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

ST Robotics - R17HS-6, the 6-axis version of the high speed R17 variant

ST Robotics - R17HS-6, the 6-axis version of the high speed R17 variant

The 6-axis version of the R17HS high speed variant of the R17 robot is now available. As is our policy the 6th axis is an optional bolt-on module. At the same time we have made it even faster and new software eliminates shake and greatly improves repeatability as this video shows. Please see https://www.youtube.com/watch?v=3wG0MeiJ-yE. The video would seem to imply a repeatability of 0.01mm but we are sticking with 0.2mm in the spec. The motor specialist was able to tune the motors from the other side of the pond. My first reaction when we put power on and entered the first commands was to jump back in amazement (and maybe an expletive). Tip speed is now 3m/s; that's 3 times as fast as its nearest competitor yet costs half the price. I love it when a plan comes together.