QCR Seminar Series: On Continuous and Probabilistic Models for Integration, Localisation, Mapping and Planning by Dr Teresa Vidal Calleja (UTS)
Time: 10 November 2020
In this talk Dr Vidal Calleja presented her recent work based on Gaussian Process (GP) for continuous and probabilistic models. First, she discussed the analytical preintegration of continuous inertial measurements using linear operators on GP Kernels, which are the core of two different frameworks for localisation and mapping; LiDAR/Inertial (IN2LAAMA) and Event-camera/Inertial (IDOL).
In the second part of the talk, she went through the derivation of our probabilistic Euclidean distance function via the log transform of a GP implicit surface formulation, which is a suitable representation for surface reconstruction and local planning. She showed the performance of all these approaches in different simulated and real scenarios.
Speaker: Dr Teresa Vidal Calleja is Deputy Head of School (Research) at the School of Mechanical and Mechatronics Engineering and core researcher at the Centre for Autonomous Systems of the University of Technology Sydney (UTS:CAS). Teresa received her BSc in Mechanical Engineering from the National Autonomous University of Mexico, her MSc in Electrical Engineering from CINVESTAV-IPN (Mexico) and her PhD in Automatic Control, Computer Vision and Robotics from the Polytechnic University of Catalonia (Spain).
She was postdoctoral fellow at LAAS-CNRS (France) and the Australian Centre for Field Robotics at the University of Sydney. She joined the UTS:CAS in 2012, where she moved from UTS Chancellor’s Research Fellow to Senior Lecturer. Teresa has established links with world-leading robotics research institutions such as Autonomous Systems Lab – ETHZ (Switzerland) and the German Aerospace Center – DLR (Germany).
Her industry collaborations are with the meat and livestock, manufacturing and services sectors. Her research interest is in robotic perception, including multisensory data fusion, self-localisation and 3D mapping, pattern recognition, air/ground robotic cooperation, and autonomous navigation and manipulation.