Loading…

A ROS framework for the extrinsic calibration of intelligent vehicles: A multi-sensor, multi-modal approach

This paper proposes a general approach to the problem of extrinsic calibration of multiple sensors of varied modalities. This is of particular relevance for intelligent vehicles, which are complex systems that often encompass several sensors of different modalities. Our approach is seamlessly integr...

Full description

Saved in:
Bibliographic Details
Published in:Robotics and autonomous systems 2020-09, Vol.131, p.103558, Article 103558
Main Authors: Oliveira, Miguel, Castro, Afonso, Madeira, Tiago, Pedrosa, Eurico, Dias, Paulo, Santos, Vítor
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes a general approach to the problem of extrinsic calibration of multiple sensors of varied modalities. This is of particular relevance for intelligent vehicles, which are complex systems that often encompass several sensors of different modalities. Our approach is seamlessly integrated with the Robot Operating System (ROS) framework, and allows for the interactive positioning of sensors and labelling of data, facilitating the calibration procedure. The calibration is formulated as a simultaneous optimization for all sensors, in which the objective function accounts for the various sensor modalities. Results show that the proposed procedure produces accurate calibrations, on par with state of the art approaches which operate only for pairwise setups. •Intelligent vehicles require a package that calibrate all sensors at once, in order to operate consistently.•The multimodal complete calibraton achieves similar accuracy when compared to standard pairwise calibrations.•The multimodal calibraton approach works on ROS and uses several interactive tools that ease the calibraton procedure.•The multimodal and multisensor calibraton does not change the initial robots transformation tree.
ISSN:0921-8890
1872-793X
DOI:10.1016/j.robot.2020.103558