Georgia Institute of Technology
Development and Implementation of an Adaptive Cruise Control Feature in a Consumer Vehicle
Abstract
dc:description.abstractThis thesis covers work to develop and implement an Adaptive Cruise Control (ACC) feature in a consumer vehicle. More specifically, the development of a perception system and vehicle controller enabling automated control over a vehicle’s longitudinal motion will be discussed. The ACC feature is able to follow other vehicles while maintaining a safe following distance or to maintain a user-set velocity in the absence of a lead vehicle. This research is driven by a larger competition, the EcoCAR Mobility Challenge, sponsored by the U.S. Department of Energy, General Motors (GM), and Mathworks. The competition tasks teams with integrating a hybrid drivetrain and developing Connected and Autonomous Vehicle (CAVs) technology to improve energy efficiency, rider comfort, and safety in a 2019 Chevy Blazer. This research leveraged off-the-shelf industry grade tools, sensors, and actuators including MATLAB’s Automated Driving and Sensor Fusion and Tracking Toolboxes, the Robot Operating System (ROS), a Mobileye camera unit, a Bosch radar sensor, and electric machines from Denso and Magna. The problems were modeled in a software environment and then deployed in the road vehicle to evaluate and tune performance. These features will be evaluated by the competition in a final event in May 2022 at a GM proving grounds facility.
Degree
thesis:*- Level thesis:degree_level
- Masters
- Department dc:contributor.department
- Electrical and Computer Engineering
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2022
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Hummel, Nicholas William
- Advisor dc:contributor.advisor
-
- Taylor, David G.
- Committee members dc:contributor.committeemember
-
- Coogan, Samuel
- Wardi, Yorai
Subjects
dc:subject × 3Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- http://hdl.handle.net/1853/66656