دانشگاه تربیت دبیر شهید رجائی
انتشارات دانشگاه تربیت دبیر شهید رجائی

  اخبار و اعلانات

 آمار

تعداد نشریات11
تعداد شماره‌ها222
تعداد مقالات2,232
تعداد مشاهده مقاله3,313,060
تعداد دریافت فایل اصل مقاله2,384,590
Arumugam, Vengatesan, Alagumalai, Vasudevan. (1404). An experimental and simulation analysis of multi-objective techniques for mobile robots using improved deep q network algorithm. فناوری آموزش, (), -. doi: 10.22061/jcarme.2025.11712.2562
Vengatesan Arumugam; Vasudevan Alagumalai. "An experimental and simulation analysis of multi-objective techniques for mobile robots using improved deep q network algorithm". فناوری آموزش, , , 1404, -. doi: 10.22061/jcarme.2025.11712.2562
Arumugam, Vengatesan, Alagumalai, Vasudevan. (1404). 'An experimental and simulation analysis of multi-objective techniques for mobile robots using improved deep q network algorithm', فناوری آموزش, (), pp. -. doi: 10.22061/jcarme.2025.11712.2562
Arumugam, Vengatesan, Alagumalai, Vasudevan. An experimental and simulation analysis of multi-objective techniques for mobile robots using improved deep q network algorithm. فناوری آموزش, 1404; (): -. doi: 10.22061/jcarme.2025.11712.2562

An experimental and simulation analysis of multi-objective techniques for mobile robots using improved deep q network algorithm

Journal of Computational & Applied Research in Mechanical Engineering (JCARME)
مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 21 مرداد 1404    اصل مقاله (827.69 K)
نوع مقاله: Research Paper
شناسه دیجیتال (DOI): 10.22061/jcarme.2025.11712.2562
نویسندگان
Vengatesan Arumugam1؛ Vasudevan Alagumalai* 2
1Department of Mechanical Engineering, Saveetha School of Engineering, SIMATS, Chennai, Tamil Nadu, India.
2Department of Mechanical Engineering, Saveetha School of Engineering, SIMATS, Chennai, Tamil Nadu, India
تاریخ دریافت: 12 بهمن 1403،  تاریخ بازنگری: 31 تیر 1404،  تاریخ پذیرش: 21 مرداد 1404 
چکیده
Mobile robots have garnered significant attention across various domains, including industrial automation, healthcare, logistics, and autonomous vehicles. However, effective navigation in dynamic and complex environments remains a critical challenge. This research introduces an improved deep q-network algorithm for learning-based mobile robot navigation, addressing a multi-objective optimization problem that seeks to minimize path distance, energy consumption, and travel time within a grid-mapped complex environment. The deep q-network algorithm was enhanced to improve its efficiency in determining the optimal path to a target point. Experimental validation using a learning robot demonstrated the effectiveness of the proposed approach, ensuring safe path generation with collision avoidance, optimized path distance, and practical implementability in mobile robot applications. Furthermore, training, simulation, and analysis results revealed less than 2% deviations between simulation and experimental outcomes, with a path distance error of only 1.3765%. Finally, the proposed algorithm was benchmarked against existing approaches, including the A* algorithm, enhanced deep q-network, and dueling double deep q-network, showcasing its superior performance.
کلیدواژه‌ها
Learning mobile robot؛ Multi- objective functions؛ Deep q network؛ Improved deep q network؛ Obstacle avoidance
مراجع
[1] K. Winkle, P. Caleb-Solly, A. Turton and P. Bremner, “Mutual shaping in the design of socially assistive robots: a case study on social robots for therapy,” Int. J. Social Rob., Vol. 12, No. 4, pp. 847–866,  (2019).

[2] L. Sheng, H. Chen and X. Chen, “A multi-agent centralized strategy gradient reinforcement learning algorithm based on state transition algorithms,” J. Algor., Vol. 17, No. 12, pp.579,(2024). 

[3] M. Morgan, T. Holzer, and T. Eveleigh, “Synergizing model‐based systems engineering, modularity, and software container concepts to manage obsolescence,” Syst. Eng., Vol. 24, No. 5, pp. 369–380, (2021).

[4] F. Yuan, G. Ren, Q. Deng, and X. Wang, “Steam generator maintenance robot design and obstacle avoidance path planning,” J. Sens., Vol. 25, No. 2, pp.514,(2025). 

[5] J. Rodano, O. Obada, J. Parron, R. Li, M. Zhu, and W. Wang, “Teaching humanoid robots to assist humans for collaborative tasks,” IEEE -ICOSC, Vol. 27, pp.344-348, (2023). 

[6] H. El-Husseini, “Dynamic modeling and task-space control of vine-like soft growing robots,” 62nd Ann. Conf. - SICE, Vol. 14, pp.1220–1225,(2023). 

[7] M. Ali, S. Das and S. Townley, “Robot differential drive navigation through probabilistic roadmap and pure pursuit,” IEEE Acc., Vol. 13, pp. 22118–22132, (2025).

[8] Y. Liu, C. Wang, H. Wu and Y. Wei, “Mobile robot path planning based on kinematically constrained A-star algorithm and DWA fusion algorithm,” Mathemat., Vol. 11, No. 21, pp. 4552, (2023).

[9] A. A. N. Kumaar and S. Kochuvila, “Mobile service robot path planning using deep reinforcement learning,” IEEE Acc., Vol. 11, pp. 100083–100096,(2023).

[10] J. Zhang and H. Zhao, “Mobile robot path planning based on improved deep reinforcement learning algorithm,” 4th Int. Conf. -NNIC , Vol. 30, pp. 1758–1761,(2024).

[11] J. Gao, W. Ye, J. Guo, and Z. Li, “Deep reinforcement learning for indoor mobile robot path planning,” Sensors, Vol. 20, No. 19, pp. 5493, (2020),  

[12] Z. Wu, Y. Yin, J. Liu, D. Zhang, J. Chen, and W. Jiang, “A novel path planning approach for mobile robot in a radioactive environment based on improved deep Q network algorithm,” J. Symmetry, Vol. 15, No. 11, pp. 2048, (2023).

[13] L. D. Hanh and V. D. Cong, “Path following and avoiding obstacle for a mobile robot under dynamic environments using reinforcement learning,” J. Rob. And Cont., Vol. 4, No. 2, pp.157–164,(2023).

[14] F. Quiroga, G. Hermosilla, G. Farias, E. Fabregas, and G. Montenegro, “Position control of a mobile robot through deep reinforcement learning,” Appl. Sci., Vol. 12, No. 14, pp. 7194,  (2022).

[15] H. Song, A. Li, T. Wang, and M. Wang, “Multimodal deep reinforcement learning with the auxiliary task for obstacle avoidance of indoor mobile robot,” J. Sens., Vol. 21, No. 4, pp. 1363,(2022).

[16] K. Zhu and T. Zhang, “Deep reinforcement learning based mobile robot navigation: A review,” Tsinghua Sci. Technol., Vol. 26, No. 5, pp.674–691,(2021). 

[17] Y. Yang, L. Juntao, and P. Lingling, “Multi‐robot path planning based on a deep reinforcement learning DQN algorithm,” CAAI Trans. Intell. Technol., Vol. 5, No. 3, pp. 177–183, (2020). 

[18] S. Yoon, K. Shik Roh, and Y. Shim, “Vision-based obstacle detection and avoidance: application to robust indoor navigation of mobile robots,” Adv. Rob., Vol. 22, No. 4, pp. 477–492, (2008).  

[19] Z. Wu, Y. Yin, J. Liu, D. Zhang, J. Chen, and W. Jiang, “A Novel Path Planning Approach for Mobile Robot in Radioactive Environment Based on Improved Deep Q Network Algorithm,” J. Symmetry, Vol. 15, No. 11, pp. 2048, (2023). 

[20] L. Sun. X. Duan, K. Zhang, P. Xu, X. Zheng, Q. Yu and Y. Luo, “Improved path planning algorithm for mobile robots,” Soft Comp., Vol. 27, No. 20, pp. 15057–15073,(2023). 

[21] L. Lv, S. Zhang, D. Ding, and Y. Wang, “Path Planning via an Improved DQN-Based Learning Policy,” IEEE Acc., Vol. 7, pp. 67319–67330, (2019).

[22] H. Qin, S. Shao, T. Wang, X. Yu, Y. Jiang, and Z. Cao, “Review of Autonomous Path Planning Algorithms for Mobile Robots,” Drones, Vol. 7, No. 3, pp. 211, (2023),

[23] Y. Chen, Z.-M. Lu, J.-L. Cui, H. Luo, and Y.-M. Zheng, “A complete coverage path planning algorithm for lawn mowing robots based on deep reinforcement learning,” J. Sens., Vol. 25, No. 2, p.416, (2025).

[24] Y. Yang, “Path planning under high-dimensional input states based on deep q-network,” High. in Sci., Engg. and Tech., Vol. 120, pp. 576–585,  (2024),

[25] J. Li, Y. Chen, X. Zhao, and J. Huang, “An improved DQN path planning algorithm,” The J. of Supercom., Vol. 78, No. 1, pp. 616–639, (2021),

[26] C. Chen, J. Cai, Z. Wang, F. Chen, and W. Yi, “An improved A* algorithm for searching the minimum dose path in nuclear facilities,” Prog. Nucl. Energy, Vol. 126, pp. 103394, (2020).

[27] A. Vengatesan, V. Alagumalai and S. Rajendran. “Simulation analysis of multi-objective functions in mobile robot navigation based on enhanced deep q-network algorithm,” SAE Tech. Paper, No. 2024-01-5110, (2024).

[28] G. Mehmet. “Dynamic path planning via dueling double deep q-network (D3QN) with prioritized experience replay”, Appl. Soft Comput.,  Vol.158, pp.111503,(2024). 

آمار
تعداد مشاهده مقاله: 4
تعداد دریافت فایل اصل مقاله: 3


سامانه مدیریت نشریات علمی. طراحی و پیاده سازی از سیناوب