基于回归预测,优化用于几乎直接驱动的膝关节外骨架机器人的扭矩控制模型
Yuxuan Xia1, Wei Wei2, Xichuan Lin3
1School of Optoelectronic Science and Engineering, Soochow University, Suzhou 215031, China.
Sensors (Basel, Switzerland)
|March 13, 2024
概括
这项研究开发了一种机器学习模型,用于在爬楼梯时控制外骨膝关节关节. 该模型准确地预测了扭矩,减少了肌肉的劳动力,并改善了用户的辅助.
科学领域:
- 机器人技术 机器人技术 机器人技术
- 生物力学 生物力学
- 机器学习 机器学习
背景情况:
- 控制下肢外骨架机器人,特别是在人机合系统中,由于复杂的,非线性传感器到扭矩映射,提出了挑战.
- 通过传统的数学工具,很难准确地建模关节扭矩.
研究的目的:
- 开发一种非线性回归预测模型,用于预测外骨架机器人的膝关节扭矩.
- 创建一个膝关节扭矩控制模型,以补偿机械和控制系统的延迟.
- 评估开发的控制模型在使用表面电肌图 (sEMG) 协助爬楼梯时的有效性.
主要方法:
- 在爬楼梯时从外骨架机器人收集膝盖扭矩和惯性测量单元 (IMU) 数据.
- 采用了结合卷积神经网络 (CNN) 和长短期记忆 (LSTM) 的多变量网络模型进行非线性近似.
- 在模型训练期间实施时间转移技术,以补偿系统延迟,并生成多个控制模型.
主要成果:
- CNN-LSTM模型成功地学习了膝关节关节扭矩预测的非线性近似值.
- 在轻量级的膝关节外骨上进行的测试显示,直腿骨 (RF) 的sEMG活性减少了20.87%,而大脑中部 (VM) 的sEMG活性增加了17.45%.
- 不同的时间转移参数影响了外骨的性能,优化的转移增强了辅助.
结论:
- 开发的机器学习控制模型在外部骨机器人上爬楼梯时有效地帮助膝关节关节.
- 使用CNN-LSTM与时间转移补偿的方法解决了非线性映射和系统延迟的挑战.
- 实验结果验证了该模型减少用户肌肉劳动和提高外骨性能的能力.
更多相关视频
11:16Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis
Published on: July 22, 2014
16.3K
05:25Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS
Published on: June 7, 2024
1.2K
相关概念视频
Net Torque Calculations
9.1K
When a mechanic tries to remove a hex nut with a wrench, it is easier if the force is applied at the farthest end of the wrench handle. The lever arm is the distance from the pivot point (the hex nut in this case) to the person’s hand. If this distance is large, the torque is higher. Only the component of the force perpendicular to the lever arm contributes to the torque. Therefore, pushing the wrench perpendicular to the lever arm is more advantageous. If multiple people apply force to...
9.1K
Torque Free Motion
480
The torque-free motion refers to the movement of a rigid body in space when no external torques are acting upon it. This type of motion can be observed in environments where there are no external forces or frictions, like in outer space. For example, a rotation of Mars in space is a torque-free motion. Mars is an axisymmetric object, meaning it has an axis of symmetry along which it rotates, designated as the z-axis. The rotating frame of reference is defined such that the center of mass of...
480
Time-Domain Interpretation of PD Control
107
Proportional-Derivative (PD) control is a widely used control method in various engineering systems to enhance stability and performance. In a system with only proportional control, common issues include high maximum overshoot and oscillation, observed in both the error signal and its rate of change. This behavior can be divided into three distinct phases: initial overshoot, subsequent undershoot, and gradual stabilization.
Consider the example of control of motor torque. Initially, a positive...
Consider the example of control of motor torque. Initially, a positive...
107
Mechanical Efficiency of Real Machines
688
The mechanical efficiency of a machine is a fundamental concept that describes how effectively a machine can convert input work into output work. According to this concept, the efficiency of a machine is equal to the ratio of the output work to the input work. An ideal machine, meaning a machine that has no energy losses, has an efficiency of one. This implies that the input work and the output work are equal.
However, in reality, no machine can be truly ideal, and all of them experience some...
However, in reality, no machine can be truly ideal, and all of them experience some...
688
Work and Energy for Variable Forces
3.6K
When an object is acted upon by a variable force, the amount of work done and the change in energy of the object can be more complex to calculate compared to when a constant force is applied. Work is the product of force and displacement, while energy is the capacity of a system to do work. When a constant force is applied to an object, the work done can be calculated as the product of the force and the distance moved in the direction of the force. However, when a variable force is applied, the...
3.6K
Kinematic Equations: Problem Solving
12.4K
When analyzing one-dimensional motion with constant acceleration, the problem-solving strategy involves identifying the known quantities and choosing the appropriate kinematic equations to solve for the unknowns. Either one or two kinematic equations are needed to solve for the unknowns, depending on the known and unknown quantities. Generally, the number of equations required is the same as the number of unknown quantities in the given example. Two-body pursuit problems always require two...
12.4K
