LocaliseBot: Multi-view 3D object localisation with differentiable rendering for robot grasping

Robot grasp typically follows five stages: object detection, object localisation, object pose estimation, grasp pose estimation, and grasp planning. We focus on object pose estimation. Our approach relies on three pieces of information: multiple views of the object, the camera's extrinsic param...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-11
Main Authors: Vijayaraghavan, Sujal, Alqasemi, Redwan, Dubey, Rajiv, Sarkar, Sudeep
Format: Article
Language:English
Subjects:
Cameras
Cloud computing
Clutter
Datasets
Grasping (robotics)
Image segmentation
Localization
Object recognition
Optimization
Pose estimation
Rendering
Robots
Semantic segmentation
Three dimensional models
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Robot grasp typically follows five stages: object detection, object localisation, object pose estimation, grasp pose estimation, and grasp planning. We focus on object pose estimation. Our approach relies on three pieces of information: multiple views of the object, the camera's extrinsic parameters at those viewpoints, and 3D CAD models of objects. The first step involves a standard deep learning backbone (FCN ResNet) to estimate the object label, semantic segmentation, and a coarse estimate of the object pose with respect to the camera. Our novelty is using a refinement module that starts from the coarse pose estimate and refines it by optimisation through differentiable rendering. This is a purely vision-based approach that avoids the need for other information such as point cloud or depth images. We evaluate our object pose estimation approach on the ShapeNet dataset and show improvements over the state of the art. We also show that the estimated object pose results in 99.65% grasp accuracy with the ground truth grasp candidates on the Object Clutter Indoor Dataset (OCID) Grasp dataset, as computed using standard practice.
ISSN:2331-8422
DOI:10.48550/arxiv.2311.08438