Object detection for a mobile robot using mixed reality

Authors:
Hua Chen;Oliver Wulf;Bernardo Wagner
Affiliations:
Learning Lab Lower Saxony (L3S) Research Center, Hanover, Germany;Institute for Systems Engineering, University of Hanover, Germany;Institute for Systems Engineering, University of Hanover, Germany
Venue:
VSMM'06 Proceedings of the 12th international conference on Interactive Technologies and Sociotechnical Systems
Year:
2006

Citing 5
Cited 1

A Spatial Sampling Criterion for Sonar Obstacle Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Mixed Reality: Merging Real and Virtual Worlds

Mixed Reality: Merging Real and Virtual Worlds
A 3D robot simulation for education

Proceedings of the 1st international conference on Computer graphics and interactive techniques in Australasia and South East Asia
World Embedded Interfaces for Human-Robot Interaction

HICSS '03 Proceedings of the 36th Annual Hawaii International Conference on System Sciences (HICSS'03) - Track 5 - Volume 5
Emerging areas: urban operations and UCAVs: a game engine based simulation of the NIST urban search and rescue arenas

Proceedings of the 35th conference on Winter simulation: driving innovation

Mixed reality simulation for mobile robots

ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a novel Human-Robot Interface (HRI) that uses a Mixed Reality (MR) space to enhance and visualize object detection for mobile robot navigation. The MR space combines the 3D virtual model of a mobile robot and its navigating environment with the real data such as physical building measurement, the real-time acquired robot’s position and laser scanned points. The huge amount of laser scanned points are rapidly segmented as belonging either to the background (i.e. fixed building) or newly appeared objects by comparing them with the 3D virtual model. This segmentation result can not only accelerate the object detection process but also facilitate the further process of object recognition with significant reduction of redundant sensor data. Such a MR space can also help human operators realizing effective surveillance through real-time visualization of the object detection results. It can be applied in a variety of mobile robot applications in a known environment. Experimental results verify the validity and feasibility of the proposed approach.