VTechWorks staff will be away for the winter holidays starting Tuesday, December 24, 2024, through Wednesday, January 1, 2025, and will not be replying to requests during this time. Thank you for your patience, and happy holidays!
 

EASE-E: Edge-AI based System for Energy-Efficiency in Autonomous Driving (ADAS/AD)

Simple item page
dc.contributor.authorKothari, Aadi Jayen
dc.contributor.committeechairTalty, Timothy Josephen
dc.contributor.committeememberZeng, Haiboen
dc.contributor.committeememberHuxtable, Scott T.en
dc.contributor.departmentElectrical and Computer Engineeringen
dc.date.accessioned2024-12-17T09:00:20Zen
dc.date.available2024-12-17T09:00:20Zen
dc.date.issued2024-12-16en
dc.description.abstractThe rise of Software-Defined Vehicles (SDVs) has rapidly advanced the development of Advanced Driver Assistance Systems (ADAS) and Autonomous Vehicle (AV) technology. However, as compute and sensing architectures for SAE Level 2 vehicles increasingly lean towards fully centralized systems, significant concerns arise regarding their energy demands. This shift may have a negative impact on one of the most critical purchasing factors for Battery Electric Vehicles (BEVs): electric driving range. This thesis investigates the potential benefits of decentralization in automotive Electrical/Electronic (E/E) architecture, powered by System-on-Module (SoM) Edge-AI boards. By facilitating efficient deep learning processing locally, the proposed EASE-E (Edge-AI based System for Energy Efficiency) solution achieves up to a 5x reduction in power consumption while maintaining high processing performance. Through a combination of bench testing and Software-in-the-Loop (SiL) simulations, this research demonstrates that EASE-E enhances energy efficiency by 32.8% in highway driving, and 10.8% in urban environments. EASE-E also offers greater scalability and resilience when compared to the existing E/E architectures: distributed, domain, and zonal. The findings underscore the potential of this solution to preserve and extend the driving range of BEVs, presenting a compelling alternative to a fully centralized approach. These insights are crucial for the future design of scalable, energy efficient, and autonomous software-defined vehicles.en
dc.description.abstractgeneralIn today's automotive world, electric vehicles are becoming more intelligent by relying heavily on software for their operations. These vehicles handle advanced driving tasks with some human oversight, but these features use a lot of energy, reducing the car's driving range. The driving range is one of the most important factors for consumers when deciding to buy electric cars, as they often have a lesser range than their gasoline counterparts. While most fully autonomous vehicles, like "self-driving" robotaxis, may benefit from using a single computer to drive autonomy, this may not work for consumer cars that driven under the supervision of the driver. This research uses AI to process information from multiple sensors on smaller, more efficient processors, reducing the strain on the main computer and saving energy. We explore a new design for vehicle electronics that reduces energy use, helping electric vehicles go farther on each charge. Through computer simulations and real-world testing, we compare this new design to the current standard and show how using smaller, more efficient processors can save significant amounts of energy. As a result, electric cars can go farther on a single charge, making them more practical and appealing for everyday use. This also supports a greener environment by promoting energy-efficient transportation.en
dc.description.degreeMaster of Scienceen
dc.format.mediumETDen
dc.identifier.othervt_gsexam:41962en
dc.identifier.urihttps://hdl.handle.net/10919/123815en
dc.language.isoenen
dc.publisherVirginia Techen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectE/E Architectureen
dc.subjectDeep Learningen
dc.subjectADASen
dc.titleEASE-E: Edge-AI based System for Energy-Efficiency in Autonomous Driving (ADAS/AD)en
dc.typeThesisen
thesis.degree.disciplineComputer Engineeringen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.levelmastersen
thesis.degree.nameMaster of Scienceen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Kothari_AJ_T_2024.pdf
Size:
5.84 MB
Format:
Adobe Portable Document Format
Download

Collections

Masters Theses