Publications
Impact of haptic cues and an active ankle exoskeleton on gait characteristics
July 1, 2022
Journal Article
Published in:
Hum. Factors, Vol. 0, No. 0, July 2022, p. 1-12.
Summary
Objective This study examined the interaction of gait-synchronized vibrotactile cues with an active ankle exoskeleton that provides plantarflexion assistance. Background An exoskeleton that augments gait may support collaboration through feedback to the user about the state of the exoskeleton or characteristics of the task. Methods Participants (N = 16) were provided combinations of torque assistance and vibrotactile cues at pre-specified time points in late swing and early stance while walking on a self-paced treadmill. Participants were either given explicit instructions (N = 8) or were allowed to freely interpret (N=8) how to coordinate with cues. Results For the free interpretation group, the data support an 8% increase in stride length and 14% increase in speed with exoskeleton torque across cue timing, as well as a 5% increase in stride length and 7% increase in speed with only vibrotactile cues. When given explicit instructions, participants modulated speed according to cue timing-increasing speed by 17% at cues in late swing and decreasing speed 11% at cues in early stance compared to no cue when exoskeleton torque was off. When torque was on, participants with explicit instructions had reduced changes in speed. Conclusion These findings support that the presence of torque mitigates how cues were used and highlights the importance of explicit instructions for haptic cuing. Interpreting cues while walking with an exoskeleton may increase cognitive load, influencing overall human-exoskeleton performance for novice users. Application Interactions between haptic feedback and exoskeleton use during gait can inform future feedback designs to support coordination between users and exoskeletons.
Summary
Objective This study examined the interaction of gait-synchronized vibrotactile cues with an active ankle exoskeleton that provides plantarflexion assistance. Background An exoskeleton that augments gait may support collaboration through feedback to the user about the state of the exoskeleton or characteristics of the task. Methods Participants (N = 16) were...
READ MORE
COVID-19 exposure notification in simulated real-world environments
April 15, 2022
Project Report
Published in:
MIT Lincoln Laboratory Report ACTA-3
Summary
Privacy-preserving contact tracing mobile applications, such as those that use the Google-Apple Exposure Notification (GAEN) service, have the potential to limit the spread of COVID-19 in communities, but the privacy-preserving aspects of the protocol make it difficult to assess the performance of the apps in real-world populations. To address this gap, we exercised the CovidWatch app on both Android and iOS phones in a variety of scripted realworld scenarios, relevant to the lives of university students and employees. We collected exposure data from the app and from the lower-level Android service, and compared it to the phones' actual distances and durations of exposure, to assess the sensitivity and specificity of the GAEN service configuration as of February 2021. Based on the app's reported ExposureWindows and alerting thresholds for Low and High alerts, our assessment is that the chosen configuration is highly sensitive under a range of realistic scenarios and conditions. With this configuration, the app is likely to capture many long-duration encounters, even at distances greater than six feet, which may be desirable under conditions with increased risk of airborne transmission.
Summary
Privacy-preserving contact tracing mobile applications, such as those that use the Google-Apple Exposure Notification (GAEN) service, have the potential to limit the spread of COVID-19 in communities, but the privacy-preserving aspects of the protocol make it difficult to assess the performance of the apps in real-world populations. To address this...
READ MORE
Bluetooth Low Energy (BLE) Data Collection for COVID-19 Exposure Notification
April 13, 2022
Project Report
Published in:
MIT Lincoln Laboratory Report ACTA-2
Summary
Privacy-preserving contact tracing mobile applications, such as those that use the Google-Apple Exposure Notification (GAEN) service, have the potential to limit the spread of COVID-19 in communities; however, the privacy-preserving aspects of the protocol make it difficult to assess the performance of the Bluetooth proximity detector in real-world populations. The GAEN service configuration of weights and thresholds enables hundreds of thousands of potential configurations, and it is not well known how the detector performance of candidate GAEN configurations maps to the actual "too close for too long" standard used by public health contact tracing staff. To address this gap, we exercised a GAEN app on Android phones at a range of distances, orientations, and placement configurations (e.g., shirt pocket, bag, in hand), using RF-analogous robotic substitutes for human participants. We recorded exposure data from the app and from the lower-level Android service, along with the phones' actual distances and durations of exposure.
Summary
Privacy-preserving contact tracing mobile applications, such as those that use the Google-Apple Exposure Notification (GAEN) service, have the potential to limit the spread of COVID-19 in communities; however, the privacy-preserving aspects of the protocol make it difficult to assess the performance of the Bluetooth proximity detector in real-world populations. The...
READ MORE
A neural network estimation of ankle torques from electromyography and accelerometry
August 26, 2021
Journal Article
Published in:
IEEE Trans. Neural Syst. Rehabilitation Eng., Vol. 29, 2021, pp. 1624-33.
Summary
Estimations of human joint torques can provide clinically valuable information to inform patient care, plan therapy, and assess the design of wearable robotic devices. Predicting joint torques into the future can also be useful for anticipatory robot control design. In this work, we present a method of mapping joint torque estimates and sequences of torque predictions from motion capture and ground reaction forces to wearable sensor data using several modern types of neural networks. We use dense feedforward, convolutional, neural ordinary differential equation, and long short-term memory neural networks to learn the mapping for ankle plantarflexion and dorsiflexion torque during standing,walking, running, and sprinting, and consider both single-point torque estimation, as well as the prediction of a sequence of future torques. Our results show that long short-term memory neural networks, which consider incoming data sequentially, outperform dense feedforward, neural ordinary differential equation networks, and convolutional neural networks. Predictions of future ankle torques up to 0.4 s ahead also showed strong positive correlations with the actual torques. The proposed method relies on learning from a motion capture dataset, but once the model is built, the method uses wearable sensors that enable torque estimation without the motion capture data.
Summary
Estimations of human joint torques can provide clinically valuable information to inform patient care, plan therapy, and assess the design of wearable robotic devices. Predicting joint torques into the future can also be useful for anticipatory robot control design. In this work, we present a method of mapping joint torque...
READ MORE
Health-informed policy gradients for multi-agent reinforcement learning
April 1, 2021
Journal Article
Published in:
https://arxiv.org/abs/1908.01022
Summary
This paper proposes a definition of system health in the context of multiple agents optimizing a joint reward function. We use this definition as a credit assignment term in a policy gradient algorithm to distinguish the contributions of individual agents to the global reward. The health-informed credit assignment is then extended to a multi-agent variant of the proximal policy optimization algorithm and demonstrated on simple particle environments that have elements of system health, risk-taking, semi-expendable agents, and partial observability. We show significant improvement in learning performance compared to policy gradient methods that do not perform multi-agent credit assignment.
Summary
This paper proposes a definition of system health in the context of multiple agents optimizing a joint reward function. We use this definition as a credit assignment term in a policy gradient algorithm to distinguish the contributions of individual agents to the global reward. The health-informed credit assignment is then...
READ MORE
Ablation analysis to select wearable sensors for classifying standing, walking, and running
December 30, 2020
Journal Article
Published in:
Sensors, Vol. 21, No. 1, 30 December 2020, 194.
Summary
The field of human activity recognition (HAR) often utilizes wearable sensors and machine learning techniques in order to identify the actions of the subject. This paper considers the activity recognition of walking and running while using a support vector machine (SVM) that was trained on principal components derived from wearable sensor data. An ablation analysis is performed in order to select the subset of sensors that yield the highest classification accuracy. The paper also compares principal components across trials to inform the similarity of the trials. Five subjects were instructed to perform standing, walking, running, and sprinting on a self-paced treadmill, and the data were recorded while using surface electromyography sensors (sEMGs), inertial measurement units (IMUs), and force plates. When all of the sensors were included, the SVM had over 90% classification accuracy using only the first three principal components of the data with the classes of stand, walk, and run/sprint (combined run and sprint class). It was found that sensors that were placed only on the lower leg produce higher accuracies than sensors placed on the upper leg. There was a small decrease in accuracy when the force plates are ablated, but the difference may not be operationally relevant. Using only accelerometers without sEMGs was shown to decrease the accuracy of the SVM.
Summary
The field of human activity recognition (HAR) often utilizes wearable sensors and machine learning techniques in order to identify the actions of the subject. This paper considers the activity recognition of walking and running while using a support vector machine (SVM) that was trained on principal components derived from wearable...
READ MORE
Ankle torque estimation during locomotion from surface electromyography and accelerometry
November 29, 2020
Conference Paper
Published in:
2020 8th IEEE Intl. Conf. on Biomedical Robotics and Biomechatronics, BioRob, 29 November - 1 December 2020.
Summary
Estimations of human joint torques can provide quantitative, clinically valuable information to inform patient care, plan therapy, and assess the design of wearable robotic devices. Standard methods for estimating joint torques are limited to laboratory or clinical settings since they require expensive equipment to measure joint kinematics and ground reaction forces. Wearable sensor data combined with neural networks may offer a less expensive and obtrusive estimation method.We present a method of mapping joint torque estimates obtained from motion capture and ground reaction forces to wearable sensor data. We use several different neural networks to learn the torque mapping for the ankle joints during standing, walking, running, and sprinting. Our results show that neural networks that consider time (recurrent and long short-term memory networks) outperform feedforward network architectures, producing results in the range of 0.005-0.008 N m/kg mean squared error (MSE) when compared to the inverse dynamics model on which it was trained. As a point of reference, the typical measurement errors from inverse dynamics models are in the range of 0.0004-0.0064 N m/kg MSE. Errors tended to increase with locomotion speed, with the highest errors during sprinting and the lowest during standing or walking. Future work may investigate model generalizability across sensor placements, subjects, locomotion variants, and usage duration. The proposed method relies on learning from a motion capture dataset, but once the model is built, the method uses wearable sensors that enable torque estimation without the motion capture data. These methods also have potential uses for the design and testing of wearable robotic systems outside of a laboratory environment.
Summary
Estimations of human joint torques can provide quantitative, clinically valuable information to inform patient care, plan therapy, and assess the design of wearable robotic devices. Standard methods for estimating joint torques are limited to laboratory or clinical settings since they require expensive equipment to measure joint kinematics and ground reaction...
READ MORE
A workflow for non-linear load parameter estimation using a power-hardware-in-the-loop experimental testbed
March 15, 2020
Conference Paper
Published in:
2020 IEEE Applied Power Electronics Conf. and Expo., APEC, 15-19 March 2020.
Summary
Low-inertia microgrids may easily have a single load which can make up most of the total load, thereby greatly affecting stability and power quality. Instead of static load models, dynamic load models are presented here for constant current loads (CILs) and constant power loads (CPLs). Next, a flexible Power-Hardware-in-the-Loop (PHiL) testbed is employed for the experiments in this work. The PHiL testbed consists of a real-time computer working with a power amplifier in order to perturb its voltage and frequency. A connected load serves as the device under test (DUT). Using the captured experimental data as a reference, a parameter estimation algorithm is then implemented. The resulting parameter estimates are used to define simulation models. Both the CIL and CPL dynamic models are simulated to produce waveforms that closely resemble experimental waveforms. The algorithm, referred to as an enhanced monte carlo algorithm (EMCA), is explained in this work. Finally, the EMCA's resulting parameter estimates are presented.
Summary
Low-inertia microgrids may easily have a single load which can make up most of the total load, thereby greatly affecting stability and power quality. Instead of static load models, dynamic load models are presented here for constant current loads (CILs) and constant power loads (CPLs). Next, a flexible Power-Hardware-in-the-Loop (PHiL)...
READ MORE
Modeling and distributed control of microgrids: a negative feedback approach
December 11, 2019
Conference Paper
Published in:
2019 IEEE 58th Conf. on Decision and Control, CDC, 11-13 December 2019.
Summary
In this paper, we first show how general microgrid can be modeled as a negative feedback configuration comprising two subsystems. The first subsystem is the interconnected microgrid grid which is affected through negative feedback by the second subsystem consisting of all single-port components. This is modeled by transforming physical state variables into energy state variables and by systematically defining input and output of system components in this transformed state space. We next draw on the fact that for this basic feedback configuration there exist several types of conditions regarding subsystem properties which ensure overall system properties. In particular, we utilize dissipativity theory to propose a subsystem nonlinear control design for heterogeneous resource components comprising microgrids so that they jointly result in a closed-loop feasible and stable dynamical system for given ranges of system disturbances.
Summary
In this paper, we first show how general microgrid can be modeled as a negative feedback configuration comprising two subsystems. The first subsystem is the interconnected microgrid grid which is affected through negative feedback by the second subsystem consisting of all single-port components. This is modeled by transforming physical state...
READ MORE
Design, simulation, and fabrication of three-dimensional microsystem components using grayscale photolithography
October 1, 2019
Journal Article
Published in:
J. Micro/Nanolith., Vol. 18, No. 4, October - December 2019, 043507.
Summary
Grayscale lithography is a widely known but underutilized microfabrication technique for creating three-dimensional (3-D) microstructures in photoresist. One of the hurdles for its widespread use is that developing the grayscale photolithography masks can be time-consuming and costly since it often requires an iterative process, especially for complex geometries. We discuss the use of PROLITH, a lithography simulation tool, to predict 3-D photoresist profiles from grayscale mask designs. Several examples of optical microsystems and microelectromechanical systems where PROLITH was used to validate the mask design prior to implementation in the microfabrication process are presented. In all examples, PROLITH was able to accurately and quantitatively predict resist profiles, which reduced both design time and the number of trial photomasks, effectively reducing the cost of component fabrication.
Summary
Grayscale lithography is a widely known but underutilized microfabrication technique for creating three-dimensional (3-D) microstructures in photoresist. One of the hurdles for its widespread use is that developing the grayscale photolithography masks can be time-consuming and costly since it often requires an iterative process, especially for complex geometries. We discuss...
READ MORE