Dynamic switching and real-time machine learning for improved human control of assistive biomedical robots

Pilarski, Patrick M.; Dawson, Michael R.; Degris, Thomas; Carey, Jason P.; Sutton, Richard S.

doi:10.1109/biorob.2012.6290309

Cited by 41 publications

(30 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GVFs allow the prediction of arbitrary signals, which makes RL more powerful and applicable to more problems. In the field of rehabilitation, TD(λ) has been used to produce GVFs for upper-limb prostheses (Pilarski et al 2012;Pilarski et al 2013a;2013b;Sherstan and Pilarski 2014;Edwards et al 2016). TOTD offers an equivalence to the theoretical forward view of TD learning with negligible increase in computational cost (van Seijen et al 2015) and has been used to predict the shoulder angle of an upper-limb prosthesis (Travnik and Pilarski 2017).…”

Section: Learning Methodsmentioning

confidence: 99%

Pavlovian Control of Intraspinal Microstimulation to Produce Over-Ground Walking

Dalrymple

Roszko

Sutton

et al. 2019

Preprint

View full text Add to dashboard Cite

ABSTRACTObjectiveNeural interface technologies are more commonly used in people with neural injury. To achieve a symbiotic relationship between device and user, the control system of the device must augment remaining function and adapt to day-to-day changes. The goal of this study was to develop predictive control strategies to produce alternating, over-ground walking in a cat model of hemisection spinal cord injury (SCI) using intraspinal microstimulation (ISMS).ApproachEight cats were anaesthetized and placed in a sling over a walkway. The residual function of a hemisection SCI was mimicked by manually moving one hind-limb through the walking cycle over the walkway. ISMS targeted motor networks in the lumbosacral enlargement to activate muscles in the other limb using low levels of current (< 130 µA). Four different people took turns to move the “intact” limb. Two control strategies, which used ground reaction force and angular velocity information about the manually moved limb to control the timing of the transitions of the other limb, were compared. The first strategy, reaction-based control, used thresholds on the sensor values to initiate state transitions. The other strategy used a reinforcement learning strategy, Pavlovian control, to learn predictions about the sensor values. Thresholds on the predictions were used to initiate transitions.Main ResultsBoth control strategies were able to produce alternating, over-ground walking. Reaction-based control required manual tuning of the thresholds for each person to produce walking, whereas Pavlovian control did not. We demonstrate that learning occurs quickly during walking. Predictions of the sensor signals were learned quickly, initiating transitions in no more than 4 steps. Pavlovian control was resilient to transitions between people walking the limb, between cat experiments, and recovered from mistakes during walking.SignificanceThis work demonstrates that Pavlovian control can augment remaining function and allow for personalized walking with minimal tuning requirements.

show abstract

Section: Learning Methodsmentioning

confidence: 99%

Pavlovian Control of Intraspinal Microstimulation to Produce Over-Ground Walking

Dalrymple

Roszko

Sutton

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Users then switch modes to control a different subset [11]–[17], a method known as modal control . Thus the user is able to move the arm everywhere, but not using all of the degrees of freedoms at the same time.…”

Section: Introductionmentioning

confidence: 99%

Assistive teleoperation of robot arms via automatic time-optimal mode switching

Herlant

Holladay

Srinivasa

2016

2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI)

View full text Add to dashboard Cite

Assistive robotic arms are increasingly enabling users with upper extremity disabilities to perform activities of daily living on their own. However, the increased capability and dexterity of the arms also makes them harder to control with simple, low-dimensional interfaces like joysticks and sip-and-puff interfaces. A common technique to control a high-dimensional system like an arm with a low-dimensional input like a joystick is through switching between multiple control modes. However, our interviews with daily users of the Kinova JACO arm identified mode switching as a key problem, both in terms of time and cognitive load. We further confirmed objectively that mode switching consumes about 17.4% of execution time even for able-bodied users controlling the JACO. Our key insight is that using even a simple model of mode switching, like time optimality, and a simple intervention, like automatically switching modes, significantly improves user satisfaction.

show abstract

“…Improvements in simulated tasks of daily life were reported, in particular task completion times were reduced by approximately 14%. 6 In this study, however, the user was only allowed to quickly move between the relatively gross movements of the elbow and wrist and was only able to successfully function with two DOFs selected at any given time.…”

Section: Introductionmentioning

confidence: 99%

“…2,4,5 In this case, it was reported that the time needed to choose the desired action of the powered prosthetic device, and switch between degrees of freedom, comprises a significant portion of the overall duration of the task. 6 And for a multi-DOF prosthetic device, a user is typically tasked with a tedious switching burden to control one-DOF-at-a-time. To improve usability, Pilarski et al 6 showed that automatic DOFswitching could be learned by a control system using an Actor Critic Model with data collected from a SEMG system.…”

Section: Introductionmentioning

confidence: 99%

“…6 And for a multi-DOF prosthetic device, a user is typically tasked with a tedious switching burden to control one-DOF-at-a-time. To improve usability, Pilarski et al 6 showed that automatic DOFswitching could be learned by a control system using an Actor Critic Model with data collected from a SEMG system. This method predicts which DOF a user is likely to control next through a reinforcement learning algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Concurrent surface electromyography and force myography classification during times of prosthetic socket shift and user fatigue

Sanford

Patterson

Popa

2017

Journal of Rehabilitation and Assistive Technologies Engineerin

View full text Add to dashboard Cite

Objective: Surface electromyography has been a long-standing source of signals for control of powered prosthetic devices. By contrast, force myography is a more recent alternative to surface electromyography that has the potential to enhance reliability and avoid operational challenges of surface electromyography during use. In this paper, we report on experiments conducted to assess improvements in classification of surface electromyography signals through the addition of collocated force myography consisting of piezo-resistive sensors. Methods: Force sensors detect intrasocket pressure changes upon muscle activation due to changes in muscle volume during activities of daily living. A heterogeneous sensor configuration with four surface electromyography-force myography pairs was investigated as a control input for a powered upper limb prosthetic. Training of two different multilevel neural perceptron networks was employed during classification and trained on data gathered during experiments simulating socket shift and muscle fatigue. Results: Results indicate that intrasocket pressure data used in conjunction with surface EMG data can improve classification of human intent and control of a powered prosthetic device compared to traditional, surface electromyography only systems. Significance: Additional sensors lead to significantly better signal classification during times of user fatigue, poor socket fit, as well as radial and ulnar wrist deviation. Results from experimentally obtained training data sets are presented.

show abstract

Dynamic switching and real-time machine learning for improved human control of assistive biomedical robots

Cited by 41 publications

References 12 publications

Pavlovian Control of Intraspinal Microstimulation to Produce Over-Ground Walking

Pavlovian Control of Intraspinal Microstimulation to Produce Over-Ground Walking

Assistive teleoperation of robot arms via automatic time-optimal mode switching

Concurrent surface electromyography and force myography classification during times of prosthetic socket shift and user fatigue

Contact Info

Product

Resources

About