Showing papers by "Willow Garage published in 2017"

Probabilistic Collision Detection Between Noisy Point Clouds Using Robust Classification

Abstract: We present a new collision detection algorithm to perform contact computations between noisy point cloud data. Our approach takes into account the uncertainty that arises due to discretization error and noise, and formulates collision checking as a two-class classification problem. We use techniques from machine learning to compute the collision probability for each point in the input data and accelerate the computation using stochastic traversal of bounding volume hierarchies. We highlight the performance of our algorithm on point clouds captured using PR2 sensors as well as synthetic data sets, and show that our approach can provide a fast and robust solution for handling uncertainty in contact computations.

Robotic bin management system and method

Abstract: One embodiment is directed to a personal robotic system, comprising: an electromechanical mobile base defining a cross-sectional envelope when viewed in a plane substantially parallel to a plane of a floor upon which the mobile base is operated; a torso assembly movably coupled to the mobile base; a head assembly movably coupled to the torso; a releasable bin-capturing assembly movably coupled to the torso; and a controller operatively coupled to the mobile base, torso assembly, head assembly, and bin-capturing assembly, and configured to capture a bin with the bin-capturing assembly and move the torso assembly relative to the mobile base so that the captured bin fits as closely as possible within the cross-sectional envelope of the mobile base.