We present the design and implementation of a vision-based system for cooperative manipulation at millimeter to micrometer scales. The system is based on an admittance control algorithm that implements a broad class of guidance modes called virtual fixtures. A virtual fixture, like a real fixture, limits the motion of a tool to a prescribed class or range of motions. We describe how both hard (unyielding) and soft (yielding) virtual fixtures can be implemented in this control framework. We then detail the construction of virtual fixtures for point positioning and curve following as well as extensions of these to tubes, cones, and sequences thereof. We also describe an implemented system using the JHU Steady Hand Robot. The system uses computer vision as a sensor for providing a reference trajectory, and the virtual fixture control algorithm then provides haptic feedback to implemented direct, shared manipulation. We provide extensive experimental results detailing both system performance and the effects of virtual fixtures on human speed and accuracy.

The bulk of current haptics human-factors research focuses on mapping basic human perceptual limits. However, many realistic applications demand a better understanding of how to construct more life-like but often less controllable experiment scenarios. In this paper, we study this problem in the context of advanced automobile interfaces. We employ a throttle pedal with programmable force feedback to indicate potentially undesirable situations in the external environment and to gently but steadily guide the driver away from them. We have found evidence that within this scenario, errors in such a warning signal can have a negative effect on the behavior of the driver within the conditions studied. These experiments required a complex protocol and necessarily permitted a variety of participant tactics. Postexperiment analysis revealed that very subtle variations in participant instruction produced large differences in tactics and consequent experiment outcome.

(LHMM) for motion intention recognition based on actionprimitives or gestemes. The proposed methodology uses three different HMM models at the gesteme level: one-dimensional HMM, multi-dimensional HMM and multi-dimensional HMM with Fourier transform. These three models are evaluated with respect to the number of gestemes, the influence of the number of training samples, the effect of noise and the effect of the number of observation symbols. I.

Submission for short paper Dividing the task that the operator is executing into several subtasks is one of the key research areas in teleoperative and humanmachine collaborative settings. Hence, segmentation and recognition of operator generated motions are commonly facilitated to provide appropriate assistance during task execution. This assistance is usually provided in a virtual fixture framework where the level of compliance can be altered online thus improving the performance both in terms of execution time and overall precision. However, the fixtures are typically inflexible, resulting in a degraded performance in cases of unexpected obstacles or incorrect fixture models. In this paper, we deal with the problem of on-line task tracking and propose the use of adaptive virtual fixtures that can cope with the above problems. The operator may remain in each of these subtasks as long as necessary and switch freely between them. Hence, rather than executing a predefined plan, the operator has the ability to avoid unforeseen obstacles and deviate from the model. In our system, the probability that the user is following a certain trajectory (subtask) is estimated and used to automatically adjusts the compliance. Thus, an on-line decision of how to fixture the movement is provided.

Acquiring, representing and modeling human skills is one of the key research areas in teleoperation, programming-by-demonstration and human-machine collaborative settings. The problems is challenging mainly because of the lack of a general mathematical model to describe human skills. One of the common approaches is to divide the task that the operator is executing into several subtasks or low-level subsystems in order to provide manageable modeling. In this paper we consider the use of a Layered Hidden Markov Model (LHMM) to model human skills. We evaluate a gesteme classifier that classifies motions into basic actionprimitives, or gestemes. The gesteme classifiers are then used in a LHMM to model a teleoperated task. The proposed methodology uses three different HMM models at the gesteme level: one-dimensional HMM, multi-dimensional HMM and multi-dimensional HMM with Fourier transform. The online and off-line classification performance of these three models is evaluated with respect to the number of gestemes, the influence of the number of training samples, the effect of noise and the effect of the number of observation symbols. We also apply the LHMM to data recorded during the execution of a trajectory tracking task in 2D and 3D with a mobile manipulator in order to provide qualitative as well as quantitative results for the proposed approach. The results indicate that the LHMM is suitable for modeling teleoperative trajectorytracking tasks and that the difference in classification performance between one and multi dimensional HMMs for gesteme classification is small. It can also be seen that the LHMM is robust with respect to misclassifications in the underlying gesteme classifiers. Key words: Layered Hidden Markov Models, human-machine collaboration, motion intention recognition

Multi-function interfaces have become increasingly pervasive and are frequently used in contexts which pose multiple demands on a single sensory modality. Assuming some degree of modularity in attentional processing and that using a different sensory channel for communication can reduce interference with critical visual tasks, one possibility is to divert some information through the touch sense. The goal of this Thesis is to advance our knowledge of relevant human capabilities and embed this knowledge into haptic communication design tools and procedures, in the interest of creating haptically supported interfaces that decrease rather than add to their users’ sensory and cognitive load. In short, we wanted to create tools and methods that would allow the creation of haptic signals (accomplished via display of either forces or vibrations) extending beyond the one bit of communication offered by current pagers and cellular phone buzzers. In our quest to create information-rich haptic signals we need to learn how