Event Location: NSH 1109
Bio: Thierry Peynot is a Research Fellow at the Australian Centre for Field
Robotics (ACFR), The University of Sydney, Australia. His current
research interests are mainly persistent autonomy, perception integrity
and terrain interpretation for Autonomous Ground Vehicles. He received
his PhD degree from the University of Toulouse in 2006, with a thesis
called Selection and Monitoring of Navigation Modes for a Mobile Robot
in Natural Environments prepared at LAAS-CNRS. From 2005 to 2007 he was
also a fixed-term Associate Professor at University Toulouse III.

Abstract: This presentation will focus on Perception for Autonomous Ground
Vehicles (AGV), in particular in challenging conditions, such as
presence of airborne dust. It has been demonstrated that to aim at
“Persistent Autonomy” (i.e. autonomy for long-term missions),
reliability and integrity in autonomous perceptual systems need to be
promoted. For this purpose, large, accurately calibrated and
synchronised, multi-modal datasets were gathered in controlled
environmental conditions, including the presence of dust, smoke and
rain. An analysis of sensor data integrity has then been realized, to
identify common perceptual failures, and on-going research is studying
methods for mitigating these failures.