AI-Driven Structural Design Advances in Assistive Rehabilitation Exoskeleton Robots

Mengfu He

doi:10.54097/v42ntz28

Authors

Mengfu He

DOI:

https://doi.org/10.54097/v42ntz28

Keywords:

Rehabilitation Exoskeleton Robots; Exoskeleton Structural Design; AI-Driven Design Methods; Generative Design and Topology Optimization; Biomimetic Structural Inspiration.

Abstract

Limb dysfunction is widespread among rehabilitation populations, such as chronic stroke patients. Confronted with substantial global rehabilitation needs, requirements for exoskeletons—including comfort and functionality—have been further elevated. The recent rapid advancement of artificial intelligence technology offers new opportunities for optimizing traditional exoskeleton structural design. Given the current lack of review studies on how AI can inform exoskeleton structural design, this article focuses on recent advances in AI-driven structural design for assistive rehabilitation exoskeletons. The author conducted a literature review to summarize and analyze recent studies. This paper systematically compares three traditional design methods with three AI-driven design approaches. The traditional methods include model-based design, iterative experiments based on user feedback, and experience- or bio-inspired structural design. The AI-driven approaches include data-driven surrogate modeling, generative design and topology optimization, and personalized human data-driven intelligent structural design. Finally, this study concludes that the introduction of AI has led to improvements in computational efficiency and iteration cycles in structural design. However, further research is warranted to deepen the validation of structural design implementations.

Downloads

Download data is not yet available.

References

[1] Boardsworth K, Rashid U, Olsen S, et al. Upper limb robotic rehabilitation following stroke: a systematic review and meta-analysis investigating efficacy and the influence of device features and program parameters. Journal of NeuroEngineering and Rehabilitation, 2025, 22(1): 164.

[2] Nicora G, Pe S, Santangelo G, et al. Systematic review of AI/ML applications in multi-domain robotic rehabilitation: trends, gaps, and future directions. Journal of NeuroEngineering and Rehabilitation, 2025, 22(1): 79.

[3] Nasr A, Ferguson S, McPhee J. Model-based design and optimization of passive shoulder exoskeletons. Journal of Computational and Nonlinear Dynamics, 2022, 17(5): 051004.

[4] Pérez-Soto M, Marín J, Marín J J. L-GABS: Parametric modeling of a generic active lumbar exoskeleton for ergonomic impact assessment. Sensors, 2025, 25(5): 1340.

[5] D'hondt L, Falisse A, Gupta D, et al. PredSim: a framework for rapid predictive simulations of locomotion. 2024 10th IEEE RAS/EMBS International Conference for Biomedical Robotics and Biomechatronics (BioRob). IEEE, 2024: 1208-1213.

[6] Slade P, Kochenderfer M J, Delp S L, et al. Personalizing exoskeleton assistance while walking in the real world. Nature, 2022, 610(7931): 277-282.

[7] Park D, An J, Lee D, et al. Human-in-the-loop optimization of hip exoskeleton assistance during stair climbing. IEEE Transactions on Biomedical Engineering, 2025.

[8] Tian M, Liu Y, Chen Z, et al. Biomimetic Design and Validation of an Adaptive Cable-Driven Elbow Exoskeleton Inspired by the Shrimp Shell. Biomimetics, 2025, 10(5): 271.

[9] Cardoso A, Ribeiro A, Carneiro P, et al. Evaluating exoskeletons for WMSD prevention: A systematic review of applications and ergonomic approach in occupational settings. International journal of environmental research and public health, 2024, 21(12): 1695.

[10] Hashemi A, Jang J, Beheshti J. A machine learning-based surrogate finite element model for estimating the dynamic response of mechanical systems. IEEE Access, 2023, 11: 54509-54525.

[11] Kneifl J, Rosin D, Avci O, et al. Low-dimensional data-based surrogate model of a continuum-mechanical musculoskeletal system based on non-intrusive model order reduction. Archive of Applied Mechanics, 2023, 93(9): 3637-3663.

[12] Mahmoudi A, Rinderknecht S, Seyfarth A, et al. Design optimization platform for assistive wearable devices applied to a knee damper exoskeleton. Wearable Technologies, 2025, 6: e30.

[13] Manasa C M, BK P K, Bali M. Reinforcement learning-based topology optimization for generative designed lightweight structures. MethodsX, 2025: 103539.

[14] Stroppa F, Soylemez A, Yuksel H T, et al. Optimizing exoskeleton design with evolutionary computation: An intensive survey. Robotics, 2023, 12(4): 106.

[15] Mariano F, Pitzalis R F, Monica L, et al. Traditional vs generative design optimization for novel wrist exoskeleton. 2024 20th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA). IEEE, 2024: 1-7.

[16] Lambranzi C, Oberti G, Di Natali C, et al. Impact of a lower limb exosuit anchor points on energetics and biomechanics. IEEE Transactions on Biomedical Engineering, 2025.

[17] Chen Y, Yu W, Benali A, et al. Towards human-like walking with biomechanical and neuromuscular control features: personalized attachment point optimization method of Cable-Driven exoskeleton. Frontiers in Aging Neuroscience, 2024, 16: 1327397.

[18] KhalilianMotamed Bonab A, Chiaradia D, Frisoli A, et al. A framework for modeling, optimization, and musculoskeletal simulation of an elbow–wrist exosuit. Robotics, 2024, 13(4): 60.

[19] Wu B, Chen C, Wang S, et al. A novel personalized strategy for hip joint flexion assistance based on human physiological State. Biosensors, 2024, 14(9): 418.