In English

Local short path generation for autonomous commercial vehicles

Viktor Hellaeus ; Yaowen Xu
Göteborg : Chalmers tekniska högskola, 2017. Diploma work - Department of Applied Mechanics, Chalmers University of Technology, Göteborg, Sweden, ISSN 1652-8557; 2017:53, 2017.
[Examensarbete på avancerad nivå]

In recent years, breakthroughs in arti cial intelligence (AI) have drawn the attention to the subject from many elds including the automotive industry, where it could become a cornerstone in order to develop fully autonomous vehicles. In the automotive industry the applications for these AI-techniques varies from classi cation of a vehicle's surroundings to behavioral-re ex approaches that mimics human behaviour. In this master thesis, the capability to navigate a truck in mining environments using neural networks has been investigated, tested and veri ed in a simulated 3D environment. As input to the neural networks, Light Detection And Ranging (LIDAR) sensors in di erent con gurations has been used. The main focus has been to create an algorithm that can create short paths at a high rate using limited computational power. Consequently, the networks has been tried on Raspberry Pi to prove their capability. Several approaches are proposed using both 2D LIDARs as well as 3D LIDARs. The developed networks are simple, does not require high performance computational units and are able to make decisions at intersections according to a global planner. Apart from the developed networks, a tool-chain for collection of training data, network training and testing in simulated environment is described in detail in the report.

Nyckelord: neural network, autonomous vehicles, short path generation, decision making, end-to-end learning,

Publikationen registrerades 2017-07-04.

CPL ID: 250464

Detta är en tjänst från Chalmers bibliotek