Human activity recognition has become an attractive research area with the development of on-body wearable sensing technology. With comfortable electronic-textiles, sensors can be embedded into clothing so that it is possible to record human movement outside the laboratory for long periods. However, a long-standing issue is how to deal with motion artifact introduced by movement of clothing with respect to the body. Surprisingly, recent empirical findings suggest that cloth-attached sensor can actually achieve higher accuracy of activity recognition than rigid-attached sensor, particularly when predicting from short time-windows. In this work, a probabilistic model is introduced in which this improved accuracy and resposiveness is explained by the increased statistical distance between movements recorded via fabric sensing. The predictions of the model are verified in simulated and real human motion capture experiments, where it is evident that this counterintuitive effect is closely captured.

Robotic packaging of fresh leafy produce such as herbs and salads generally involves picking out a target mass from a pile or crate of plant material. Typically, for low-complexity parallel grippers, the weight picked can be controlled by varying the opening aperture. However, often individual strands of plant material get entangled with each other, causing more to be picked out than desired. This paper presents a simple spread-and-pick approach that significantly reduces the degree of entanglement in a herb pile when picking. Compared to the traditional approach of picking from an entanglement-free point in the pile, the proposed approach results in a decrease of up to 29.06% of the variance in for separate homogeneous piles of fresh herbs. Moreover, it shows good generalisation with up to 55.53% decrease in picked weight variance for herbs previously unseen by the system.

Energy efficiency is a crucial issue towards long-term deployment of compliant robots in the real world. In the context of variable impedance actuators (VIAs), one of the main focuses has been on improving energy efficiency through reduction of energy consumption. However, the harvesting of dissipated energy in such systems remains under-explored. This study proposes a variable damping module design enabling energy regeneration in VIAs by exploiting the regenerative braking effect of dc motors. The proposed damping module uses four switches to combine regenerative and dynamic braking, in a hybrid approach that enables energy regeneration without a reduction in the range of damping achievable. A physical implementation on a simple VIA mechanism is presented in which the regenerative properties of the proposed module are characterized and compared against theoretical predictions. To investigate the role of variable regenerative damping in terms of energy efficiency of long-term operation, experiments are reported in which the VIA, equipped with the proposed damping module, performs sequential reaching to a series of stochastic targets. The results indicate that the combination of variable stiffness and variable regenerative damping results in a 25% performance improvement on metrics incorporating reaching accuracy, settling time, energy consumption and regeneration over comparable schemes, where either stiffness or damping are fixed.

With the increase in complexity of robotic systems and the rise in non-expert users, it can be assumed that task constraints are not explicitly known. In tasks where avoiding singularity is critical to success, this paper provides an approach, especially for non-expert users, for the system to learn the constraints contained in a set of demonstrations, such that they can be used to optimise an autonomous controller to avoid singularity, without having to explicitly know them. The proposed approach avoids singularity, and thereby unpredictable behaviour when carrying out a task, by maximising the learnt manipulability throughout the motion of the constrained system, and is not limited to kinematic systems. Its benefits are demonstrated through comparisons with other control policies which show that the constrained manipulability of a system learnt through demonstration can be used to avoid singularities in cases where these other policies would fail. In the absence of the system's manipulability subject to a task's constraints, the proposed approach can be used instead to infer these with results showing errors less than 10-5in 3DOF simulated systems and less than 10-2using a 7DOF real world robotic system.

Learning from Demonstration depends on a robot learner generalising its learned model to unseen conditions. Generally, it is not feasible for a person to provide demonstrations that account for all possible variations in non-trivial tasks. While there are many learning methods that can handle interpolation of observed data effectively, extrapolation from observed data offers a much greater challenge. To address this problem, this paper proposes a modified Task-Parameterised Gaussian Mixture Regression method that considers the relevance of task parameters during trajectory generation, as determined by variance in the data. The benefits of the proposed method are first explored using a simulated reaching task data set. Here it is shown that the proposed method offers far-reaching, low-error extrapolation abilities that are different in nature to existing learning methods. Data collected from novice users for a real-world manipulation task is then considered, where it is shown that the proposed method is able to effectively reduce grasping performance errors by $\sim $40% and extrapolate to unseen grasp targets under real-world conditions. These results indicate the proposed method can benefit novice users by placing less reliance on the user to provide high quality demonstration data sets.

The low-cost manufacturing and maintenance of prostheses is of vital importance to their successful deployment in developing countries. Low-cost prosthesis actuation is generally achieved by combining pre-programmed control strategies, with surface-electromyographic measurements taken from the residual limb. In a standard setting, these signals are measured with disposable gel electrodes. However, this limit on electrode reuse requires that prosthesis users have a stable supply of electrodes. Alternatively, the textile electrodes sewn from conductive thread are studied in the context of hand gesture recognition to consider their future use with low-cost prostheses. In this paper, it is demonstrated that textile electrodes can be applied for gesture recognition. To do so, surface electromyography (sEMG) experiments are run in South Africa on three amputees where they were asked to perform gestures with their phantom limb (i.e., the missing limb segment). A gesture recognition method is implemented, and the classification accuracy with data recorded from textile electrodes is compared to that from gel electrodes. Further analysis examining the relationship between classifier performance and physiological parameters are performed. Results show that textile electrodes can be used to perform accurate gesture recognition, and are comparable to disposable gel electrodes. This demonstrates that low-cost sensory systems are not barrier to myoelectric control in developing countries.

Using Programming by Demonstration to teach robot learners generalisable skills relies on having effective human teachers. This paper aims to address two problems commonly observed in demonstration data sets that arise due to poor teaching strategies; undemonstrated states and ambiguous demonstrations. Overcoming these issues through the use of visual feedback and simple heuristic rules is investigated as a potential way of guiding novice users to more effectively teach robot learners to generalise a task. The proposed method intends to offer the user a more transparent understanding of the robot learner's model state during the teaching phase, to create a more interactive and robust teaching process. Results from a single-factor, three-phase repeated measures study with n=30 participants, comparing the proposed feedback and heuristic rules set against an unguided condition, show a statistically significant (F(2,58)=7.952,p=0.001) improvement of user teaching efficiency of approximately 180% when using the proposed feedback visualisation.

Increasing research efforts have been made to improve the energy efficiency of variable impedance actuators (VIAs) through reduction of energy consumption. However, the harvesting of dissipated energy in such systems remains under-explored. This study proposes a novel variable damping module design enabling energy regeneration in VIAs by exploiting the regenerative braking effect of DC motors. The proposed damping module uses four switches to combine regenerative and dynamic braking, in a hybrid approach that enables energy regeneration without reduction in the range of damping achievable. Numerical simulations and a physical experiment are presented in which the proposed module shows an optimal trade-off between task-performance and energy efficiency.

This paper presents a programming by demonstration framework for teaching impedance modulation using human demonstrations. Physiologically, human stiffness and damping are coupled at the muscle level, restricting the ability to modulate impedance according to task demands. Robotic systems often do not have this restriction (stiffness and damping can be varied independently), but the challenge is to devise an appropriate variable impedance profile for a given task. In this paper, the task critical component is first learned for imitation and a robot-specific controller is then blended into the control using the null space. In doing so, the control cheme takes advantage of both human and robot `best practice'. Experimental results on a physical robot suggest an order of magnitude better mean performance, with lower variance, can be achieved using the blended scheme.

Many human skills can be described in terms of performing a set of prioritised tasks. While a number of tools have become available that recover the underlying control policy from constrained movements, few have explicitly considered learning how constraints should be imposed in order to perform the control policy. In this paper, a method for learning the self-imposed constraints present in movement observations is proposed. The problem is formulated into the operational space control framework, where the goal is to estimate the constraint matrix and its null space projection that decompose the task space and any redundant degrees of freedom. The proposed method requires no prior knowledge about either the dimensionality of the constraints nor the underlying control policies. The techniques are evaluated on a simulated three degree-of-freedom arm and on the AR10 humanoid hand.

Muscle activity monitoring or Electromyography (EMG) is useful in gait analysis, injury prevention, computer or robot interfaces and assisting patients with communication difficulties. However, EMG is typically invasive or obtrusive, expensive and difficult to use for untrained users. A possible solution is textile-based surface EMG (sEMG) integrated into clothing and used as a wearable device. This is, however, challenging due to (i) uncertainties in the electrical properties of conductive threads used to construct electrodes, (ii) imprecise fabrication technologies (e.g., embroidery, sewing), and (iii) a lack of standardisation in the choice of design variables. This paper, for the first time, provides a design guide for such sensors by performing a thorough examination of the effect of design variables on sEMG quality. Electrical characterisation and sEMG measurements are performed, considering the effects of manufacturing imprecision. Results show that the imprecisions in digital embroidery lead to a trade-off between low electrode resistance and high consistency. An optimum set of variables for this trade-off is identified and tested with sEMG during a variable force isometric grip exercise with n=6 participants and compared with traditional gel-based electrodes. Results show that thread-based electrodes provide a similar level of sensitivity to force variation as gel-based electrodes with about 90% correlation with expected linear behaviour.

Many everyday human skills can be considered in terms of performing some task subject to a set of self-imposed or environmental constraints. In recent years, a number of new tools have become available in the learning and robotics community that allow data from constrained and/or redundant systems to be used to uncover underlying consistent behaviours that may be otherwise masked by the constraints. However, while a wide variety of work for generalisation of movements have been proposed, few have explicitly considered learning the constraints of the motion and ways to cope with unknown environment. In this paper, we propose a method to learn the constraints such that some previously learnt behaviours can be adapted to new environment in an appropriate way. In particular, we consider learning the null space projection matrix of a kinematically constrained system, and see how previously learnt policies can be adapted to novel constraints.

Internal impedance is one of the key factors determining the quality of embodied perception and action in biological organisms and robots. Though the role of impedance control in robotic actuation has been well studied, its significance in the accuracy of proprioception with embodied sensors is not well known yet. Therefore, it is important to characterize the relationship between the entropy of sensor information and the impedance of their physical embodiment, through which sensors feel the internal state of the body and the environment. In this paper, we address the role of internal impedance in the accuracy of embodied perception. To investigate this, we pose the problem of using only torque data measured at the stationary base of a two link planar manipulator, to estimate the deflection caused by an external torque in the McKibben type pivot joint with variable stiffness. Based on analytical modelling and experimental validation, this paper presents, for the first time, that non-linear static memory primitives relating internal impedance, internal kinematic variables, and forces felt at the base of the manipulator - similar to the functionality of tendon organs of biological counterparts - can be used to tune optimal internal impedance parameters to maximize the accuracy of internal state estimation during external perturbations.

This paper introduces Locally Weighted Least Squares Policy Iteration for learning approximate optimal control in settings where models of the dynamics and cost function are either unavailable or hard to obtain. Building on recent advances in Least Squares Temporal Difference Learning, the proposed approach is able to learn from data collected from interactions with a system, in order to build a global control policy based on localised models of the state-action value function. Evaluations are reported characterising learning performance for non-linear control problems including an under-powered pendulum swing-up task, and a robotic door-opening problem under different dynamical conditions.

This paper presents a comparative study of approaches to control robots with variable impedance actuators (VIAs) in ways that imitate the behavior of humans. We focus on problems where impedance modulation strategies are recorded from human demonstrators for transfer to robotic systems with differing levels of heterogeneity, both in terms of the dynamics and actuation. We categorize three classes of approach that may be applied to this problem, namely, 1) direct, 2) feature-based, and 3) inverse optimal approaches to transfer. While the first is restricted to highly biomorphic plants, the latter two are shown to be sufficiently general to be applied to various VIAs in a way that is independent of the mechanical design. As instantiations of such transfer schemes, 1) a constraint-based method and 2) an apprenticeship learning framework are proposed, and their suitability to different problems in robotic imitation, in terms of efficiency, ease of use, and task performance, is characterized. The approaches are compared in simulation on systems of varying complexity, and robotic experiments are reported for transfer of behavior from human electromyographic data to two different variable passive compliance robotic devices.

Considerable research effort has gone into the design of variable passive stiffness actuators (VSAs). A number of different mechanical designs have been proposed, aimed at either a biomorphic (i.e., antagonistic) design, compactness, or simplified modelling and control. In this paper, we propose a (model-based) unified control methodology that is able to exploit the benefits of variable stiffness independent of the specifics of the mechanical design. Our approach is based on forming constraints on commands sent to the VSA to ensure that the equilibrium position and stiffness of the VSA are tracked to the desired values. We outline how our approach can be used for tracking stiffness and equilibrium position both in joint and task space, and how it may be used in the context of constrained local optimal control. In our experiments we illustrate the utility of our approach in the context of online teleoperation, to transfer compliant human behaviour to a variable stiffness device.

Reinforcement learning in the high-dimensional, continuous spaces typical in robotics, remains a challenging problem. To overcome this challenge, a popular approach has been to use demonstrations to find an appropriate initialisation of the policy in an attempt to reduce the number of iterations needed to find a solution. Here, we present an alternative way to incorporate prior knowledge from demonstrations of individual postures into learning, by extracting the inherent problem structure to find an efficient state representation. In particular, we use probabilistic, nonlinear dimensionality reduction to capture latent constraints present in the data. By learning policies in the learnt latent space, we are able to solve the planning problem in a reduced space that automatically satisfies task constraints. As shown in our experiments, this reduces the exploration needed and greatly accelerates the learning. We demonstrate our approach for learning a bimanual reaching task on the 19-DOF KHR-1HV humanoid.

Many everyday tasks performed by people, such as reaching, pointing or drawing, resolve redundant degrees of freedom in the arm in a similar way. In this paper we present a novel method for learning the strategy used to resolve redundancy by exploiting the variability in multiple observations of different tasks. We demonstrate the effectiveness of this method on three simulated plants: a toy example, a three link planar arm, and the KUKA lightweight arm.

Many everyday human skills can be framed in terms of performing some task subject to constraints imposed by the environment. Constraints are usually unobservable and frequently change between contexts. In this paper, we present a novel approach for learning (unconstrained) control policies from movement data, where observations come from movements under different constraints. As a key ingredient, we introduce a small but highly effective modification to the standard risk functional, allowing us to make a meaningful comparison between the estimated policy and constrained observations. We demonstrate our approach on systems of varying complexity, including kinematic data from the ASIMO humanoid robot with 27 degrees of freedom.

Many everyday human skills can be framed in terms of performing some task subject to constraints imposed by the environment. Constraints are usually unobservable and frequently change between contexts. In this paper, we present a novel approach for learning (unconstrained) control policies from movement data, where observations are recorded under different constraint settings. Our approach seamlessly integrates unconstrained and constrained observations by performing hybrid optimisation of two risk functionals. The first is a novel risk functional that makes a meaningful comparison between the estimated policy and constrained observations. The second is the standard risk, used to reduce the expected error under impoverished sets of constraints. We demonstrate our approach on systems of varying complexity, and illustrate its utility for transfer learning of a car washing task from human motion capture data.