Sensor Data Integrity and Mitigation of Perceptual Failures
Abstract
In the first part of this project, in 2008, large amounts of synchronised data were gathered from a representative UGV platform using a wide variety of sensing modalities (Fig. 1). These modalities included a visual camera, an infrared (IR) camera, laser range finders and a mm-wave radar. The data sets were collected from a UGV in the presence of challenging environmental conditions (such as the presence of airborne dust, smoke, rain). The collected data were then published, and are now extensively used for the developments of this new project. The general objective is to better understand and promote integrity and dependability of perceptual systems for unmanned ground vehicle (UGV) systems, to provide them with the ability to achieve long-term autonomous operations in off-road environments, including (and in particular) in challenging conditions.
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 24, 2011
- Accession Number
- ADA537597
Entities
People
- Thierry Peynot
Organizations
- University of Sydney