X-Ray: Mechanical Search for an Occluded Object by Minimizing Support of Learned Occupancy Distributions

04/20/2020
by   Michael Danielczuk, et al.
2

For applications in e-commerce, warehouses, healthcare, and home service, robots are often required to search through heaps of objects to grasp a specific target object. For mechanical search, we introduce X-Ray, an algorithm based on learned occupancy distributions. We train a neural network using a synthetic dataset of RGBD heap images labeled for a set of standard bounding box targets with varying aspect ratios. X-Ray minimizes support of the learned distribution as part of a mechanical search policy in both simulated and real environments. We benchmark these policies against two baseline policies on 1,000 heaps of 15 objects in simulation where the target object is partially or fully occluded. Results suggest that X-Ray is significantly more efficient, as it succeeds in extracting the target object 82 than the best-performing baseline. Experiments on an ABB YuMi robot with 20 heaps of 25 household objects suggest that the learned policy transfers easily to a physical system, where it outperforms baseline policies by 15 rate with 17 http://sites.google.com/berkeley.edu/x-ray .

READ FULL TEXT

page 1

page 3

page 5

page 6

research
11/23/2020

Mechanical Search on Shelves using Lateral Access X-RAY

Efficiently finding an occluded object with lateral access arises in man...
research
03/04/2019

Mechanical Search: Multi-Step Retrieval of a Target Object Occluded by Clutter

When operating in unstructured environments such as warehouses, homes, a...
research
02/24/2023

From Occlusion to Insight: Object Search in Semantic Shelves using Large Language Models

How can a robot efficiently extract a desired object from a shelf when i...
research
07/05/2022

Mechanical Search on Shelves with Efficient Stacking and Destacking of Objects

Stacking increases storage efficiency in shelves, but the lack of visibi...
research
01/22/2022

Mechanical Search on Shelves using a Novel "Bluction" Tool

Shelves are common in homes, warehouses, and commercial settings due to ...
research
07/20/2020

Non-Markov Policies to Reduce Sequential Failures in Robot Bin Picking

A new generation of automated bin picking systems using deep learning is...
research
08/13/2020

Visuomotor Mechanical Search: Learning to Retrieve Target Objects in Clutter

When searching for objects in cluttered environments, it is often necess...

Please sign up or login with your details

Forgot password? Click here to reset