Personalized Software in Heavy-Duty Vehicles - Exploring the Feasibility of Self-Adapting Smart Cruise Control Using Machine Learning

Abstract This study aims to explore possible and feasible ways to personalize driving functions for heavy-duty vehicles. The idea is to use machine learning algorithms, specifically ocusing on Long Short-Term Memory (LSTM) neural networks and traditional classification algorithms for current state velocity predictions, independent velocity predictions, and driver classification. The goal is to explore potential approaches for enhancing the existing software to improve the vehicle’s drivability while not compromising fuel consumption. The research methodology involved collecting relevant data from the heavy-duty vehicle, including various readings using the CAN us and map-based data. The data was preprocessed and used to train and evaluate the LSTM neural network and traditional classification algorithms. The results obtained were satisfactory for all of the models. The predictions from the LSTM models were adequate. The one-second velocity predictions were favorable when compared to the ten-second velocity predictions. From the training progress, it is possible to see that the model learns and identified trends. Furthermore, the classification accuracy using traditional and LSTM classifiers ranged from 93 % to 99 %. These findings highlight the challenges and limitations of employing LSTM neural networks and traditional classification algorithms for software adaptation. Further research is necessary to explore alternative approaches, such as using sufficient and more suitable data for transfer- and deep learning. The insights gained from this study help comprehend machine learning applications in heavy-duty vehicles and suggest future research efforts to enhance software adaptation and thus improve vehicle performance.

Department dc:contributor.department

Chalmers tekniska högskola / Institutionen för elektroteknik

Year dc:date.issued

2023

Authors dc:creator

• Matsson, Alex
• De Geer, Charlotte

Advisor dc:contributor.supervisor

• Karlsson, Robin

• Long Short-Term Memory, LSTM, classification, driver behavior, adapt ability, machine learning, ML, neural network, time series.

Language dc:language.iso

eng

Handle dc:identifier.uri

https://hdl.handle.net/20.500.12380/306715

OAI record oai:identifier

https://odr.chalmers.se/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Aodr.chalmers.se%3A20.500.12380%2F306715