Prospection is an important part of how humans come up with new task plans, but has not been explored in depth in robotics. Predicting multiple task-level is a challenging problem that involves capturing both task semantics and continuous variability over the state of the world. Ideally, we would combine the ability of machine learning to leverage big data for learning the semantics of a task, ...

Applications in mobile manipulation require sophisticated motion execution skills to address issues like redundancy resolution, reactive obstacle avoidance, and transitioning between diflerent motion behaviors. The elastic strip framework is an approach to reactive mot ion generation providing an integrated solution to these problems. Novel techniques within the elastic strip framework are pres...

Findings from eye movement research in humans have demonstrated that the task determines where to look. One hypothesis is that the purpose of looking is to reduce uncertainty about properties relevant to the task. Following this hypothesis, we define a model that poses the problem of where to look as one of maximising task performance by reducing task relevant uncertainty. We implement and test...

Systems that can track and intelligently adapt to changes in users’ cognitive capacities may help to improve human performance. The experiment reported here was designed to assess the benefit of placing neuro-physiological sensors on users to provide data about their cognitive states that can drive performance mitigations. A test group of 16 participants performed a primary task while monitorin...

The influence of self-efficacy on physiological arousal and self-reported anxiety was examined in the first phase of this study. All 32 undergraduate females in the study performed five trials of both an easy task and a difficult task, with half of them performing the easy task first and half performing the difficult task first. A manipulation check revealed that the easy task clearly elicited ...

Title of Document: MULTI-DIGIT MANIPULATION OF A CIRCULAR OBJECT Junfeng Huang, Doctor of Philosophy, 2012 Directed By: Associate Professor, Jae Kun Shim Department of Kinesiology Multi-digit prehension tasks are commonly encountered in our daily activities. Previous studies investigated behavioral characteristics and neuromuscular mechanisms during manipulation actions. The purpose of this dis...

This paper discusses recent research progress in robotic grasping and manipulation the light of latest Robotic Grasping Manipulation Competitions (RGMCs). We first provide an overview past benchmarks competitions related to robotics field. Then, we discuss methodology behind designing tasks RGMCs. a detailed analysis key challenges for each task identify most difficult aspects based on competin...

This study evaluates the effect of fingertip covering on the performance of perceptual and manipulation tasks. For the perceptual task, subjects were timed as they detected hard lumps in soft rubber models while barehanded and while wearing gloves of thickness 0.32 mm, 0.64 mm, 0.95 mm, 1.27 mm, 1.59 mm and 1.91 mm. Four lump sizes with diameters 3.2 mm, 4.8 mm, 6.4 mm and 7.9 mm were used. Ana...

Robotic mobile manipulation in unstructured environments requires integration of a number of key reasearch areas such as localization, navigation, object recognition, visual tracking/servoing, grasping and object manipulation. It has been demonstrated that, given the above, and through simple sequencing of basic skills, a robust system can be designed, [19]. In order to provide the robustness a...