Description
Toyota Material Handling is hiring a master thesis student to develop deep-learning methods for pallet perception, with a focus on general pallet identification and localization. The project involves training and evaluating deep-learning models, developing algorithms for fusing RGB-camera and ToF-camera outputs, and assessing performance on real-world data compared with synthetic-environment results. The work will be carried out in collaboration with a machine-learning development team and will use a modern sensor system including a 2D RGB camera, a ToF 3D camera, pixel-to-point-cloud correlation, and an NVIDIA GPU in an embedded environment. The thesis is 30 hp and intended for 1–2 students, starting in January 2027, with applications accepted until 2026-11-01.
