مهندسی مکانیک مدرس

مهندسی مکانیک مدرس

نگاشت کروموزمی مسئله عبور از مانع: چارچوبی تطبیقی مبتنی بر الگوریتم ژنتیک-فازی برای ربات شش چرخ-پا

نوع مقاله : مقاله پژوهشی

نویسندگان
دانشکده مهندسی مکانیک، دانشگاه صنعتی اصفهان، ،84156-83111اصفهان، ا یران
10.48311/mme.2026.120505.83013
چکیده
ربات‌های هیبریدی چرخ‌دار-راه‌رونده با تلفیق بازدهی حرکتی چرخ‌ها و قابلیت سازگاری پاها، توانمندی بالایی برای حرکت در محیط‌های ناهموار دارند. با این حال، عبور کارآمد از موانع پیچیده مستلزم راهبردهای هوشمندی است که حرکات پا، سرعت چرخ‌ها و وضعیت بدنه را هماهنگ سازد. این مقاله یک چارچوب یادگیری یکپارچه برای استخراج سیاست‌های تغییر پیکربندی بهینه جهت عبور یک ربات شش چرخ-پا از مانع پله نامتقارن ارائه می‌دهد. در ابتدا، روابط سینماتیکی حاکم بر تعامل چرخ-پا با زمین و تنظیم سرعت چرخ‌ها بدون لغزش استخراج شده است. به‌عنوان نوآوری کلیدی، مسئله عبور از مانع به یک فضای بهینه‌سازی پارامتری کم‌بعد و پیوسته نگاشت شده و بر این اساس چارچوب یادگیری مبتنی بر الگوریتم ژنتیک ارائه می‌شود. این چارچوب، بدون تحمیل مفروضات محدودکننده، پیچیدگی فضای جستجو را به‌طور چشمگیری کاهش می‌دهد. در کنار این رویکرد، از منطق فازی جهت انتقال خبرگی انسان به تابع هزینه و تطبیق ضرایب وزنی آن بهره گرفته شده است که امکان کشف خودکار سیاست‌های عملی را بدون نیاز به توالی‌های حرکتی از پیش تعریف‌شده فراهم می‌آورد. نتایج شبیه‌سازی با آزمایش‌های تجربی بر روی ربات ویراکس اعتبارسنجی شده و تطابق نزدیکی بین توالی حرکات پا، گذار چندضلعی تکیه‌گاه و کاهش انحرافات ناخواسته بدنه مشاهده شده است. در مجموع، این رویکرد راه‌حلی مؤثر و مقیاس‌پذیر برای بهینه‌سازی عبور از مانع در ربات‌های هیبریدی ارائه می‌دهد و پتانسیل استراتژی‌های مبتنی بر یادگیری را در محیط‌های پیچیده برجسته می‌سازد.
کلیدواژه‌ها
موضوعات

عنوان مقاله English

Chromosome-Based Mapping of the Obstacle Traversal Problem: An Adaptive Fuzzy-Genetic Framework for a Six Wheel-Leg Robot

نویسندگان English

Seyed Mostafa Hoseini
Saeed Behbahani
Department of Mechanical Engineering, Isfahan University of Technology, Isfahan, Iran
چکیده English

Hybrid wheeled-legged robots offer superior mobility in unstructured terrain by combining the locomotion efficiency of wheels with the adaptability of legs. However, efficiently traversing complex obstacles necessitates intelligent reconfiguration policies that coordinate leg movements, wheel velocities, and body posture. This paper presents an integrated learning framework to derive optimal policies for a six-wheeled-legged robot traversing an asymmetric step obstacle. Initially, the kinematic relationships governing wheel-leg interaction with the ground and slip-free wheel velocity coordination are formulated. As the key innovation, the obstacle traversal problem is mapped into a low-dimensional and continuous parametric optimization space, upon which a Genetic Algorithm-based learning framework is developed. Without imposing restrictive assumptions, this framework significantly reduces the complexity of the search space. In addition, fuzzy logic is employed to integrate human expertise into the cost function and adapt its weighting coefficients. This facilitates the automatic discovery of practical policies without relying on pre-defined motion sequences. Simulation results are validated through experiments on the ViraHex robot, demonstrating close agreement in leg motion sequences, support polygon transitions, and the mitigation of undesired body deviations. Overall, this framework offers an effective and scalable solution for optimizing obstacle traversal in hybrid robots, highlighting the potential of learning-based strategies in complex environments.

کلیدواژه‌ها English

Hybrid Wheel-Leg Robot
Reconfiguration
Kinematic Modeling
Obstacle Traversal
Genetic Algorithm
[1] C. Grand, F. BenAmar, F. Plumet, and P. Bidaud, "Decoupled control of posture and trajectory of the hybrid wheel-legged robot Hylos," in IEEE International Conference on Robotics and Automation, 2004, vol. 5: IEEE; 1999, pp. 5111-5116.
doi: 10.1109/ROBOT.2004.1302528
[2] J. Aguilar et al., "A review on locomotion robophysics: the study of movement at the intersection of robotics, soft matter and dynamical systems," Reports on Progress in Physics, vol. 79, no. 11, p. 110001, 2016.
doi: 10.1088/0034-4885/79/11/110001
[3] R. A. I. Khan, C. Zhang, Y. Pan, A. Zhang, R. Li, X. Zhao, and H. Shang, "Hierarchical optimum control of a novel wheel-legged quadruped," Robotics and Autonomous Systems, vol. 180, p. 104775, 2024.
doi: 10.1016/j.robot.2024.104775
[4] M. Mohammadi Moghadam and M. Moradi Dalvand, "Design, Construction, and Control of a Stair- and Obstacle-Climbing Robot (MSRox)," Modares Mechanical Engineering, vol. 6, no. 1, pp. 13–30, 2006. [Online]. Available: https://mme.modares.ac.ir/article_7632_20754aeb165b7072f49615f07ab6122e.pdf
[5] C. Liu et al., "Mechanical design and wheel-leg-body cooperation control of a stepclimbing robot," Journal of Field Robotics, vol. 39, no. 7, pp. 1054-1068, 2022. doi: 10.1002/rob.22087
[6] L. Bruzzone, S. E. Nodehi, and P. Fanghella, "WheTLHLoc 4W: Smallscale inspection ground mobile robot with two tracks, two rotating legs, and four wheels," Journal of Field Robotics, vol. 41, no. 4, pp. 1146-1166, 2024.
doi: 10.1002/rob.22314
[7] J. Kang, W. Kim, J. Lee, and K. Yi, "Skid steering-based control of a robotic vehicle with six in-wheel drives," Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, vol. 224, no. 11, pp. 1369-1391, 2010.
doi: 10.1243/09544070JAUTO1405
[8] A. N. A. Rafai, N. Adzhar, and N. I. Jaini, "A review on path planning and obstacle avoidance algorithms for autonomous mobile robots," Journal of Robotics, vol. 2022, no. 1, p. 2538220, 2022.
doi: 10.1155/2022/2538220
[9] A. Pandey, S. Pandey, and D. Parhi, "Mobile robot navigation and obstacle avoidance techniques: A review," Int Rob Auto J, vol. 2, no. 3, p. 00022, 2017.
doi: 10.15406/iratj.2017.02.00023
[10] W. Rahmaniar and A. E. Rakhmania, "Mobile robot path planning in a trajectory with multiple obstacles using genetic algorithms," Journal of Robotics and Control (JRC), vol. 3, no. 1, pp. 1-7, 2022.
doi: 10.18196/jrc.v3i1.11024
[11] M. N. Ab Wahab, A. Nazir, A. Khalil, W. J. Ho, M. F. Akbar, M. H. M. Noor, and A. S. A. Mohamed, "Improved genetic algorithm for mobile robot path planning in static environments," Expert Systems with Applications, vol. 249, p. 123762, 2024.
doi: 10.1016/j.eswa.2024.123762
[12] S. M. R. Seyed Noorani, M. Shoaaran, and S. Farshbaf, "Optimization of Synaptic Weights in a Four-Cell Central Pattern Generator Network for Bipedal Gait Generation," Modares Mechanical Engineering, vol. 16, no. 12, pp. 144–152, 2017. [Online]. Available: https://mme.modares.ac.ir/article_9556_177da57035b03c2eb2cbe9b872348d15.pdf
[13] T. Kato, K. Shiromi, M. Nagata, H. Nakashima, and K. Matsuo, "Gait pattern acquisition for four-legged mobile robot by genetic algorithm," in IECON 2015-41st Annual Conference of the IEEE Industrial Electronics Society, 2015: IEEE, pp. 004854-004857.
doi: 10.1109/IECON.2015.7392860
[14] Y. Liu, Y. Wei, C. Wang, and H. Wu, "Trajectory optimization for adaptive deformed wheels to overcome steps using an improved hybrid genetic algorithm and an adaptive particle swarm optimization," Mathematics, vol. 12, no. 13, p. 2077, 2024. doi: 10.3390/math12132077
[15] G. Chen and J. Liu, "Mobile robot path planning using ant colony algorithm and improved potential field method," Computational intelligence and neuroscience, vol. 2019, no. 1, p. 1932812, 2019.
doi: 10.1155/2019/1932812
[16] J. M. García, J. L. Martínez, A. Mandow, and A. García-Cerezo, "Caster-leg aided maneuver for negotiating surface discontinuities with a wheeled skid-steer mobile robot," Robotics and Autonomous Systems, vol. 91, pp. 25-37, 2017.
doi: 10.1016/j.robot.2016.12.007
[17] Z. Gyenes, L. Bölöni, and E. G. Szádeczky-Kardoss, "Can genetic algorithms be used for real-time obstacle avoidance for lidar-equipped mobile robots?," Sensors, vol. 23, no. 6, p. 3039, 2023.
doi: 10.3390/s23063039
[18] S. Abinaya, V. H. Kumar, P. S. Karthic, D. Tamilselvi, and S. M. Shalinie, "Hybrid genetic algorithm approach for mobile robot path planning," Advances in Natural and Applied Sciences, vol. 8, no. 17, pp. 41-48, 2014.
[19] K. B. Lim, S. Park, S. Kim, J. M. Jeong, and Y.-S. Yoon, "Behavior planning of an unmanned ground vehicle with actively articulated suspension to negotiate geometric obstacles," in 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2009: IEEE, pp. 821-826.
doi: 10.1109/IROS.2009.5354137
[20] K. B. Lim, S. J. Kim, and Y.-S. Yoon, "Deliberative planner for UGV with actively articulated suspension to negotiate geometric obstacles by using centipede locomotion pattern," in ICCAS 2010, 2010: IEEE, pp. 1482-1486. doi: 10.1109/ICCAS.2010.5670132
[21] K. B. Lim and Y.-S. Yoon, "Reconfiguration planning for a robotic vehicle with actively articulated suspension in obstacle Terrain during straight motion," Advanced Robotics, vol. 26, no. 13, pp. 1471-1494, 2012. doi: 10.1080/01691864.2012.690191
[22] S. Jeong and M. Won, "Motion Planning and Control of Wheel-legged Robot for Obstacle Crossing," The Journal of Korea Robotics Society, vol. 17, no. 4, pp. 500-507, 2022. doi: 10.7746/jkros.2022.17.4.500
[23] E. Papadopoulos and D. A. Rey, "A new measure of tipover stability margin for mobile manipulators," in Proceedings of IEEE International Conference on Robotics and Automation, 1996, vol. 4: IEEE, pp. 3111-3116. doi: 10.1109/ROBOT.1996.509185
[24] K. D. Iagnemma, A. Rzepniewski, S. Dubowsky, P. Pirjanian, T. L. Huntsberger, and P. S. Schenker, "Mobile robot kinematic reconfigurability for rough terrain," in Sensor Fusion and Decentralized Control in Robotic Systems III, 2000, vol. 4196: SPIE, pp. 413-420.
doi: 10.1117/12.403739
[25] W.-H. Wang, X.-J. Xu, H.-J. Xu, and C.-L. Sun, "Development of variable-configuration wheeled driving system for enhancing the obstacle-crossing ability of unmanned vehicles," Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, vol. 235, no. 9, pp. 1645-1659, 2021. doi: 10.1177/0954406220951600
[26] K. B. Lim, J.-h. Kang, Y.-S. Yoon, S. H. Lee, and S. Kang, "Obstacle-overcoming algorithm for unmanned ground vehicle with actively articulated suspensions on unstructured terrain," in 2008 International Conference on Control, Automation and Systems, 2008: IEEE, pp. 324-328. doi: 10.1109/ICCAS.2008.4694665
[27] M. Mosadeghzad, D. Naderi, and S. Ganjefar, "Dynamic modeling and stability optimization of a redundant mobile robot using a genetic algorithm," Robotica, vol. 30, no. 3, pp. 505-514, 2012.
doi: 10.1017/S0263574711000804
[28] X. Ding, K. Li, and K. Xu, "Dynamics and wheel's slip ratio of a wheel-legged robot in wheeled motion considering the change of height," Chinese Journal of Mechanical Engineering, vol. 25, no. 5, pp. 1060-1067, 2012. doi: 10.3901/CJME.2012.05.1060
[29] Y. Li, "Dynamic Simulation Analyses of a Six-leg-wheel Hybrid Mobile Robot under uneven terrains," in 2010 Third International Conference on Intelligent Networks and Intelligent Systems, 2010: IEEE, pp. 308-311. doi: 10.1109/ICINIS.2010.176
[30] J. Niu, H. Wang, H. Shi, N. Pop, D. Li, S. Li, and S. Wu, "Study on structural modeling and kinematics analysis of a novel wheel-legged rescue robot," International Journal of Advanced Robotic Systems, vol. 15, no. 1, p. 1729881417752758, 2018.
doi: 10.1177/1729881417752758
[31] J. Zhao, T. Han, S. Wang, C. Liu, J. Fang, and S. Liu, "Design and research of all-terrain wheel-legged robot," Sensors, vol. 21, no. 16, p. 5367, 2021.
doi: 10.3390/s21165367