CRCNS Research Proposal: Collaborative Research: Data-driven approaches for restoring naturalistic motor functions using functional neural stimulation

下肢瘫痪的患者在中枢神经系统中仍有计划和启动步态的能力，但由于脊髓损伤或中风等情况，无法将这些指令传递给下肢肌肉。该研究项目采用了一种受生物学启发的数据驱动方法来解决这一缺陷。具体来说，研究小组正在开发和评估机器学习方法和神经电刺激来控制下肢运动。目标是开发和评估在瘫痪动物模型中恢复自然，协调和优雅步态的方法。这项活动是为瘫痪社区提供利益的第一步，它为功能性步态恢复系统的开发和商业化创造了途径，使瘫痪的肢体能够更自然地、可控地运动。此外，该项目还提供了独特的机会，培养工程专业学生在临床前研究中的表现，将这些未来的研究人员置于工程技术和医学研究的前沿。本研究项目旨在开发和评估方法，以恢复自然，协调和优美的步态在瘫痪动物模型中，通过一系列实验支持的多学科和多大学研究团队的协同合作，并结合创新建模和算法开发。具体而言，该项目旨在实现以下子目标，涉及在一系列实验中应用数据驱动算法，这些实验旨在在拟议的工作过程中唤起越来越复杂的运动：(a)开发，表征和评估仅在单一方向上单个关节的关节角度和关节扭矩产生的先进控制器，以便将数据驱动模型与早期的经典控制方法进行比较；(b)开发、表征和评估单个关节在两个方向上的关节角度和关节扭矩产生的先进控制器，以阐明先进控制器解决激动剂-拮抗剂肌肉对控制的欠约束问题所使用的方法；(c)开发、表征和评估双向多关节关节角度和关节扭矩产生的先进控制器，阐明先进控制器解决双关节肌肉控制竞争目标问题的方法；(d)通过使用前三个目标产生的高级控制器重新创建自然，协调和优雅的步态，并在跑步机平台上演示此结果。

Individuals with lower limb paralysis retain the ability to plan and initiate gait within the central nervous system but, due to conditions such as spinal cord injury or stroke, are unable to transmit those directives to the muscles of the lower limb. This research project uses a biologically-inspired, data-driven approach to address this deficiency. Specifically, the research team is developing and evaluating machine learning methods and electrical stimulation of nerves to control movements of the lower limbs. The goal is to develop and evaluate methods to restore natural, coordinated, and graceful gait in an animal model of paralysis. This activity is a first step toward providing benefit to the paralyzed community by creating pathways toward the development and commercialization of functional gait restoration systems that evoke more natural, controlled movement of paralyzed limbs. In addition, the project offers unique opportunities to train engineering students in the performance of pre-clinical studies, placing these future researchers at the forefront of engineering technology and medical research. This research project aims to develop and evaluate methods to restore natural, coordinated, and graceful gait in an animal model of paralysis using a synergistic collaboration of a multi-disciplinary and multi-university team of investigators and a combination of innovative modeling and algorithm development supported by a series of experiments. Specifically, the project aims to achieve the following sub-goals involving application of data-driven algorithms in a series of experiments that are designed to evoke increasingly complex movements over the course of the proposed work: (a) Develop, characterize, and evaluate advanced controllers of joint angle and joint torque production of a single joint in only a single direction, to allow comparison of the data-driven model to earlier, classical controls methods; (b) Develop, characterize, and evaluate advanced controllers of joint angle and joint torque production of a single joint in both directions, to elucidate methods used by the advanced controller's solution to the under-constrained problem of agonist-antagonist muscle pair control; (c) Develop, characterize, and evaluate advanced controllers of joint angle and joint torque production of multiple joints in both directions, to elucidate methods used by the advanced controller's solution to the competing-goals problem of biarticular muscle control; and, (d) Recreate natural, coordinated, and graceful gait by use of the advanced controllers arising from the first three goals, and demonstrate this result on a treadmill platform.