Lab Meeting Nov. 21, (Channing) Where Do I Look Now? Gaze Allocation During Visually Guided Manipulation (ICRA 2012)

Title: Where Do I Look Now? Gaze Allocation During Visually Guided Manipulation (ICRA 2012)
Authors: Jose Nunez-Varela, B. Ravindran, Jeremy L.Wyatt

ABSTRACT - In this work we present principled methods for the coordination of a robot's oculomotor system with the rest of its body motor systems. The problem is to decide which physical actions to perform next and where the robot's gaze should be directed in order to gain information that is relevant to the success of its physical actions. Previous work on this problem has shown that a reward-based coordination mechanism provides an efficient solution. However, that approach does not allow the robot to move its gaze to different parts of the scene, it considers the robot to have only one motor system, and assumes that the actions have the same duration. The main contributions of our work are to extend that previous reward-based approach by making decisions about where to fixate the robot's gaze, handling multiple motor systems, and handling actions of variable duration. We compare our approach against two common baselines: random and round robin gaze allocation. We show how our method provides a more effective strategy to allocate gaze where it is needed the most.

Link

The Extension of the above work:

Title: Gaze Allocation Analysis for a Visually Guided Manipulation Task (SAB 2012)

Authors: Jose Nunez-Varela, B. Ravindran, Jeremy L.Wyatt

ABSTRACT - 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 de ne 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 our model on a simulated humanoid robot which has to move objects from a table into containers. Our model outperforms and is more robust than two other baseline schemes in terms of task performance whilst varying three environmental conditions, reach/grasp sensitivity, observation noise and the camera's field of view.

Link