Master thesis: Robust Multimodal 3D Object Detection with RADAR
Core
Develop robust multimodal 3D object detection methods for autonomous transport systems that maintain reliability when RADAR data is missing or noisy.
Role type
Master thesis researcher (multimodal perception)
Builds
Training strategies for 3D object detectors using modality dropout or modality-aware learning
Domain
Autonomous transport / Machine perception
Deliverable
research
Required skills
Python programming, deep-learning frameworks (PyTorch or TensorFlow), multimodal sensor data analysis, experimental design
Preferred skills
Experience with autonomous systems, modality dropout techniques, scientific documentation
Technologies
PyTorch, TensorFlow, RADAR, LiDAR, cameras
Responsibilities
Design training and evaluation strategies for missing-modality conditions, train and test detectors under varying sensor conditions, measure robustness using performance metrics, analyze results and document findings in a scientific report
Seniority
Master's thesis student
