DeMaMech: EU-Japan Collaboration in Higher Education Student Exchange Program

Offer of Research Topic

Offer from	University	Hokkaido University
	Faculty/Department/Institute	Division of Systems Science and Informatics, Graduate School of Information Sciences and Technology
	Group Name	Laboratory of Hybrid Systems
Research Theme		Realization of Reinforcement Learning Using FPGA
Brief Explanation		FPGA(Field Programmable Gate Array) is an LSI including gate circuits which can be generated by software called HDL(Hardware Description Language). In this study, FPGAs for reinforcement-learning based control of an autonomous miniature car will be designed using HDL.
Research Steps		1. Study of HDL and Reinforcement Learning (two months) 2. Development of HDL (two months) 3. Evaluation of the design in comparison with fuzzy-based control (one month)
Period		5 months, but can be extended as a 10-month project, by including hardware experiments.
Necessary Background, Knowledge, Skills		Computer programming skills. It is preferable to have knowledge on logic circuits. If necessary, some references can be specified.
Further Information		http://hbd.ist.hokudai.ac.jp/
Contact Person		Prof. Dr. Hajime Igarashi (igarashi@ssi.ist.hokudai.ac.jp)