One Object at a Time: Accurate and Robust Structure From Motion for Robots

07/31/2022
by   Aravind Battaje, et al.
4

A gaze-fixating robot perceives distance to the fixated object and relative positions of surrounding objects immediately, accurately, and robustly. We show how fixation, which is the act of looking at one object while moving, exploits regularities in the geometry of 3D space to obtain this information. These regularities introduce rotation-translation couplings that are not commonly used in structure from motion. To validate, we use a Franka Emika Robot with an RGB camera. We a) find that error in distance estimate is less than 5 mm at a distance of 15 cm, and b) show how relative position can be used to find obstacles under challenging scenarios. We combine accurate distance estimates and obstacle information into a reactive robot behavior that is able to pick up objects of unknown size, while impeded by unforeseen obstacles.

READ FULL TEXT

page 1

page 2

page 5

page 6

research
04/14/2018

Motion-based Object Segmentation based on Dense RGB-D Scene Flow

Given two consecutive RGB-D images, we propose a model that estimates a ...
research
03/02/2021

Spatial Attention Point Network for Deep-learning-based Robust Autonomous Robot Motion Generation

Deep learning provides a powerful framework for automated acquisition of...
research
10/02/2022

Throwing Objects into A Moving Basket While Avoiding Obstacles

The capabilities of a robot will be increased significantly by exploitin...
research
07/11/2020

Learning Object Depth from Camera Motion and Video Object Segmentation

Video object segmentation, i.e., the separation of a target object from ...
research
04/02/2018

Stress-Based Navigation for Microscopic Robots in Viscous Fluids

Objects moving in fluids experience patterns of stress on their surfaces...
research
07/08/2021

Active Safety Envelopes using Light Curtains with Probabilistic Guarantees

To safely navigate unknown environments, robots must accurately perceive...
research
02/26/2020

Probabilistic approach to physical object disentangling

Physically disentangling entangled objects from each other is a problem ...

Please sign up or login with your details

Forgot password? Click here to reset