Decision making under uncertainty is exceptionally computationally demanding. Since the robot has to decide online the best action, a typical approach is to approximate the decisionmaking mechanism. In this project, we will harness the capabilities of the bleeding edge scientific language JULIA alongside NVIDIA CUDA to move computations to GPU.
By massive parallelization, we hope to solve the decision making problem precisely.
Andrey Zhitnikov (Tel. 0547658690) firstname.lastname@example.org
Assoc. Prof. Vadim Indelman, email@example.com
In this project we shall use deep learning for autonomous navigation and perception. Specific project objectives will be determined together with the student(s).
In this project we shall use deep learning for robot localization. Specific project objectives will be determined together with the student(s).