef]
- Szuster, M.; Gierlak, P. Approximate Dynamic Programming in Tracking Control of a Robotic Manipulator. Int. J. Adv. Robot. Syst. 2016, 13, 16. [Google Scholar] [CrossRef]
- Kang, D.J.; Jung, M.H. Road lane segmentation using dynamic programming for active safety vehicles. Pattern Recognit. Lett. 2003, 24, 3177–3185. [Google Scholar] [CrossRef]
- Sundstrom, O.; Ambuhl, D.; Guzzella, L. On Implementation of Dynamic Programming for Optimal Control Problems with Final State Constraints. Oil Gas Sci. Technol. 2009, 65, 91–102. [Google Scholar] [CrossRef]
- Silva, J.E.; Sousa, J.B. A dynamic programming approach for the motion control of autonomous vehicles. In Proceedings of the 49th IEEE Conference on Decision and Control (CDC), Atlanta, GA, USA, 15–17 December 2010; pp. 6660–6665. [Google Scholar] [CrossRef]
- Wei, Y.; Avci, C.; Liu, J.; Belezamo, B.; Aydın, N.; Li, P.; Zhou, X. Dynamic programming-based multi-vehicle longitudinal trajectory optimization with simplified car following models. Transp. Res. Part B Methodol. 2017, 106, 102–129. [Google Scholar] [CrossRef]
- Deshpande, S.R.; Jung, D.; Canova, M. Integrated Approximate Dynamic Programming and Equivalent Consumption Minimization Strategy for Eco-Driving in a Connected and Automated Vehicle. arXiv 2020, arXiv:2010.03620v1. [Google Scholar] [CrossRef]
- Lin, S.C.; Hsu, H.; Lin, Y.Y.; Lin, C.W.; Jiang, I.H.R.; Liu, C. A Dynamic Programming Approach to Optimal Lane Merging of Connected and Autonomous Vehicles. In Proceedings of the 2020 IEEE Intelligent Vehicles Symposium (IV), Las Vegas, NV, USA, 19 October 2020–13 November 2020; pp. 349–356. [Google Scholar] [CrossRef]
- Wang, H.; Hu, C.; Zhou, J.; Feng, L.; Ye, B.; Lu, Y. Path tracking control of an autonomous vehicle with model-free adaptive dynamic programming and RBF neural network disturbance compensation. Proc. Inst. Mech. Eng. Part D J. Automob. Eng. 2022, 236, 825–841. [Google Scholar] [CrossRef]
- Lin, Z.; Ma, J.; Duan, J.; Li, S.E.; Ma, H.; Cheng, B.; Lee, T.H. Policy Iteration Based Approximate Dynamic Programming Toward Autonomous Driving in Constrained Dynamic Environment. IEEE Trans. Intell. Transp. Syst. 2023, 24, 5003–5013. [Google Scholar] [CrossRef]
- Gjorshevski, H.; Trivodaliev, K.; Kosovic, I.N.; Kalajdziski, S.; Stojkoska, B.R. Dynamic Programming Approach for Drone Routes Planning. In Proceedings of the 26th Telecommunications Forum (TELFOR), Belgrade, Serbia, 20–21 November 2018; pp. 1–4. [Google Scholar] [CrossRef]
- Bouman, P.; Agatz, N.; Schmidt, M. Dynamic programming approaches for the traveling salesman problem with dron. Networks 2018, 72, 4. [Google Scholar] [CrossRef]
- Flint, M.; Fernandez, E. Approximate Dynamic Programming Methods for Cooperative UAV Search. IFAC Proc. Vol. 2005, 38, 59–64. [Google Scholar] [CrossRef]
- Azam, M.A.; Dey, S.; Mittelmann, H.D.; Ragi, S. Decentralized UAV Swarm Control for Multitarget Tracking using Approximate Dynamic Programming. In Proceedings of the 2021 IEEE World AI IoT Congress, AIIoT 2021, Virtual Conference, 10–13 May 2021; Paul, R., Ed.; Institute of Electrical and Electronics Engineers Inc.: Piscataway, NJ, USA, 2021. Article 9454229. pp. 457–461. [Google Scholar] [CrossRef]
- Din, A.F.U.; Akhtar, S.; Maqsood, A.; Habib, M.; Mir, I. Modified model free dynamic programming: An augmented approach for unmanned aerial vehicle. Appl. Intell. 2023, 53, 3048–3068. [Google Scholar] [CrossRef]
- Jennings, A.L.; Ordonez, R.; Ceccarelli, N. Dynamic programming applied to UAV way point path planning in wind. In Proceedings of the IEEE International Conference on Computer-Aided Control Systems, San Antonio, TX, USA, 8–12 December 2008; pp. 215–220. [Google Scholar] [CrossRef]
- Vibhute, S. Adaptive Dynamic Programming Based Motion Control of Autonomous Underwater Vehicles. In Proceedings of the 5th International Conference on Control, Decision and Information Technologies (CoDIT), Thessaloniki, Greece, 10–13 April 2018; pp. 966–971. [Google Scholar] [CrossRef]
- Chen, T.; Khurram, S.; Zoungrana, J.; Pandey, L.; Chen, J.C.Y. Advanced controller design for AUV based on adaptive dynamic programming. Adv. Comput. Des. 2020, 5, 233–260. [Google Scholar] [CrossRef]
- Che, G.; Hu, X. Optimal trajectory-tracking control for underactuated AUV with unknown disturbances via single critic network based adaptive dynamic programming. J. Ambient Intell. Hum. Comput. 2023, 14, 7265–7279. [Google Scholar] [CrossRef]
- Wei, S.; Zhou, P. Development of a 3D Dynamic Programming Method for Weather Routing. TransNav Int. J. Mar. Navig. Saf. Sea Transp. 2012, 6, 79–85. [Google Scholar]
- Geng, X.; Wang, Y.; Wang, P.; Zhang, B. Motion Plan of Maritime Autonomous Surface Ships by Dynamic Programming for Collision Avoidance and Speed Optimization. Sensors 2019, 19, 434. [Google Scholar] [CrossRef] [PubMed]
- Esfahani, H.N.; Szlapczynski, R. Robust-adaptive dynamic programming-based time-delay control of autonomous ships under stochastic disturbances using an actor-critic learning algorithm. J. Mar. Sci. Technol. 2021, 26, 1262–1279. [Google Scholar] [CrossRef]
- Mi, Y.; Shao, K.; Liu, Y.; Wang, X.; Xu, F. Integration of Motion Planning and Control for High-Performance Automated Vehicles Using Tube-based Nonlinear MPC. IEEE Trans. Intell. Veh. 2023, 1, 1–16. [Google Scholar] [CrossRef]
- Bokanowski, O.; Desilles, A.; Zidani, H. Relationship between maximum principle and dynamic programming in presence of intermediate and final state constraints. ESAIM Control Optim. Calc. Var. 2021, 27, 91. [Google Scholar] [CrossRef]
- Francelin, R.; Kacprzyk, J.; Gomide, F. Neural Network Based Algorithm for Dynamic System Optimization. Asian J. Control. 2001, 3, 131–142. [Google Scholar] [CrossRef]
- Shi, H.; Gao, W.; Jiang, X.; Su, C.; Ping, L. Two-dimensional model-free Q-learning-based output feedback fault-tolerant control for batch processes. Comput. Chem. Eng. 2024, 182, 108583. [Google Scholar] [CrossRef]
- Shi, H.; Lv, M.; Jiang, X.; Su, C.; Li, P. Optimal tracking control of batch processes with time-invariant state delay: Adaptive Q-learning with two-dimensional state and control policy. Eng. Appl. Artif. Intell. 2024, 132, 108006. [Google Scholar] [CrossRef]
- Russell, S.O.D. Sensitivity analysis with dynamic programming. Can. J. Civ. Eng. 1984, 11, 1–7. [Google Scholar] [CrossRef]
- Tan, C.H.; Hartman, J.C. Sensitivity Analysis and Dynamic Programming; Wiley Online Library: Hoboken, NJ, USA, 2011. [Google Scholar] [CrossRef]
- Kumabe, S.; Yoshida, Y. Average Sensitivity of Dynamic Programming. arXiv 2021, arXiv:2111.02657. [Google Scholar]
Object j | Bearing Nj (deg) | Distance Dj (nm) | Course ψj (deg) | Speed Vj (kn) |
---|---|---|---|---|
0 | 0 | 0 | 0 | 20 |
1 | 11 | 7.5 | 200 | 16 |
2 | 305 | 4 | 0 | 0 |
3 | 55 | 5.7 | 90 | 12 |
4 | 326 | 8.8 | 90 | 14.5 |
5 | 340 | 12 | 0 | 0 |
6 | 6 | 14.3 | 180 | 16.2 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the author. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Lisowski, J. Creating Autonomous Multi-Object Safe Control via Different Forms of Neural Constraints of Dynamic Programming. Electronics 2024, 13, 936. https://doi.org/10.3390/electronics13050936
Lisowski J. Creating Autonomous Multi-Object Safe Control via Different Forms of Neural Constraints of Dynamic Programming. Electronics. 2024; 13(5):936. https://doi.org/10.3390/electronics13050936
Chicago/Turabian StyleLisowski, Józef. 2024. "Creating Autonomous Multi-Object Safe Control via Different Forms of Neural Constraints of Dynamic Programming" Electronics 13, no. 5: 936. https://doi.org/10.3390/electronics13050936
APA StyleLisowski, J. (2024). Creating Autonomous Multi-Object Safe Control via Different Forms of Neural Constraints of Dynamic Programming. Electronics, 13(5), 936. https://doi.org/10.3390/electronics13050936