Visual feedback control of a robot in an unknown environment (learning control using neural networks)

In this paper, a visual feedback control approach based on neural networks is presented for a robot with a camera installed on its end-effector to trace an object in an unknown environment. First, the one-to-one mapping relations between the image feature domain of the object to the joint angle domain of the robot are derived. Second, a method is proposed to generate a desired trajectory of the robot by measuring the image feature parameters of the object. Third, a multilayer neural network is used for off-line learning of the mapping relations so as to produce on-line the reference inputs for the robot. Fourth, a learning controller based on a multilayer neural network is designed for realizing the visual feedback control of the robot. Last, the effectiveness of the present approach is verified by tracing a curved line using a 6-degrees-of-freedom robot with a CCD camera installed on its end-effector. The present approach does not necessitate the tedious calibration of the CCD camera and the complicated coordinate transformations.

Short-interval intracortical inhibition is not affected by varying visual feedback in an isometric task in biceps brachiii muscle

Purpose : To establish if visual feedback and force requirements influence SICI.

Methods : SICI was assessed from 10 healthy adults (5 males and 5 females aged between 21 and 35 years) in three submaximal isometric elbow flexion torque levels [5, 20, and 40% of maximal voluntary contraction (MVC)] and with two tasks differing in terms of visual feedback. Single-pulse and paired-pulse motor-evoked potentials (MEPs), supramaximal M-wave, and background surface electromyogram (sEMG) were recorded from the biceps brachii muscle.

Results : Repeated measures MANOVA was used for statistical analyses. Background sEMG did not differ between tasks (F = 0.4, P = 0.68) nor was task × torque level interaction observed (F = 1.2, P = 0.32), whereas background sEMG increased with increasing torque levels (P = 0.001). SICI did not differ between tasks (F = 0.9, P = 0.43) and no task × torque level interaction was observed (F = 2.3, P = 0.08). However, less SICI was observed at 40% MVC compared to the 5 and 20% MVC torque levels (P = 0.01–0.001).

Conclusion : SICI was not altered by performing the same task with differing visual feedback. However, SICI decreased with increasing submaximal torque providing further evidence that SICI is one mechanism of modulating cortical excitability and plays a role in force gradation.

An empirical examination of feedback : user control and performance in a hapto-audio-visual training environment

Utilising advanced technologies, such as virtual environments (VEs), is of importance to training and education. The need to develop and effectively apply interactive, immersive 3D VEs continues to grow. As with any emerging technology, user acceptance of new software and hardware devices is often difficult to measure and guidelines to introduce and ensure adequate and correct usage of such technologies are lacking. It is therefore imperative to obtain a solid understanding of the important elements that play a role in effective learning through VEs. In particular, 3D VEs may present unusual and varied interaction and adoption considerations. The major contribution of this study is to investigate a complex set of interrelated factors in the relatively new sphere of VEs for training and education. Although many of the factors appears to be important from past research, researcher have not explicitly studied a comprehensive set of inter-dependant, empirically validated factors in order to understand how VEs aid complex procedural knowledge and motor skill learning. By integrating theory from research on training, human computer interaction (HCI), ergonomics and cognitive psychology, this research proposes and validates a model that contributes to application-specific VE efficacy formation. The findings of this study show visual feedback has a significant effect on performance. For tactile/force feedback and auditory feedback, no significant effect were found. For satisfaction, user control is salient for performance. Other factors such as interactivity and system comfort, as well as level of task difficulty, also showed effects on performance.

Feedback of personal retinal images appears to have a motivational impact in people with non-proliferative diabetic retinopathy and suboptimal HbA1c: findings of a pilot study

AIM:
To conduct a pilot study to explore the potential impact of visual feedback of personal retinal images on diabetes outcomes.

METHODS:
Twenty-five participants with non-proliferative diabetic retinopathy and suboptimal HbA1c (> 53 mmol/mol; > 7%) were randomized to receive visual feedback of their own retinal images or to a control group. At baseline and 3-month follow-up, HbA1c, standard measures of beliefs, diabetes-related distress and self-care activities were assessed.

RESULTS:
In unadjusted models, relative to controls, the intervention group showed significantly greater improvement in HbA1c at 3-month follow-up (–0.6% vs. +0.3%, P < 0.01), as well as enhanced motivation to improve blood glucose management (P < 0.05).

CONCLUSIONS:
This small pilot study provides preliminary evidence that visual feedback of personal retinal images may offer a practical educational strategy for clinicians in eye care services to improve diabetes outcomes in non-target compliant patients. A fully powered randomized controlled trial is required to confirm these findings and determine the optimal use of feedback to produce sustained effects.

Piloting the feasibility of head-mounted video technology to augment student feedback during simulated clinical decision-making: an observational design pilot study

BACKGROUND: Clinical decision-making is a complex activity that is critical to patient safety. Simulation, augmented by feedback, affords learners the opportunity to learn critical clinical decision-making skills. More detailed feedback following simulation exercises has the potential to further enhance student learning, particularly in relation to developing improved clinical decision-making skills. OBJECTIVE: To investigate the feasibility of head-mounted video camera recordings, to augment feedback, following acute patient deterioration simulations. DESIGN: Pilot study using an observational design. METHODS: Ten final-year nursing students participated in three simulation exercises, each focussed on detection and management of patient deterioration. Two observers collected behavioural data using an adapted version of Gaba's Clinical Simulation Tool, to provide verbal feedback to each participant, following each simulation exercise. Participants wore a head-mounted video camera during the second simulation exercise only. Video recordings were replayed to participants to augment feedback, following the second simulation exercise. Data were collected on: participant performance (observed and perceived); participant perceptions of feedback methods; and head-mounted video camera recording feasibility and capability for detailed audio-visual feedback. RESULTS: Management of patient deterioration improved for six participants (60%). Increased perceptions of confidence (70%) and competence (80%), were reported by the majority of participants. Few participants (20%) agreed that the video recording specifically enhanced their learning. The visual field of the head-mounted video camera was not always synchronised with the participant's field of vision, thus affecting the usefulness of some recordings. CONCLUSION: The usefulness of the video recordings, to enhance verbal feedback to participants on detection and management of simulated patient deterioration, was inconclusive. Modification of the video camera glasses, to improve visual-field synchronisation with participants' actual visual field, is recommended to further explore this technology for enhancing student performance.

3D haptic needle insertion simulator utilising an agent based spherical voxel model

This paper describes a technique for the real-time modeling of deformable tissue. Specifically geared towards needle insertion simulation, the low computational requirements of the model enable highly accurate haptic feedback to a user without introducing noticeable time delay or buzzing generally associated with haptic surgery simulation. Using a spherical voxel array combined with aspects of computational geometry and agent communication and interaction principals, the model is capable of providing haptic update rates of over 1000Hz with real-time visual feedback. Iterating through over 1000 voxels per millisecond to determine collision and haptic response while making use of Vieta’s Theorem for extraneous force culling.

The development of CBT programmes for anger : the role of interventions to promote perspective-taking skills

Although the emotion of anger has, in recent years, been the subject of increasing theoretical analysis, there are relatively few accounts of how interventions designed to reduce problematic anger might be related to cognitively oriented theories of emotion. In this review of the literature we describe how a cognitive-behavioural approach to the treatment of those with anger-related problems might be understood in relation to conceptualizations of anger from a cognitive perspective. Three additional interventions (visual feedback, chair-work, forgiveness therapy) are identified that aim to improve the perspective-taking skills of angry clients. It is concluded that such interventions might be considered for use within the context of cognitive-behavioural treatment.

Examination of EMG normalisation methods for the study of the posterior and posterolateral neck muscles in healthy controls

The purpose of this study was to examine the reliability of normalisation methods used in the study of the posterior and posterolateral neck muscles in a group of healthy controls. Six asymptomatic male subjects performed a total of 12 maximum voluntary isometric contractions (MVIC) and 60%-submaximal isometric contractions (60%-MVIC) against the torque arm of an isokinetic dynamometer whilst surface and intramuscular electromyography (EMG) was recorded unilaterally from representative posterior and posterolateral locations. Reliability was calculated using intra-class correlation coefficient (ICC), relative standard error of measurement (%SEM) and relative coefficient of variation (%CV). Maximal torque output was found to be highly reliable in the directions of extension and right lateral bending when the first of three MVIC contractions was excluded. When averaged across contraction direction, high reliability was found for both surface (MVIC: ICC = 0.986, %SEM = 7.5, %CV = 9.2; 60%-MVIC: ICC = 0.975, %SEM = 10, %CV = 13.7) and intramuscular (MVIC: ICC = 0.910, %SEM = 20, %CV = 19.1; 60%-MVIC: ICC = 0.952, %SEM = 16.5, %CV = 13.5) electrodes. Intramuscular electrodes displayed the least reliability in right lateral bending. The use of visual feedback markedly increased the reliability of 60%-MVIC contractions.

Mechanisms for multimodality : taking fiction to another dimension

We present methods for automatically constructing representations of fiction books in a range of modalities: audibly, graphically and as 3D virtual environments. The correspondence between the sequential ordering of events against the order of events presented in the text is used to correctly resolve the dynamic interactions for each representation. Synthesised audio created from the fiction text is used to calibrate the base time-line against which the other forms of media are correctly aligned. The audio stream is based on speech synthesis using the text of the book, and is enhanced using distinct voices for the different characters in a book. Sound effects are included automatically. The graphical representation represents the text (as subtitles), identifies active characters and provides visual feedback of the content of the story. Dynamic virtual environments conform to the constraints implied by the story, and are used as a source of further visual content. These representations are all aligned to a common time-line, and combined using sequencing facilities to provide a multimodal version of the original text.

Virtual haptic cell model for operator training

Microrobotic cell injection is an area of growing research interest. Typically, operators rely on visual feedback to perceive the microscale environment and are subject to lengthy training times and low success rates. Haptic interaction offers the ability to utilise the operator’s haptic modality and to enhance operator performance. Our earlier work presented a haptically enabled system for assisting the operator with certain aspects of the cell injection task. The system aimed to enhance the operator’s controllability of the micropipette through a logical mapping between the haptic device and microrobot, as well as introducing virtual fixtures for haptic guidance. The system was also designed in such a way that given the availability of appropriate force sensors, haptic display of the cell penetration force is straightforward. This work presents our progress towards a virtual replication of the system, aimed at facilitating offline operator training. It is suggested that operators can use the virtual system to train offline and later transfer their skills to the physical system. In order to achieve the necessary representation of the cell within the virtual system, methods based on a particle-based cell model are utilised. In addition to providing the necessary visual representation, the cell model provides the ability to estimate cell penetration forces and haptically display them to the operator. Two different approaches to achieving the virtual system are discussed.

Visual perception of movement kinematics and the acquisition of "action prototypes"

Recognizing a class of movements as belonging to a "nominal" action category, such as walking, running, or throwing, is a fundamental human ability. Three experiments were undertaken to test the hypothesis that common ("prototypical") features of moving displays could be learned by observation. Participants viewed moving stick-figure displays resembling forearm flexion movements in the saggital plane. Four displays (presentation displays) were first presented in which one or more movement dimensions were combined with 2 respective cues: direction (up, down), speed (fast, slow), and extent (long, short). Eight test displays were then shown, and the observer indicated whether each test display was like or unlike those previously seen. The results showed that without corrective feedback, a single cue (e.g., up or down) could be correctly recognized, on average, with the proportion correct between .66 and .87. When two cues were manipulated (e.g., up and slow), recognition accuracy remained high, ranging between .72 and .89. Three-cue displays were also easily identified. These results provide the first empirical demonstration of action-prototype learning for categories of human action and show how apparently complex kinematic patterns can be categorized in terms of common features or cues. It was also shown that probability of correct recognition of kinematic properties was reduced when the set of 4 presentation displays were more variable with respect to their shared kinematic property, such as speed or amplitude. Finally, while not conclusive, the results (from 2 of the 3 experiments) did suggest that similarity (or "likeness") with respect to a common kinematic property (or properties) is more easily recognized than dissimilarity.

User-centered design and evaluation of an interactive visual-haptic-auditory interface : a user study on assembly

Utilizing user-centred system design and evaluation method has become an increasingly important tool to foster better usability in the field of virtual environments (VEs). In recent years, although it is still the norm that designers and developers are concerning the technological advancement and striving for designing impressive multimodal multisensory interfaces, more and more awareness are aroused among the development team that in order to produce usable and useful interfaces, it is essential to have users in mind during design and validate a new design from users' perspective. In this paper, we describe a user study carried out to validate a newly developed haptically enabled virtual training system. By taking consideration of the complexity of individual differences on human performance, adoption and acceptance of haptic and audio-visual I/O devices, we address how well users learn, perform, adapt to and perceive object assembly training. We also explore user experience and interaction with the system, and discuss how multisensory feedback affects user performance, perception and acceptance. At last, we discuss how to better design VEs that enhance users perception, their interaction and motor activity.