Willow Garage

About: Willow Garage is a based out in . It is known for research contribution in the topics: Robot & Mobile robot. The organization has 76 authors who have published 191 publications receiving 28617 citations.

Toward Automatic 3D Generic Object Modeling from One Single Image

Abstract: We present a novel method for solving the challenging problem of generating 3D models of generic object categories from just one single un-calibrated image. Our method leverages the algorithm proposed in [1] which enables a partial reconstruction of the object from a single view. A full reconstruction is achieved in a subsequent object completion stage where modified or state-of-the-art 3D shape and texture completion techniques are used to recover the complete 3D model. We present results of our method on a number of images containing objects from five generic categories (mice, staplers, mugs, cars, and bicycles). We demonstrate (numerically and qualitatively) that our method produces convincing 3D models from a single image using minimal or no human intervention. Our technique is targeted to applications where users are interested in building virtual collections of 3D models of objects, and sharing such models in virtual environments such as Google 3D Warehouse or Second Life (secondlife.com).

A single planner for a composite task of approaching, opening and navigating through non-spring and spring-loaded doors

Abstract: Opening and navigating through doors remains a challenging problem, particularly in cluttered environments and for spring-loaded doors. Passing through doors, especially spring-loaded doors, requires making and breaking contacts with the door and preventing the door from closing while passing through. In this work, we present a planning framework that handles non-spring and spring-loaded doors, in cluttered or confined workspaces, planning the approach to the door, pushing or pulling it open, and passing through. Because the problem is solved in a combined search space, the planner yields an overall least-cost path. The planner is able to insert a transition between robot-door contacts at any point along the plan. We utilize a compact graph-based representation of the problem to keep planning times low. We precompute the force workspace of the end-effectors to eliminate checks against joint torque limits at plan time. We have validated our solution in both simulation and real-world experiments on the PR2 mobile manipulation platform; the robot is able to successfully open a variety of spring-loaded and non-spring-loaded doors by pushing and pulling.

Grasp Planning Using Low Dimensional Subspaces

Abstract: Recent advances in neuroscience research have shown that posture variation of the human hand during grasping is dominated by movement in a configuration space of highly reduced dimensionality. In this chapter we explore how robot and artificial hands may take advantage of similar subspaces to reduce the complexity of dexterous grasping. We first describe our method for grasp synthesis using a low-dimensional posture subspace, and apply it to a set of hand models with different kinematics and numbers of degrees of freedom. We then discuss two applications of the method: online interactive grasp planning and data-driven grasp planning using a pre-computed database of stable grasps.

Force-Sensitive Detents Improve User Performance for Linear Selection Tasks

Abstract: Haptic technology, providing force cues and creating a programmable interface, can assist users in more accurately using an interface. This paper investigates haptic assistance in combination with auditory feedback instead of visual feedback. A user test is carried out in which participants select fundamental frequencies from a continuous range to play brief musical melodies. Two control conditions are compared with two detent-based haptic assistance conditions. The detents gently guide the users toward locations of equal tempered fundamental frequencies. Results from the user test confirm improved accuracy brought about by the detents. It is further helpful to provide regulation of the strength of haptic assistance in real time, allowing the user to remain always in control. This concept motivated the force-sensitive detent condition, which enables the user to adjust the strength of the haptic assistance in real time by changing the downward force applied to the haptic device. The work implies that users of graphical user interfaces could similarly benefit from force-sensitive detents and more generally real-time regulation of the strength of haptic assistance.

Sparse Kernel-SARSA(λ) with an eligibility trace

Abstract: We introduce the first online kernelized version of SARSA(λ) to permit sparsification for arbitrary λ for 0 ≤ λ ≤ 1; this is possible via a novel kernelization of the eligibility trace that is maintained separately from the kernelized value function This separation is crucial for preserving the functional structure of the eligibility trace when using sparse kernel projection techniques that are essential for memory efficiency and capacity control The result is a simple and practical Kernel-SARSA(λ) algorithm for general 0 ≤ λ ≤ 1 that is memory-efficient in comparison to standard SARSA(λ) (using various basis functions) on a range of domains including a real robotics task running on a Willow Garage PR2 robot