Learning Camera Performance Models for Active Multi-Camera Visual Teach and Repeat

03/25/2021
by   Matías Mattamala, et al.
0

In dynamic and cramped industrial environments, achieving reliable Visual Teach and Repeat (VT R) with a single-camera is challenging. In this work, we develop a robust method for non-synchronized multi-camera VT R. Our contribution are expected Camera Performance Models (CPM) which evaluate the camera streams from the teach step to determine the most informative one for localization during the repeat step. By actively selecting the most suitable camera for localization, we are able to successfully complete missions when one of the cameras is occluded, faces into feature poor locations or if the environment has changed. Furthermore, we explore the specific challenges of achieving VT R on a dynamic quadruped robot, ANYmal. The camera does not follow a linear path (due to the walking gait and holonomicity) such that precise path-following cannot be achieved. Our experiments feature forward and backward facing stereo cameras showing VT R performance in cluttered indoor and outdoor scenarios. We compared the trajectories the robot executed during the repeat steps demonstrating typical tracking precision of less than 10cm on average. With a view towards omni-directional localization, we show how the approach generalizes to four cameras in simulation. Video: https://youtu.be/iAY0lyjAnqY

READ FULL TEXT

page 1

page 6

research
03/23/2023

Mobile MoCap: Retroreflector Localization On-The-Go

Motion capture (MoCap) through tracking retroreflectors obtains high pre...
research
08/15/2022

Look Both Ways: Bidirectional Visual Sensing for Automatic Multi-Camera Registration

This work describes the automatic registration of a large network (appro...
research
01/15/2020

Pose-Assisted Multi-Camera Collaboration for Active Object Tracking

Active Object Tracking (AOT) is crucial to many visionbased applications...
research
05/19/2021

Large-scale Localization Datasets in Crowded Indoor Spaces

Estimating the precise location of a camera using visual localization en...
research
03/01/2022

Indoor Localization for Quadrotors using Invisible Projected Tags

Augmented reality (AR) technology has been introduced into the robotics ...
research
08/17/2020

PAR: Personal Activity Radius Camera View for Contextual Sensing

Contextual sensing using wearable cameras has seen a variety of differen...
research
09/23/2022

Wide-Area Geolocalization with a Limited Field of View Camera

Cross-view geolocalization, a supplement or replacement for GPS, localiz...

Please sign up or login with your details

Forgot password? Click here to reset