Tyson Phillips

Dr. Tyson Phillips serves as Senior Lecturer and Director of Teaching and Learning in the School of Mechanical and Mining Engineering at the University of Queensland, part of the Faculty of Engineering, Architecture and Information Technology. He completed his Doctor of Philosophy at the University of Queensland in 2016, with a thesis entitled 'Determining and verifying object pose from LiDAR measurements to support the perception needs of an autonomous excavator.' Phillips was a finalist in the 2014 University of Queensland Three Minute Thesis competition. In 2020, he received a Citation for Excellence in Student Learning from the EAIT Faculty Teaching and Learning Awards, recognizing his outstanding contributions to student education.

Phillips' research centers on advanced perception technologies for autonomous mining systems, with expertise in point cloud analysis employing evidential methods, real-time object pose estimation, LiDAR sensor registration and performance in adverse conditions like dust and fog, and probabilistic terrain mapping. His publications appear in prestigious venues such as the Journal of Field Robotics, The International Journal of Robotics Research, and Sensors. Notable works include 'When the dust settles: the four behaviors of LiDAR in the presence of fine airborne particulates' (Journal of Field Robotics, 2017), 'Maximum sum of evidence—an evidence-based solution to object pose estimation in point cloud data' (Sensors, 2021), 'Real-time 6-DOF pose estimation of known geometries in point cloud data' (Sensors, 2023), and 'Minimal configuration point cloud odometry and mapping' (The International Journal of Robotics Research, 2024). He has attracted substantial industry funding from Caterpillar Inc., Fortescue Metals Group Limited, and the Australian Coal Association Research Program for projects including autonomous articulated truck systems, electric rope shovel operator assist, and coal stockpile management for remote bulldozers. Phillips supervises doctoral candidates on situational awareness from point cloud data for autonomous mining machines and is available for higher degree research supervision.