Deep Learning for Detecting Robotic Grasps

From Ian Lenz, Honglak Lee, Ashutosh Saxena:

Abstract

We consider the problem of detecting robotic grasps in an RGB-D view of a scene containing objects. In this work, we apply a deep learning approach to solve this problem, which avoids time-consuming hand-design of features. This presents two main challenges. First, we need to evaluate a huge number of candidate grasps. In order to make detection fast and robust, we present a two-step cascaded system with two deep networks, where the top detections from the first are re-evaluated by the second. The first network has fewer features, is faster to run, and can effectively prune out unlikely candidate grasps. The second, with more features, is slower but has to run only on the top few detections. Second, we need to handle multimodal inputs effectively, for which we present a method that applies structured regularization on the weights based on multimodal group regularization. We show that our method improves performance on an RGBD robotic grasping dataset, and can be used to successfully execute grasps on two different robotic platforms... (homepage) (full pdf paper)

Comments (0)

This post does not have any comments. Be the first to leave a comment below.


Post A Comment

You must be logged in before you can post a comment. Login now.

Featured Product

igus® Robolink: Articulated joint modules for robots. Lightweight. Compact.

igus® Robolink: Articulated joint modules for robots. Lightweight. Compact.

Robolink: Articulated joint modules for robots. igus® now offers a lightweight, maintenance- and corrosion-free range of robot joints for humanoid systems or other automated applications. The carbon-fiber plastic joints can rotate and oscillate freely via four wire ropes. No more expensive milling, cutting or DIY systems. Moving mass is reduced to a minimum. The actuators (engines, pneumatics and hydraulics) and the control module (DP, PC) are kept separate. Contact igus® for more information and free samples.