A performance evaluation of commercially available and 3D-printable prosthetic hands: a comparison using the anthropomorphic hand assessment protocol.

Despite significant technological progress in prosthetic hands, a device with functionality akin to a biological extremity is far from realization. To better support the development of next-generation technologies, we investigated the grasping capabilities of clinically prescribable and commercially available (CPCA) prosthetic hands against those that are 3D-printed, which offer cost-effective and customizable solutions. Our investigation utilized the Anthropomorphic Hand Assessment Protocol (AHAP) as a benchtop evaluation of the multi-grasp performance of 3D-printed devices against CPCA prosthetic hands.

A multifaceted suite of metrics for comparative myoelectric prosthesis controller research.

Upper limb robotic (myoelectric) prostheses are technologically advanced, but challenging to use. In response, substantial research is being done to develop person-specific prosthesis controllers that can predict a user's intended movements. Most studies that test and compare new controllers rely on simple assessment measures such as task scores (e.

A Case Series in Position-Aware Myoelectric Prosthesis Control Using Recurrent Convolutional Neural Network Classification with Transfer Learning.

Position-aware myoelectric prosthesis controllers require long, data-intensive training routines. Transfer Learning (TL) might reduce training burden. A TL model can be pre-trained using forearm muscle signal data from many individuals to become the starting point for a new user.

Communicative capital: a key resource for human-machine shared agency and collaborative capacity.

In this work, we present a perspective on the role machine intelligence can play in supporting human abilities. In particular, we consider research in rehabilitation technologies such as prosthetic devices, as this domain requires tight coupling between human and machine. Taking an agent-based view of such devices, we propose that human-machine collaborations have a capacity to perform tasks which is a result of the combined agency of the human and the machine.

What's a good prediction? Challenges in evaluating an agent's knowledge.

Constructing general knowledge by learning task-independent models of the world can help agents solve challenging problems. However, both constructing and evaluating such models remain an open challenge. The most common approaches to evaluating models is to assess their accuracy with respect to observable values.

Composite Recurrent Convolutional Neural Networks Offer a Position-Aware Prosthesis Control Alternative While Balancing Predictive Accuracy with Training Burden.

To mitigate the "limb position effect" that hinders myoelectric upper limb prosthesis control, pattern recognition-based models must accurately predict user-intended movements across a multitude of limb positions. Such models can use electromyography (EMG) and inertial measurement units to capture necessary multi-position data. However, this data capture solution requires lengthy user-performed model training routines, with movements in many limb positions, plus retraining thereafter due to inherent signal variations over time.

Machine-learned Adaptive Switching in Voluntary Lower-limb Exoskeleton Control: Preliminary Results.

Lower-limb exoskeletons utilize fixed control strategies and are not adaptable to user's intention. To this end, the goal of this study was to investigate the potential of using temporal-difference learning and general value functions for predicting the next possible walking mode that will be selected by users wearing exoskeletons in order to reduce the effort and cognitive load while switching between different modes of walking. Experiments were performed with a user wearing the Indego exoskeleton and given the authority to switch between five walking modes that were different in terms of speed and turn direction.

Generating accurate 3D gaze vectors using synchronized eye tracking and motion capture.

Assessing gaze behavior during real-world tasks is difficult; dynamic bodies moving through dynamic worlds make gaze analysis difficult. Current approaches involve laborious coding of pupil positions. In settings where motion capture and mobile eye tracking are used concurrently in naturalistic tasks, it is critical that data collection be simple, efficient, and systematic.

Prediction, Knowledge, and Explainability: Examining the Use of General Value Functions in Machine Knowledge.

Within computational reinforcement learning, a growing body of work seeks to express an agent's knowledge of its world through large collections of predictions. While systems that encode predictions as General Value Functions (GVFs) have seen numerous developments in both theory and application, whether such approaches are explainable is unexplored. In this perspective piece, we explore GVFs as a form of explainable AI.

Comparison of a Miniaturized Cassette PCR System with a Commercially Available Platform for Detecting in Beef Carcass Swabs.

Detection sensitivity of cassette PCR was compared with a commercial BAX PCR system for detection of and genes in from 806 beef carcass swabs. Cassette PCR detects multiple genetic markers on multiple samples using PCR and melt curve analysis. Conventional PCR served as a gold standard.

Myoelectric prosthesis users and non-disabled individuals wearing a simulated prosthesis exhibit similar compensatory movement strategies.

Background: Research studies on upper limb prosthesis function often rely on the use of simulated myoelectric prostheses (attached to and operated by individuals with intact limbs), primarily to increase participant sample size. However, it is not known if these devices elicit the same movement strategies as myoelectric prostheses (operated by individuals with amputation). The objective of this study was to address the question of whether non-disabled individuals using simulated prostheses employ the same compensatory movements (measured by hand and upper body kinematics) as individuals who use actual myoelectric prostheses.

Embodied Cooperation to Promote Forgiving Interactions With Autonomous Machines.

During every waking moment, we must engage with our environments, the people around us, the tools we use, and even our own bodies to perform actions and achieve our intentions. There is a spectrum of control that we have over our surroundings that spans the extremes from full to negligible. When the outcomes of our actions do not align with our goals, we have a tremendous capacity to displace blame and frustration on external factors while forgiving ourselves.

Examining the Use of Temporal-Difference Incremental Delta-Bar-Delta for Real-World Predictive Knowledge Architectures.

Predictions and predictive knowledge have seen recent success in improving not only robot control but also other applications ranging from industrial process control to rehabilitation. A property that makes these predictive approaches well-suited for robotics is that they can be learned online and incrementally through interaction with the environment. However, a remaining challenge for many prediction-learning approaches is an appropriate choice of prediction-learning parameters, especially parameters that control the magnitude of a learning machine's updates to its predictions (the or ).

Interpretable PID parameter tuning for control engineering using general dynamic neural networks: An extensive comparison.

Modern automation systems largely rely on closed loop control, wherein a controller interacts with a controlled process via actions, based on observations. These systems are increasingly complex, yet most deployed controllers are linear Proportional-Integral-Derivative (PID) controllers. PID controllers perform well on linear and near-linear systems but their simplicity is at odds with the robustness required to reliably control complex processes.

Gaze and Movement Assessment (GaMA): Inter-site validation of a visuomotor upper limb functional protocol.

Background: Successful hand-object interactions require precise hand-eye coordination with continual movement adjustments. Quantitative measurement of this visuomotor behaviour could provide valuable insight into upper limb impairments. The Gaze and Movement Assessment (GaMA) was developed to provide protocols for simultaneous motion capture and eye tracking during the administration of two functional tasks, along with data analysis methods to generate standard measures of visuomotor behaviour.

Compensatory strategies of body-powered prosthesis users reveal primary reliance on trunk motion and relation to skill level.

Background: While body-powered prostheses are commonly used, the compensatory strategies required to operate body-powered devices are not well understood. Kinematic assessment in addition to standard clinical tests can give a comprehensive evaluation of prosthesis user function and skill. This study investigated the movement compensations of body-powered prosthesis users and determined whether a correlation is present between compensatory strategies and skill level, as measured by a standard clinical test.

Quantitative Eye Gaze and Movement Differences in Visuomotor Adaptations to Varying Task Demands Among Upper-Extremity Prosthesis Users.

Importance: New treatments for upper-limb amputation aim to improve movement quality and reduce visual attention to the prosthesis. However, evaluation is limited by a lack of understanding of the essential features of human-prosthesis behavior and by an absence of consistent task protocols.

Objective: To evaluate whether task selection is a factor in visuomotor adaptations by prosthesis users to accomplish 2 tasks easily performed by individuals with normal arm function.

Exploring the Impact of Machine-Learned Predictions on Feedback from an Artificial Limb.

Learning to get by without an arm or hand can be very challenging, and existing prostheses do not yet fill the needs of individuals with amputations. One promising solution is to improve the feedback from the device to the user. Towards this end, we present a simple machine learning interface to supplement the control of a robotic limb with feedback to the user about what the limb will be experiencing in the near future.

The Effect of an Automatically Levelling Wrist Control System.

Upper limb loss is a devastating injury for which current prosthetic replacement inadequately compensates. A lack of wrist movement in prostheses due to mechanical design and control system considerations compels prosthetic users to employ compensatory movements using their upper back and shoulder that can eventually result in strain and overuse injuries. One possible means of easing this control burden is to allow a prosthetic wrist to self-regulate, keeping the terminal device of the prosthesis level relative to the ground when appropriate, such as when raising a cup of liquid.

Supporting Play by Applying Haptic Guidance Along a Surface Learnt from Single Motion Trajectories.

Haptic-enabled teleoperated robots can help children with physical disabilities to reach toys by applying haptic guidance towards their toys, thus compensating for their limitations in reaching and manipulating objects. In this article we preliminarily tested a learning from demonstration (LfD) approach, where a robotic system learnt the surface that best approximated to all motion trajectories demonstrated by the participants while playing a whack-a-mole game. The end-goal of the system is for therapists or parents to demonstrate to it how to play a game, and then be used by children with physical disabilities.

Hand Function Kinematics when using a Simulated Myoelectric Prosthesis.

Studies that investigate myoelectric prosthesis control commonly use non-disabled participants fitted with a simulated prosthetic device. This approach improves participant recruitment numbers but assumes that simulated movements represent those of actual prosthesis users. If this assumption is valid, then movement performance differences between simulated prosthesis users and normative populations should be similar to differences between actual prosthesis users and normative populations.

Detection of pathogenic Escherichia coli on potentially contaminated beef carcasses using cassette PCR and conventional PCR.

Background: Over a one year period, swabs of 820 beef carcasses were tested for the presence of Shiga toxin-producing Escherichia coli by performing Polymerase Chain Reaction (PCR) in a novel technology termed "cassette PCR", in comparison to conventional liquid PCR. Cassette PCR is inexpensive and ready-to-use. The operator need only add the sample and press "go".

Characterization of normative angular joint kinematics during two functional upper limb tasks.

Background: Optical motion capture is a powerful tool for assessing upper body kinematics, including compensatory movements, in different populations. However, the lack of a standardized protocol with clear functional relevance hinders its clinical acceptance.

Research Question: The objective of this study was to use motion capture to: (1) characterize angular joint kinematics in a normative population performing two complex, yet standardized upper limb tasks with clear functional relevance; and (2) assess the protocol's intra-rater reliability.

Using synchronized eye and motion tracking to determine high-precision eye-movement patterns during object-interaction tasks.

This study explores the role that vision plays in sequential object interactions. We used a head-mounted eye tracker and upper-limb motion capture to quantify visual behavior while participants performed two standardized functional tasks. By simultaneously recording eye and motion tracking, we precisely segmented participants' visual data using the movement data, yielding a consistent and highly functionally resolved data set of real-world object-interaction tasks.

Reactive Reinforcement Learning in Asynchronous Environments.

The relationship between a reinforcement learning (RL) agent and an asynchronous environment is often ignored. Frequently used models of the interaction between an agent and its environment, such as Markov Decision Processes (MDP) or Semi-Markov Decision Processes (SMDP), do not capture the fact that, in an asynchronous environment, the state of the environment may change during computation performed by the agent. In an asynchronous environment, minimizing reaction time-the time it takes for an agent to react to an observation-also minimizes the time in which the state of the environment may change following observation.