2016 Fiscal Year Research-status Report
簡潔な・利用しやすい構造を有する学習ネットワークの構成と応用に関する研究
| Project/Area Number |
15K18095
|
|---|
| Research Institution | Waseda University |
|---|
Principal Investigator |
Parque Victor 早稲田大学, 理工学術院, 助教授 (50745221)
|
|---|
| Project Period (FY) |
2015-04-01 – 2019-03-31
|
| Keywords | succinctness / modularity / computer-aided design / path planning / graph representation |
|---|
| Outline of Annual Research Achievements |
In 2016, the algorithmic foundations and application benchmarks for Genetic Counterfactual Programming (GCP) in computer-aided design and robotics were further developed: (1) a new method for solving modular combinatorial problems under succinct representation schemes, enabling the optimal formation of modules, the organization of functional units in networks, and the algorithmic foundations for modular Genetic Counterfactual Programming (2) the succinct representation of both directed and undirected graphs with self-loops, enabling the development of canonical learning algorithms for networks with self-loop structures, and the use of succinct representation of GCP with self-loops (3) the extension of our benchmarks for the design of unique and high-performing vehicle layouts under large-scale historical data using the state of the art gradient-free optimization algorithms, (4) the new methods for route bundling, enabling the path planning and algorithmic benchmarks in robotics where transport resource is scarce or navigable space is constrained, and (5) a new method for path planning using log-aesthetic curves, enabling the safe, flexible and energy-efficient path planning schemes and algorithmic benchmarks in robotics.
|
| Current Status of Research Progress |
Current Status of Research Progress
1: Research has progressed more than it was originally planned.
Reason
The algorithmic foundations and application benchmarks for Genetic Counterfactual Programming in design and robotics problems were further developed.
|
| Strategy for Future Research Activity |
In 2017, while gaining awareness and insights toward the deployment in real world systems, research on the applications of Genetic Counterfactual Programming are to be conducted: (1) Research on the application of Genetic Counterfactual Programming in robot control, and (2) Research on the application of Genetic Counterfactual Programming in computer-aided design.
|
| Causes of Carryover |
The reasons for Incurring Amount to be Used Next Fiscal Year are as follows: (1) the acquisition of a computer suitable for sophisticated numerical computations was postponed to the consecutive year, since the existing hardware at Waseda University satisfies the computational loads to current date, and (2) publication in a zero-cost journal was achieved, resulting in cost savings in journal publication.
|
| Expenditure Plan for Carryover Budget |
It is expected that the amount to be used in the next fiscal year is split among the travel costs and registration fees of conferences attended during 2017, the costs for acquiring a computer suitable for sophisticated numerical computations, the costs for acquiring relevant books and the costs for publishing at relevant journals venues.
|
