This paper presents an improved artificial potential field (I-APF) to address the problem of local minima and implements reinforcement learning (RL) to reach its desired waypoint in the presence of actuator attacks. The proposed I-APF ensures that the robot avoids the local minima in the APF by generating the desired velocities for the robot’s kinematics. The RL-based guidance algorithm drives the robot toward the assigned goal, and it also incorporates tolerance against faults due to actuator attacks while minimizing tracking errors. The stability of the I-APF and the derived RL control law have also been studied and found to be the uniform ultimate bound. The effectiveness of the control algorithm has been verified in both simulation and experimental environments with different scenarios, such as with static and dynamic obstacles and in the presence of actuator attacks, which confirms the convergence of the robot’s position to the assigned goal.
FengTLiJJiangH, et al. The optimal global path planning of mobile robot based on improved hybrid adaptive genetic algorithm in different tasks and complex road environments. IEEE Access2024; 12: 18400–18415. https://doi.org/10.1109/ACCESS.2024.3357990
2.
ZongTLiJLuG. Hierarchical maximum likelihood identification based on levenberg–marquardt and particle swarm optimization for feedback nonlinear systems. Proc Inst Mech Eng Part I: J Syst Contr Eng2023; 237(9): 1573–1586. https://doi.org/10.1177/09596518231165348
3.
WuLHuangXCuiJ, et al. Modified adaptive ant colony optimization algorithm and its application for solving path planning of mobile robot. Expert Syst Appl2023; 215: 119410. https://doi.org/10.1016/j.eswa.2022.119410
SalamaOAAEltaibMEHMohamedHA, et al. RCD: radial cell decomposition algorithm for mobile robot path planning. IEEE Access2021; 9: 149982–149992. https://doi.org/10.1109/ACCESS.2021.3125105
6.
LiuWJingCWanP, et al. Combining extended Kalman filtering and rapidly-exploring random tree: an improved autonomous navigation strategy for four-wheel steering vehicle in narrow indoor environments. Proc Inst Mech Eng Part I: J Syst Contr Eng2022; 236(5): 883–896. https://doi.org/10.1177/09596518221080623
7.
RavankarAARavankarAEmaruT, et al. Hpprm: Hybrid potential based probabilistic roadmap algorithm for improved dynamic path planning of mobile robots. IEEE Access2020; 8: 221743–221766.
8.
WuZDaiJJiangB, et al. Robot path planning based on artificial potential field with deterministic annealing. ISA Trans2023; 138: 74–87. https://doi.org/10.1016/j.isatra.2023.02.018
9.
LoganathanAAhmadNS. A systematic review on recent advances in autonomous mobile robot navigation. Eng Sci Technol Int J2023; 40: 101343. https://doi.org/10.1016/j.jestch.2023.101343
10.
MoradiPHabibnejad KorayemMYousefi LademakhiN. Extended nonlinear time-varying lugre-based friction model identification of robot manipulator with sliding mode control compensation approach. Proc Inst Mech Eng Part I: J Syst Contr Eng2023; 237(2): 207–219. https://doi.org/10.1177/09596518221128469
11.
JiangYXuXZhangL, et al. Model free predictive path tracking control of variable-configuration unmanned ground vehicle. ISA Trans2022; 129: 485–494. https://doi.org/10.1016/j.isatra.2022.01.026
12.
ZhuXZhangBQiuY, et al. An interaction behavior decision-making model of service robots for the disabled based on human–robot empathy. IEEE Access2024; 12: 15778–15790. https://doi.org/10.1109/access.2024.3358614
13.
FanXGuoYLiuH, et al. Improved artificial potential field method applied for auv path planning. Math Probl Eng2020; 2020(1): 1–21. https://doi.org/10.1155/2020/6523158
14.
PanZZhangCXiaY, et al. An improved artificial potential field method for path planning and formation control of the multi-uav systems. IEEE Trans Circuits Syst II Express Briefs2022; 69(3): 1129–1133. https://doi.org/10.1109/TCSII.2021.3112787
15.
SzczepanskiR. Safe artificial potential field - novel local path planning algorithm maintaining safe distance from obstacles. IEEE Robot Autom Lett2023; 8(8): 4823–4830. https://doi.org/10.1109/LRA.2023.3290819
16.
SouzaRMJALimaGVMoraisAS, et al. Modified artificial potential field for the path planning of aircraft swarms in three-dimensional environments. Sensors2022; 22(4): 1558–1576. https://doi.org/10.3390/s22041558
17.
YaoQZhengZQiL, et al. Path planning method with improved artificial potential field—a reinforcement learning perspective. IEEE Access2020; 8: 135513–135523. https://doi.org/10.1109/ACCESS.2020.3011211
Orozco-RosasUPicosKPantrigoJJ, et al. Mobile robot path planning using a qapf learning algorithm for known and unknown environments. IEEE Access2022; 10: 84648–84663. https://doi.org/10.1109/ACCESS.2022.3197628
20.
LiHLiuWYangC, et al. An optimization-based path planning approach for autonomous vehicles using the dynefwa-artificial potential field. IEEE Trans Intell Vehicles2022; 7(2): 263–272. https://doi.org/10.1109/TIV.2021.3123341
21.
YangHFanXShiP, et al. Nonlinear control for tracking and obstacle avoidance of a wheeled mobile robot with nonholonomic constraint. IEEE Trans Control Syst Technol2015; 24(2): 1–746. https://doi.org/10.1109/TCST.2015.2457877
22.
ShamsfakhrFBighamBS. A neural network approach to navigation of a mobile robot and obstacle avoidance in dynamic and unknown environments. Turk J Electr Eng Comput Sci2017; 25(3): 1629–1642. https://doi.org/10.3906/elk-1603-75
23.
DuguleanaMMoganG. Neural networks based reinforcement learning for mobile robots obstacle avoidance. Expert Syst Appl2016; 62: 104–115. https://doi.org/10.1016/j.eswa.2016.06.021
24.
El-FerikSMaarufMAl-SunniFM, et al. Reinforcement learning-based control strategy for multi-agent systems subjected to actuator cyberattacks during affine formation maneuvers. IEEE Access2023; 11: 77656–77668. https://doi.org/10.1109/ACCESS.2023.3296741
25.
YuMWangWHuangJ, et al. Decentralized adaptive secure control of uncertain nonlinear time-varying interconnected systems against sensor and actuator attacks. IEEE Trans Cybern2024; 54(9): 5012–5025. https://doi.org/10.1109/TCYB.2024.3373198
26.
LiuJDongYZhaL, et al. Reinforcement learning-based tracking control for networked control systems with dos attacks. IEEE Trans Inf Forensics Secur2024; 19: 4188–4197. https://doi.org/10.1109/TIFS.2024.3376250
27.
CaoZNiuYSongJ. Finite-time sliding-mode control of markovian jump cyber-physical systems against randomly occurring injection attacks. IEEE Trans Automat Contr2020; 65(3): 1264–1271. https://doi.org/10.1109/TAC.2019.2926156
28.
CaoZNiuYZouY. Adaptive neural sliding mode control for singular semi-markovian jump systems against actuator attacks. IEEE Trans Syst Man Cybern Syst2019; 51(3): 1–11. https://doi.org/10.1109/TSMC.2019.2898428
HePJagannathanS. Reinforcement learning neural-network-based controller for nonlinear discrete-time systems with input constraints. IEEE Trans Syst Man Cybern B2007; 37(2): 425–436. https://doi.org/10.1109/tsmcb.2006.883869
31.
The MathWorks Inc.Matlab version: 9.13.0 (r2022b), https://www.mathworks.com (2022, accessed April 2025).
32.
HaoLYDongGLiT, et al. Path-following control with obstacle avoidance of autonomous surface vehicles subject to actuator faults. IEEE/CAA J Autom Sin2024; 11(4): 956–964. https://doi.org/10.1109/JAS.2023.123675
33.
ZhouYVamvoudakisKGHaddadWM, et al. A secure control learning framework for cyber-physical systems under sensor and actuator attacks. IEEE Trans Cybern2021; 51(9): 4648–4660. https://doi.org/10.1109/TCYB.2020.3006871
