Dela med andra

Artificial Intelligence: Decision Making

Publicerad 2018-10-08

Om uppdragsgivaren
The Volvo Group is one of the world’s leading manufacturers of trucks, buses, construction equipment and marine and industrial engines under the leading brands Volvo, Renault Trucks, Mack, UD Trucks, Eicher, SDLG, Terex Trucks, Prevost, Nova Bus, UD Bus, Sunwin Bus and Volvo Penta.
Volvo CE develops and manufactures construction machinery. We are one of the biggest in the business, and have a leading position in technology.

Beskrivning av examensarbetet
Background of thesis work
Department Emerging Technologies at Volvo Construction Equipment is responsible for introducing future technologies internally, via research projects and demonstrators.
We believe that a very important feature when building autonomous machines for construction is to handle the decision making process. To take decisions by artificial intelligence SW is a pretty well defined research area, but we want to focus on our typical automated work tasks, and how to handle the decision process when productivity, robustness, traceability and capability to solve typical dynamic construction situations is at focus.
Suitable background
Computational engineer at master level, or equivalent education profile, with specific interest in AI and programming.

Description of thesis work
We will create a use-case for an autonomous machine in construction, and based on this develop a novel decision-making function. Our plan is to implement the function in levels. First level may be considered as a state machine with the operations for filling a truck with gravel. Second level may be considered dynamic situations that hinder the execution of this state machine, like an obstacle on the path to travel. Third level may be considered lack of space to avoid the hinder. We see this as a cascade of dynamic situations that depends hierarchal on each other’s, and therefore need to be solved with a strategy that handles this. We will in the thesis implement at least 3 levels of dynamic decision making. The thesis work will on a high level consist of:
• Defining a use-case scenario with an autonomous machine
• State-of-art in decision making investigation
• Defining a state-machine leveled approach, where dynamic situations are treated as interrupts of regular work task, and handled in a lower level parallel state-machine
• Implementation of the decision making function for the use-case
• Verification, evaluation, and demonstration of implemented work
• Written report
The thesis work is for 1-2 students, takes place at Volvo CE’s facilities in Eskilstuna, and is paid according to Volvo’s standard routines.

Thesis Level: Master level

Language: Swedish or English
Starting date: January/February 2019 and ending before the summer vacation
Number of students: 1-2
Tutor: Torbjörn Martinsson, Research Engineer

Torbjörn Martinsson
Emerging Technologies, Dept. 77440
Telephone: +46-16-541 43 31

Torbjörn Martinsson


Volvo CE


Sista ansökningdag

2019, vårtermin

Bookmark and Share