A review of current state-of-the-art control methods for lower-limb powered prostheses

Gehlhar, Rachel; Tucker, Maegan; Young, Aaron; Ames, Aaron D.

doi:10.1016/j.arcontrol.2023.03.003

Cited by 25 publications

(10 citation statements)

References 174 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For equation‐error autoregressive (EEAR) systems, a filtered generalized projection‐based iterative identification method, a filtered (multi‐innovation) generalized gradient‐based iterative identification method, and a filtered (multi‐innovation) generalized least squares‐based iterative identification method are proposed. Although these filtered generalized iterative identification methods are proposed for equation‐error autoregressive systems under the interference of autoregressive noises, the basic idea can be extended to linear and nonlinear stochastic systems with colored noises 112–121 . and can be applied to engineering systems 122–129 such as process control and manufacture systems.…”

Section: Discussionmentioning

confidence: 99%

Filtered generalized iterative parameter identification for equation‐error autoregressive models based on the filtering identification idea

Ding,

Shao,

et al. 2024

Adaptive Control & Signal

View full text Add to dashboard Cite

SummaryBy using the collected batch data and the iterative search, and based on the filtering identification idea, this article investigates and proposes a filtered multi‐innovation generalized projection‐based iterative identification method, a filtered generalized gradient‐based iterative identification method, a filtered generalized least squares‐based iterative identification method, a filtered multi‐innovation generalized gradient‐based iterative identification method and a filtered multi‐innovation generalized least squares‐based iterative identification method for equation‐error autoregressive systems described by the equation‐error autoregressive models. These filtered generalized iterative identification methods can be extended to other linear and nonlinear scalar and multivariable stochastic systems with colored noises.

show abstract

Section: Discussionmentioning

confidence: 99%

Filtered generalized iterative parameter identification for equation‐error autoregressive models based on the filtering identification idea

Ding,

Shao,

et al. 2024

Adaptive Control & Signal

View full text Add to dashboard Cite

show abstract

“…It is important to note that our visual perception system is designed to supplement, not replace, the existing intent recognition systems of robotic prosthetic legs and exoskeletons that use mechanical, inertial, and/or EMG data to estimate the current state of the human-robot-environment system [26]. We view computer vision as a means to improve the speed and accuracy of locomotion mode (intent) recognition by minimizing the search space of potential solutions based on the perceived walking environment.…”

Section: Discussionmentioning

confidence: 99%

AI-Powered Smart Glasses for Sensing and Recognition of Human-Robot Walking Environments

Rossos,

Mihailidis,

Laschowski

2023

Preprint

View full text Add to dashboard Cite

Environment sensing and recognition can allow humans and robots to dynamically adapt to different walking terrains. However, fast and accurate visual perception is challenging, especially on embedded devices with limited computational resources. The purpose of this study was to develop a novel pair of AI-powered smart glasses for onboard sensing and recognition of human-robot walking environments with high accuracy and low latency. We used a Raspberry Pi Pico microcontroller and an ArduCam HM0360 low-power camera, both of which interface with the eyeglass frames using 3D-printed mounts that we custom-designed. We trained and optimized a lightweight and efficient convolutional neural network using a MobileNetV1 backbone to classify the walking terrain as either indoor surfaces, outdoor surfaces (grass and dirt), or outdoor surfaces (paved) using over 62,500 egocentric images that we adapted and manually labelled from the Meta Ego4D dataset. We then compiled and deployed our deep learning model using TensorFlow Lite Micro and post-training quantization to create a minimized byte array model of size 0.31MB. Our system was able to accurately predict complex walking environments with 93.6% classification accuracy and had an embedded inference speed of 1.5 seconds during online experiments using the integrated camera and microcontroller. Our AI-powered smart glasses open new opportunities for visual perception of human-robot walking environments where embedded inference and a low form factor is required. Future research will focus on improving the onboard inference speed and miniaturization of the mechatronic components.

show abstract

“…Our algorithm could include a third layer capable of handling transition state-action pairs between different locomotion modes and adding additional instances to our second layer for each mode such that each instance of the second layer is responsible for a specific locomotor task, while the third layer is responsible for task transitions. This hierarchical architecture resembles the control system design of most robotic leg prostheses and exoskeletons [1]. For example, deep learning models of vision [34][35], inertial, and/or EMG data used for high-level locomotion mode recognition could be integrated with reinforcement learning algorithms at the mid-level for end-to-end AI-powered robotic leg control.…”

Section: Discussionmentioning

confidence: 99%

“…Control of robotic leg prostheses and exoskeletons is an open problem and an active area of research [1], [2]. Computer simulation can be used to study the dynamics and control of human walking and extract principles that can be programmed into robotic legs to behave similar to biological legs.…”

Section: Introductionmentioning

confidence: 99%

Reinforcement Learning for Control of Human Locomotion in Simulation

Dashkovets,

Laschowski

2023

Preprint

View full text Add to dashboard Cite

Control of robotic leg prostheses and exoskeletons is an open challenge. Computer modeling and simulation can be used to study the dynamics and control of human walking and extract principles that can be programmed into robotic legs to behave similar to biological legs. In this study, we present the development of an efficient two-layer Q-learning algorithm, with k-d trees, that operates over continuous action spaces and a reward model that estimates the degree of muscle activation similarity between the agent and human state-to-action pairs and state-to-action sequences. We used a human musculoskeletal model acting in a high-dimensional, physics-based simulation environment to train and evaluate our algorithm to simulate biomimetic walking. We used imitation learning and artificial bio-mechanics data to accelerate training via expert demonstrations and used experimental human data to compare and validate our predictive simulations, achieving 79% accuracy. Also, when compared to the previous state-of-the-art that used deep deterministic policy gradient, our algorithm was significantly more efficient with lower computational and memory storage requirements (i.e., requiring 7 times less RAM and 87 times less CPU compute), which can benefit real-time embedded computing. Overall, our new two-layer Q-learning algorithm using sequential data for continuous imitation of human locomotion serves as a first step towards the development of bioinspired controllers for robotic prosthetic legs and exoskeletons. Future work will focus on improving the prediction accuracy compared to experimental data and expanding our simulations to other locomotor activities.

show abstract

A review of current state-of-the-art control methods for lower-limb powered prostheses

Cited by 25 publications

References 174 publications

Filtered generalized iterative parameter identification for equation‐error autoregressive models based on the filtering identification idea

Filtered generalized iterative parameter identification for equation‐error autoregressive models based on the filtering identification idea

AI-Powered Smart Glasses for Sensing and Recognition of Human-Robot Walking Environments

Reinforcement Learning for Control of Human Locomotion in Simulation

Contact Info

Product

Resources

About