Perancangan Model Pergerakan Mobile Robot dengan Metode Deep Q Learning

Samsul Arifin, Siti Sendari, Ilham Ari Elbaith Zaini

Abstract


Path Planning merupakan salah satu permasalahan yang sering terjadi pada mobile robot. Tujuan utama dalam path planning adalah untuk mendapatkan path/jalur yang paling optimal sehingga bisa meminimalisir waktu komputasi. Kelemahan yang umum terjadi pada path planning adalah waktu komputasi yang besar pada suatu environment. Dengan adanya permasalahan ini maka akan diterapkan metode deep Q learning untuk meningkatkan kecepatan waktu komputasi. Metode deep q learning menyimpan hasil pembelajaran dalam bentuk neural network. Mobile robot dilatih agar dapat menemukan jalur pada environment yang belum dikenali sama sekali. Melalui beberapa tahapan dalam proses training dan proses running maka mobile robot dapat menemukan jalur dengan cepat. Keseimbangan proses eksplorasi dan eksploitasi akan mempengaruhi proses training. Pada penelitan ini ditentukan nilai untuk proses eksplorasi adalah 80 episode pertama. Pada proses training telah didapatkan nilai parameter gamma yang optimal adalah 0.9. Setelah mendapatkan pengetahuan dari proses training maka mobile robot dapat menemukan path yang paling optimal dengan waktu tempuh ± 1.92s.


Keywords


path planning; mobile robot; deep Q learning; training; environment

Full Text:

PDF

References


H. Zhang, W. Lin, and A. Chen, “Path Planning for the Mobile Robot: A Review,” Symmetry, vol. 10, no. 10, p. 450, Oct. 2018, doi: 10.3390/sym10100450.

E. S. Low, P. Ong, C. Y. Low, and R. Omar, “Modified Q-learning with distance metric and virtual target on path planning of mobile robot,” Expert Systems with Applications, vol. 199, p. 117191, Aug. 2022, doi: 10.1016/j.eswa.2022.117191.

R. Huang, C. Qin, J. L. Li, and X. Lan, “Path planning of mobile robot in unknown dynamic continuous environment using reward-modified deep Q-network,” Optimal Control Applications and Methods, vol. n/a, no. n/a, doi: 10.1002/oca.2781.

T. Bonny and M. Kashkash, “Highly optimized Q-learning-based bees approach for mobile robot path planning in static and dynamic environments,” Journal of Field Robotics, vol. 39, no. 4, pp. 317–334, 2022, doi: 10.1002/rob.22052.

J. Dai, J. Qiu, H. Yu, C. Zhang, Z. Wu, and Q. Gao, “Robot Static Path Planning Method Based on Deterministic Annealing,” Machines, vol. 10, no. 8, p. 600, Jul. 2022, doi: 10.3390/machines10080600.

M. Luo, X. Hou, and J. Yang, “Surface Optimal Path Planning Using an Extended Dijkstra Algorithm,” IEEE Access, vol. 8, pp. 147827–147838, 2020, doi: 10.1109/ACCESS.2020.3015976.

D. Xiang, H. Lin, J. Ouyang, and D. Huang, “Combined improved A* and greedy algorithm for path planning of multi-objective mobile robot,” Sci Rep, vol. 12, no. 1, p. 13273, Aug. 2022, doi: 10.1038/s41598-022-17684-0.

M. N. A. Wahab, S. Nefti-Meziani, and A. Atyabi, “A comparative review on mobile robot path planning: Classical or meta-heuristic methods?,” Annual Reviews in Control, vol. 50, pp. 233–252, 2020, doi: 10.1016/j.arcontrol.2020.10.001.

Y. Li, W. Wei, Y. Gao, D. Wang, and Z. Fan, “PQ-RRT*: An improved path planning algorithm for mobile robots,” Expert Systems with Applications, vol. 152, p. 113425, Aug. 2020, doi: 10.1016/j.eswa.2020.113425.

Q. Luo, H. Wang, Y. Zheng, and J. He, “Research on path planning of mobile robot based on improved ant colony algorithm,” Neural Comput & Applic, vol. 32, no. 6, pp. 1555–1566, Mar. 2020, doi: 10.1007/s00521-019-04172-2.

H. S. Hewawasam, M. Y. Ibrahim, and G. K. Appuhamillage, “Past, Present and Future of Path-Planning Algorithms for Mobile Robot Navigation in Dynamic Environments,” IEEE Open J. Ind. Electron. Soc., vol. 3, pp. 353–365, 2022, doi: 10.1109/OJIES.2022.3179617.

T. A. Teli and M. A. Wani, “A fuzzy based local minima avoidance path planning in autonomous robots,” Int. j. inf. tecnol., vol. 13, no. 1, pp. 33–40, Feb. 2021, doi: 10.1007/s41870-020-00547-0.

T. Zhang and H. Mo, “Reinforcement learning for robot research: A comprehensive review and open issues,” International Journal of Advanced Robotic Systems, vol. 18, no. 3, p. 172988142110073, May 2021, doi: 10.1177/17298814211007305.

E. S. Low, P. Ong, and K. C. Cheah, “Solving the optimal path planning of a mobile robot using improved Q-learning,” Robotics and Autonomous Systems, vol. 115, pp. 143–161, May 2019, doi: 10.1016/j.robot.2019.02.013.

L. Zhang, Y. Zhang, and Y. Li, “Path planning for indoor Mobile robot based on deep learning,” Optik, vol. 219, p. 165096, Oct. 2020, doi: 10.1016/j.ijleo.2020.165096.

H. Shen, H. Hashimoto, A. Matsuda, Y. Taniguchi, D. Terada, and C. Guo, “Automatic collision avoidance of multiple ships based on deep Q-learning,” Applied Ocean Research, vol. 86, pp. 268–288, May 2019, doi: 10.1016/j.apor.2019.02.020.

J. Gao, W. Ye, J. Guo, and Z. Li, “Deep Reinforcement Learning for Indoor Mobile Robot Path Planning,” Sensors, vol. 20, no. 19, p. 5493, Sep. 2020, doi: 10.3390/s20195493.

H. Quan, Y. Li, and Y. Zhang, “A novel mobile robot navigation method based on deep reinforcement learning,” International Journal of Advanced Robotic Systems, vol. 17, no. 3, p. 172988142092167, May 2020, doi: 10.1177/1729881420921672.

M.-F. R. Lee and S. H. Yusuf, “Mobile Robot Navigation Using Deep Reinforcement Learning,” Processes, vol. 10, no. 12, p. 2748, Dec. 2022, doi: 10.3390/pr10122748.




DOI: http://dx.doi.org/10.26418/jp.v9i3.64541

Refbacks

  • There are currently no refbacks.