Master Thesis Improving Object Detection Performance of Automotive Radar by Deeply Reinforced Cognitive Sensing

Fields of workResearch Job typeFull-time Start DateAccording to arrangement Apply now Welcome to Bosch Your tasks We are seeking a master's thesis student to contribute to the improvement of object detection performance in automotive radar systems. This research aims to address the challenges of detecting weak targets and vulnerable road users at long distances and in complex object constellations, overcoming the limitations of current static sensor modulations. During your master thesis, you will adapt sensor modulation based on sensor results and their uncertainties to optimise radar object detection capabilities. You will extend the existing online radar simulation framework to create a closed-loop pipeline for reinforcement learning. You will also train a reinforcement learning agent to optimise sensor modulation parameters under different conditions and driving scenarios. You will perform regression tests and ablation studies to evaluate the performance of the approach. Finally, you will benchmark the cognitive sensing approach against baseline methods in different use cases. Contact & Additional information This location offers Social counselling and intermediary service for care services Discounts for employees