Automotive Research
header foto

AUTOCAN-ID successfully complete

KIEM AUTOCAN-ID was initiated at the beginning of 2020 together with partners V-TRON and SD-Insights. Two students Arvind and Yashvanth together with colleagues from HAN, V-Tron and SD-Insights explored different approaches to the problem and successfully defended their research during mid-December 2020. 

Cooperative mobility relies majorly on big data that is generated potentially by millions of vehicles that are travelling on the road. But how can this data be generated? Modern vehicles already contain a host of sensors that are required for its operation. This data is typically circulated within an automobile via the CAN bus and can in-principle be shared with the outside world considering the privacy aspects of data sharing. The main problem is, however, the difficulty in interpreting this data. This is mainly because the configuration of this data varies between manufacturers and vehicle models and have not been standardized by the manufacturers. Signals from the CAN bus could be manually reverse engineered, but this process is extremely labour-intensive and time-consuming. AUTOCAN-ID set out to investigate if an intelligent tool could be developed to extract CAN messages and their composition efficiently irrespective of vehicle brand and type. The developed tool aims at reducing costs and time required for business that intend to use vehicle data for their applications.

Yashvanth, on one hand, was tasked to develop a tool using Machine Learning techniques. Yashvanth deployed LSTM networks together with a unified testing/data collection procedure to automatically reverse-engineer all the 6 CAN signals (Vehicle speed, throttle position, yaw rate, lateral acceleration, brake status and steering angle). Yashvanth received an 8.6 for his thesis.  

Arvind, on the other hand, was tasked to research into methods that do not employ Machine Learning for the development of the tool. Arvind also developed unified testing/data collection procedures for the six variables of interest and employed a data-change algorithm. Arvind scored a 7 in his thesis.