Human activity recognition is progressing from automatically determining what a person is doing and when, to additionally analyzing the quality of these activities—typically referred to as skill assessment. In this chapter, we propose a new framework for skill assessment that generalizes across application domains and can be deployed for near-real-time applications. It is based on the notion of repeatability of activities defining skill. The analysis is based on two subsequent classification steps that analyze (1) movements or activities and (2) their qualities, that is, the actual skills of a human performing them. The first classifier is trained in either a supervised or unsupervised manner and provides confidence scores, which are then used for assessing skills. We evaluate the proposed method in two scenarios: gymnastics and surgical skill training of medical students. We demonstrate both the overall effectiveness and efficiency of the generalized assessment method, especially compared to previous work.

Actuators for haptic devices tend to have a different set of requirements in comparison to many other engineering applications. Small permanent magnet DC electric motors are commonly used as actuators in haptic devices and, in operation, tend to spend a significant period of time in a `stalled' condition where they are attempting to oppose an applied force. Ideally a haptic actuator together with its power amplifier exchange energy reversibly with the mechanical loads. However this is not feasible at room temperature and to achieve good force performance results in energy loss as heat in the motor windings. This paper identifies the relationship between heat loss and force generation in haptic electromagnetic actuators. The work then presents results on current over-stressing of small DC motors so as to understand the risks of demagnetisation against thermal damage to the armature. Results indicate that it should be possible to apply short current over-stresses to commercial DC permanent magnet motors to increase end point force. Also by paying careful attention to heat dissipation in the design of small permanent magnet actuators motors, it should be possible to improve the overall performance of actuators for haptic applications.

Using haptic interfaces to assist the training of skills in the curriculum of undergraduate dentists provides a unique opportunity to advance rendering algorithms and engineering of haptic devices. In this paper we use the dental context to explore a rendering technique called smoothed particle hydrodynamics (SPH) as a potential method to train the insertion of filling material into a previously prepared (virtual) dental cavity. The paper also considers how problems of haptic rendering might be implemented on a Graphical Processing Unit (GPU) that operates in the haptics control loop. The filling simulation used 3000 particles to represent the cavity boundary and filling material, running at an average of 447Hz. Novel smoothing function in SPH was developed and its flexibility is presented.

Chronic conditions, such as diabetes and obesity are related to quality of diet. However, current research findings are conflicting with regards to the impact of snacking on diet quality. One reason for this is the lack of a clear definition of a snack or a meal. This paper presents a novel approach to understanding how foods are grouped together in eating events using a machine learning algorithm, topic models. Approaches for applying topic models to a nutrition application are discussed. A topic model is implemented for the UK National Diet and Nutrition Survey Rolling Programme dataset. The results demonstrate that the topics found are representative of typical eating events in terms of food group content and associated time of day. There is a strong potential for topic models to reveal useful patterns in food diary data that have not previously been considered.

This paper discusses the design of a Redundant Drive Joint with Double Actuation (RDJ-DA) to produce controlled compliant motions over a higher bandwidth. First, our strategies on mechanical and controller designs to produce compliant motions are described, and the basic structure and impedance control of the RDJ-DA with internal serial structure explained. The standard form of the basic structure is introduced using a set of parameters which can be used to express the inertia property of RDJ-DA. Second, a problem statement for the design of RDJ-DAs is described after pointing out that required torques of the second actuator of the RDJ-DA could be large. Then, a basic idea of introducing springs into the second actuator in parallel is proposed as a part of the structural design of RDJ-DA to reduce the large torques. Simulations are conducted to find out a set of the design parameters of RDJ-DA which obtains a higher natural frequency of the output joint admittance satisfying both the desired output joint admittance and the limitations of two identical motors on their performance. Finally, a prototype design of RDJ-DA using the obtained set of the design parameters is presented.

This paper proposes impedance control of redundant drive joints with double actuation (RDJ-DA) to produce compliant motions with the future goal of higher bandwidth. First, to reduce joint inertia, a double-input-single-output mechanism with one internal degree of freedom (DOF) is presented as part of the basic structure of the RDJ-DA. Next, the basic structure of RDJ-DA is further explained and its dynamics and statics are derived. Then, the impedance control scheme of RDJ-DA to produce compliant motions is proposed and the validity of the proposed controller is investigated using numerical examples.

In this paper, we will demonstrate how force feedback, motion-parallax, and stereoscopic vision can enhance the opportunities for learning in the context of dentistry. A dental training workstation prototype has been developed intended for use by dental students in their introductory course to preparing a tooth cavity. The multimodal feedback from haptics, motion tracking cameras, computer generated sound and graphics are being exploited to provide 'near-realistic' learning experiences. Whilst the empirical evidence provided is preliminary, we describe the potential of multimodal interaction via these technologies for enhancing dental-clinical skills.

Robot-mediated neurorehabilitation is a rapidly advancing field that seeks to use advances in robotics, virtual realities, and haptic interfaces, coupled with theories in neuroscience and rehabilitation to define new methods for treating neurological injuries such as stroke, spinal cord injury, and traumatic brain injury. The field is nascent and much work is needed to identify efficient hardware, software, and control system designs alongside the most effective methods for delivering treatment in home and hospital settings. This paper identifies the need for robots in neurorehabilitation and identifies important goals that will allow this field to advance

Many localization techniques today rely on absolute landmark measurements to efficiently track the robot's position in space. Although absolute landmarks are essential for correctly estimating its position, they might be rare in an unknown environment. This means that the robot would have to traverse long distances without any outside reference point resulting in system degradation. In case of a robot team though, each robot can rely on both absolute or relative position measurements between robots. This paper describes an approach for a multi-robot localization system, based on a single centralized extended Kalman filter (CEKF) to track the position and orientation changes of a group of robots. Moreover, it is shown that if the robots in the group collect only relative measurements the system suffers from observability problem. It is proven that an increasing number of mobile robots capable of relative measurements only, reduces the observability problem and compensates for the need of external absolute landmarks thus providing efficient localization.

Smooth trajectories are essential for safe interaction in between human and a haptic interface. Different methods and strategies have been introduced to create such smooth trajectories. This paper studies the creation of human-like movements in haptic interfaces, based on the study of human arm motion. These motions are intended to retrain the upper limb movements of patients that lose manipulation functions following stroke. We present a model that uses higher degree polynomials to define a trajectory and control the robot arm to achieve minimum jerk movements. It also studies different methods that can be driven from polynomials to create more realistic human-like movements for therapeutic purposes.

The main objective is to generate kinematic models for the head and neck movements. The motivation comes from our study of individuals with quadriplegia and the need to design rehabilitation aiding devices such as robots and teletheses that can be controlled by head-neck movements. It is then necessary to develop mathematical models for the head and neck movements. Two identification methods have been applied to study the kinematics of head-neck movements of able-body as well as neck-injured subjects. In particular, sagittal plane movements are well modeled by a planar two-revolute-joint linkage. In fact, the motion in joint space seems to indicate that sagittal plane movements may be classified as a single DOF motion. Finally, a spatial three-revolute-joint system has been employed to model 3D head-neck movements.

Rehabilitation robot manipulators for persons with disabilities often encounter contact tasks in uncertain environments. In order for rehabilitation robots to readily adapt to their changing environment, an advanced and practically implementable control approach is needed. This paper present a robot manipulator control scheme which combines a discrete-time adaptive controller with a discrete-time impedance dynamics trajectory generator. The discrete-time adaptive controller assures the trajectory tracking of robot manipulators while the discrete-time impedance dynamics trajectory generator regulates the relation between forces and motions. By using the adaptive controller the knowledge of either the structure or the parameter values of the robot dynamics is not required. The proposed discrete-time adaptive impedance control scheme is simple and suitable for the digital computer based real-time robot manipulator control. Simulations are given for a planar two-link manipulator arm under discrete adaptive impedance control with forces contaminated by Gaussian distributed noise. Results are presented to demonstrate the proposed scheme.>

Elderly people would like to maintain independence for as long as possible in a familiar environment. Limitations within that environment often necessitate a move into residential care facilities where care attendants are available for assistance. This research investigates one potential area where a robot based technology may provide a solution that is usable by an elderly clientele. The application area is that of assisting a person to achieve independent transfer between a seated and a standing position such as might be encountered in moving between a chair, wheelchair, bed, toilet, or shower seat. An important goal of this work is to demonstrate that advanced technology can be simple and effective. To be successful the technology must be easy to use, meet the needs of elderly people and become an accepted component of daily life.>