No CrossRef data available.
Article contents
Recurrent neural network-based dynamic obstacle avoidance for dual-arm robot with joint discomfort optimization
Published online by Cambridge University Press: 05 May 2026
Abstract
Humanoid dual-arm robots face significant challenges in planning safe and humanoid motions during collaborative tasks due to overlapping workspaces and kinematic redundancy. This paper proposes a real-time joint adjustment planning method that optimizes dual-arm motion by defining a “joint discomfort” metric, which quantifies the deviation of joint angles from their comfort positions, thereby enhancing the naturalness and human-likeness of the motion. Leveraging the parallel computing capability of recurrent neural networks (RNNs) and the redundancy resolution of dual arms, our method dynamically adjusts joint configurations to minimize discomfort while integrating trajectory tracking and obstacle avoidance constraints. Predefined tasks and constraints are formulated as a Quadratic Programming (QP) problem, efficiently solved using an RNN-based approach. Numerical simulations and physical experiments on the Ginger robot – a dual-arm system with 7-degree-of-freedom (DOF) manipulators – validate the efficacy of the proposed planning method in three key aspects: (1) optimizing joint space utilization to enhance workspace flexibility, (2) adaptively regulating joint motions, and (3) achieving sub-millimeter tracking accuracy (position error ¡0.15 mm) under dynamically constrained scenarios.
Keywords
Information
- Type
- Research Article
- Information
- Copyright
- © The Author(s), 2026. Published by Cambridge University Press
References
Aldawsari, S. and Chen, Y.-P. P., “Intervention scenarios and robot capabilities for support, guidance and health monitoring for the elderly,” Comput. Sci. Rev. 54, 100687 (2024).CrossRefGoogle Scholar
Li, S., Zhang, Y. and Jin, L., “Kinematic control of redundant manipulators using neural networks,” IEEE Trans. Neural Netw. Learn. 28(10), 2243–2254 (2017).CrossRefGoogle ScholarPubMed
Zhang, Z., Zheng, L., Chen, Z., Kong, L. and Karimi, H. R., “Mutual-collision-avoidance scheme synthesized by neural networks for dual redundant robot manipulators executing cooperative tasks,” IEEE Trans. Neural Netw. Learn. 32(3), 1052–1066 (2021).CrossRefGoogle ScholarPubMed
Yang, S., MacLachlan, R. A. and Riviere, C. N., “Manipulator design and operation of a six-degree-of-freedom handheld tremor-canceling microsurgical instrument,” IEEE/ASME Trans. Mechatron. 20(2), 761–772 (2015).CrossRefGoogle ScholarPubMed
Singh, G. K. and Claassens, J., ”An Analytical Solution for the Inverse Kinematics of a Redundant 7DoF Manipulator with Link Offsets,” In: 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (2010) pp. 2976–2982.Google Scholar
Nearchou, A. C., “Solving the inverse kinematics problem of redundant robots operating in complex environments via a modified genetic algorithm,” Mech. Mach. Theory 33(3), 273–292 (1998).CrossRefGoogle Scholar
Zhang, Y., Li, S., Gui, J. and Luo, X., “Velocity-level control with compliance to acceleration-level constraints: A novel scheme for manipulator redundancy resolution,” IEEE Trans. Ind. Informat. 14(3), 921–930 (2018).CrossRefGoogle Scholar
Maciejewski, A. A. and Klein, C. A., “Obstacle avoidance for kinematically redundant manipulators in dynamically varying environments,” Int. J. Robot. Res. 4, 109–117 (1985).CrossRefGoogle Scholar
Wang, H., Liu, K., Liu, X., Chen, B. and Lin, C., “Neural-based adaptive output-feedback control for a class of nonstrict-feedback stochastic nonlinear systems,” IEEE Trans. Cybern. 45(9), 1977–1987 (2015).CrossRefGoogle ScholarPubMed
Zhang, Y., Wang, J. and Xia, Y., “A dual neural network for redundancy resolution of kinematically redundant manipulators subject to joint limits and joint velocity limits,” IEEE Trans. Neural Netw. 14(3), 658–667 (2003).CrossRefGoogle Scholar
Zhang, Y. and Wang, J., “A dual neural network for constrained joint torque optimization of kinematically redundant manipulators,” IEEE Trans. Syst., Man, Cybern., Part B (Cybern.) 32(5), 654–662 (2002).CrossRefGoogle Scholar
Wiedmeyer, W., Altoé, P., Auberle, J., Ledermann, C. and Kröger, T., “A real-time-capable closed-form multi-objective redundancy resolution scheme for seven-dof serial manipulators,” IEEE Robot. Autom. Lett. 6(2), 431–438 (2021).CrossRefGoogle Scholar
Faria, C., Ferreira, F., Erlhagen, W., Monteiro, S. and Bicho, E., “Position-based kinematics for 7-dof serial manipulators with global configuration control, joint limit and singularity avoidance,” Mech. Mach. Theory 121, 317–334 (2018).CrossRefGoogle Scholar
Cai, B. and Zhang, Y., “Different-level redundancy-resolution and its equivalent relationship analysis for robot manipulators using gradient-descent and zhang ’s neural-dynamic methods,” IEEE Trans. Ind. Electron. 59(8), 3146–3155 (2012).CrossRefGoogle Scholar
Khatib, O., “Real-Time Obstacle Avoidance for Manipulators and Mobile Robots,” In: 1985 IEEE International Conference on Robotics and Automation, vol. 2 (1985) pp. 500–505.Google Scholar
Quan, Y., Wang, K., Zhao, C., Lv, C., Zhao, H. and Lv, H., “Obstacle avoidance method for fixed trajectory of a seven-degree-of-freedom manipulator,” Robotica 41(5), 1515–1535 (2023).CrossRefGoogle Scholar
Csiszar, A., Drust, M., Dietz, T., Verl, A. and Brisan, C., ”Dynamic and Interactive Path Planning and Collision Avoidance for an Industrial Robot using Artificial Potential Field Based Method,” In: Mechatronics Jabloński, R. and Březina, T. eds.) (Springer, Berlin, Heidelberg, 2012) pp. 413–421.Google Scholar
Merchan-Cruz, E. and Morris, A., “Fuzzy-ga-based trajectory planner for robot manipulators sharing a common workspace,” IEEE Trans. Robot. 22(4), 613–624 (2006).CrossRefGoogle Scholar
Wei, L., Wang, Y., Hu, Y. and Lam, T. L., “Online dual robot-human collaboration trajectory generation by convex optimization,” Robot. Comput.-Intergr. Manuf. 91, 102850 (2025).CrossRefGoogle Scholar
Qin, X., Liao, Z., Liu, C. and Xiong, Z., “Online task allocation and scheduling in multi-manipulator system considering collision constraints and unknown tasks,” Robot. Comput.-Intergr. Manuf. 90, 102808 (2024).CrossRefGoogle Scholar
Khan, A. H., Li, S. and Luo, X., “Obstacle avoidance and tracking control of redundant robotic manipulator: An rnn-based metaheuristic approach,” IEEE Trans. Ind. Informat. 16(7), 4670–4680 (2020).CrossRefGoogle Scholar
Ijaz, M. U., Khan, A. T. and Li, S., “Bio-inspired bas: Run-time path-planning and the control of differential mobile robot,” EAI Endors. Trans. AI Robot. 1(1), 6–2022.Google Scholar
Fitts, P. M., “The information capacity of the human motor system in controlling the amplitude of movement,” J. Exp. Psychol. 47 (6), 381–391 (1954).CrossRefGoogle ScholarPubMed
Uno, Y., Kawato, M. and Suzuki, R., “Formation and control of optimal trajectory in human multijoint arm movement,” Biol. Cybern. 61, 89–101 (1989).CrossRefGoogle Scholar
Soechting, J. F., Buneo, C. A., Herrmann, U. and Flanders, M., “Moving effortlessly in three dimensions: Does donders’ law apply to arm movement?,” J. Neurosci. 15(9), 6271–6280 (1995).CrossRefGoogle ScholarPubMed
Jung, E. S. and Choe, J., “Human reach posture prediction based on psychophysical discomfort,” Int. J. Ind. Ergonom. 18(2–3), 173–179 (1996).CrossRefGoogle Scholar
Li, S., Han, K., He, P., Li, Z., Liu, Y. and Xiong, Y., “Human-like redundancy resolution: An integrated inverse kinematics scheme for anthropomorphic manipulators with radial elbow offset,” Adv. Eng. Informat. 54, 101812 (2022).CrossRefGoogle Scholar
Pattacini, U., Nori, F., Natale, L., Metta, G. and Sandini, G., “An Experimental Evaluation of a Novel Minimum-Jerk Cartesian Controller for Humanoid Robots,” In: 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (2010) pp. 1668–1674.Google Scholar
Nguyen, P. D., Bottarel, F., Pattacini, U., Hoffmann, M., Natale, L. and Metta, G., “Merging Physical and Social Interaction for Effective Human–Robot Collaboration,” In: 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids) (2018) pp. 1–9.Google Scholar
Nguyen, D. H. P., Hoffmann, M., Roncone, A., Pattacini, U. and Metta, G., “Compact Real-Time Avoidance on a Humanoid Robot for Human–Robot Interaction,” In: 2018 13th ACM/IEEE International Conference on Human–Robot Interaction (HRI) (2018) pp. 416–424.Google Scholar
Suleiman, W., “On inverse kinematics with inequality constraints: New insights into minimum jerk trajectory generation,” Adv. Robot. 30(17–18), 1164–1172 (2016).CrossRefGoogle Scholar
Zhao, J., Xie, B. and Song, C., “Generating human-like movements for robotic arms,” Mech. Mach. Theory 81, 107–128 (2014).CrossRefGoogle Scholar
Yang, J., Marler, R. T. and Kim, H., “Multi-objective Optimization for Upper Body Posture Prediction,” In: 10th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference (2004) p. 4506.Google Scholar
Ma, L., Zhang, W., Chablat, D., Bennis, F. and Guillaume, F., “Multi-objective optimisation method for posture prediction and analysis with consideration of fatigue effect and its application case,” Comput. Ind. Eng. 57(4), 1235–1246 (2009).CrossRefGoogle Scholar
Zhao, Q., Lu, T., Tao, M., Cheng, S. and Wen, G., “Inertial motion capture-driven digital human for ergonomic validation: A case study of core drilling,” Sensors 24(18), 5962 (2024).CrossRefGoogle ScholarPubMed
Zhang et al. supplementary material
Zhang et al. supplementary material
File
76.9 MB