Friday, March 03, 2023
Decision Factors for Offloading Automated Driving Functions to Cloud via 6G
Background and Goal of the Thesis
Cloud- and edge-based computing in the context of automated driving promises to support, enhance, as well as completely replace intelligent driving functions of automated vehicles. Next-generation communication technologies like 5G and beyond enable completely new use cases such as offloading functions from the vehicle to connected (edge-)cloud servers.
Offloading intelligent driving functions to a connected (edge-)cloud server promises to reduce vehicle power consumption, gives access to more compute, and potentially increases the vehicle hardware upgrade cycle.
The goal of this thesis is to design and possibly implement a decision process determining under which circumstances which functions are qualified to be offloaded to a connected (edge-)cloud server. To this end, suitable functions should be identified and decision criteria based on relevant properties of the current vehicle state should be derived. The decision process should also include an assessment of when to return offloaded functions back to the vehicle.
You will have access to ika’s extensive hardware and software infrastructure, including research vehicles, high-performance computers, simulation environments, and deep learning-frameworks. Additionally, you can expect close supervision and collaboration with other highly motivated researchers.
Working Points
- Literature research on function offloading in the domain of automated driving and robotics in general
- Identification of intelligent driving functions suitable for offloading, based on literature research and experience with ika’s existing driving functions
- Derivation of decision criteria, based on literature research and experience with ika’s existing driving functions
- Design of a decision process determining under which circumstances which functions are qualified to be offloaded
- (optional) Implementation and evaluation of the designed decision process using ika’s research vehicle and high-performance cloud servers
Requirements
- Reliability, commitment, and enjoyment of working independently
- Enthusiasm for cutting-edge automated driving research
- Logical and structured thinking and problem-solving
- Nice-to-have experience
- C++
- ROS
Note: Please attach brief resume and grade summary.
Contact
Lennart Reiher M.Sc.
+49 241 80 25614
Email
Type of work
Bachelorarbeit, Masterarbeit
Start
at the earliest possible date
Prior knowledge
C++, ROS
Language
Deutsch, Englisch
Research area
Fahrzeugintelligenz & Automatisiertes Fahren