研究者詳細 - 上野　史

LSTM-based Abstraction of Hetero Observation and Transition in Non-Communicative Multi-Agent Reinforcement Learning. 査読

その他リンク： https://dblp.uni-trier.de/db/conf/hci/hci2022-4.html#UwanoYT22

Fumito Uwano

Proceedings of the 14th International Conference on Agents and Artificial Intelligence 172 - 179 2022年2月

Policy-oriented Goal Selection in Multi-Agent Reinforcement Learning for Dynamic Environments without Communication 査読

上野史

Proceedings of 27th International Symposium on Artificial Life and Robotics (AROB 2022) 2022年1月

Table-structure Recognition Method Consisting of Plural Neural Network Modules.

Hiroyuki Aoyagi, Teruhito Kanazawa, Atsuhiro Takasu, Fumito Uwano, Manabu Ohta

Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods(ICPRAM) 542 - 549 2022年

複雑ネットワークに基づく多次元意見共有モデル上の誤報伝搬防止査読

上野史, 北島瑛貴, 高玉圭樹

人工知能学会論文誌 36 ( 6 ) B-KB2_1 - 12 2021年11月

A Cooperative Learning Method for Multi-Agent System with Different Input Resolutions. 査読

Fumito Uwano

4th International Symposium on Agents, Multi-Agent Systems and Robotics(ISAMSR) 84 - 90 2021年9月

Directionality Reinforcement Learning to Operate Multi-Agent System without Communication. 査読

Fumito Uwano, Keiki Takadama

CoRR abs/2110.05773 2021年

多次元意見共有モデル上のシグモイド関数に基づく誤報防止アルゴリズム査読

上野史, 北島瑛貴, 髙玉圭樹

人工知能学会論文誌 36 ( 6 ) 2021年

How to Emote for Consensus Building in Virtual Communication. 査読

Yoshimiki Maekawa, Fumito Uwano, Eiki Kitajima, Keiki Takadama

Human Interface and the Management of Information. Interacting with Information - Thematic Area 194 - 205 2020年7月

Reward Value-Based Goal Selection for Agents’ Cooperative Route Learning Without Communication in Reward and Goal Dynamism 査読

上野史, 髙玉圭樹

SN Computer Science 1 ( 3 ) 182 - 182 2020年5月

Theoretical learning goal selection for non-communicative multi-agent cooperation

Fumito Uwano, Keiki Takadama

IEEJ Transactions on Electronics, Information and Systems 140 ( 1 ) 75 - 84 2020年

記述言語：日本語掲載種別：研究論文（学術雑誌）出版者・発行元：Institute of Electrical Engineers of Japan

This paper extended PMRL as the non-communicative and theoretical method for two agents, and proposed PLA as the method to be able to force agents to learn cooperative behavior for any number of agents. In addition, this paper adds the theoretic explanation for PLA that all agents achieve all purposes without spending the largest times. Concretely PLA forces each agent to avoid the more difficult purposes requiring many time to be reached by limiting the purpose which it can achieve, and it forces the agents to learn cooperative policy as achieving the appropriate purpose among the limited purposes. The experimental results in this paper derive that (1) PLA enables the agents to learn cooperative policy in the two grid world problems for three and five agents, and (2) PLA can force all agents to achieve all purposes in the problems with the minimum time.

DOI： 10.1541/ieejeiss.140.75

How to Design Adaptable Agents to Obtain a Consensus with Omoiyari. 査読

Yoshimiki Maekawa, Fumito Uwano, Eiki Kitajima, Keiki Takadama

Human Interface and the Management of Information. Visual Information and Knowledge Management - Thematic Area 462 - 475 2019年7月

How to Select Appropriate Craters to Estimate Location Accurately in Comprehensive Situations for SLIM Project 査読

上野史, 辰巳嵩豊, 村田暁紀, 髙玉圭樹, 鎌田弘之, 石田貴行, 福田盛介, 澤井秀次郎, 坂井真一郎

Proceedings of the 32nd International Symposium on Space Technology and Science (ISTS) & 9th Nano-Satellite Symposium (NSAT) 2019年6月

Bat Algorithm with Dynamic Niche Radius for Multimodal Optimization 査読

岩瀬拓哉, 高野諒, 上野史, 佐藤寛之, 高玉圭樹

Proceedings of the 3rd International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence (ISMSI 2019) 2019年3月

Maximum Entropy Inverse Reinforcement Learning with Incomplete Experts 査読

長谷川智, 上野史, 髙玉圭樹

Proceedings of the 24th International Symposium on Artificial Life and Robotics 2019年1月

Utilizing Observed Information for No-Communication Multi-agent Reinforcement Learning toward Cooperation in Dynamic Environment 査読

上野史, 髙玉圭樹

SICE Journal of Control, Measurement, and System Integration 2019年

目的制限に基づく通信なしマルチエージェント協調行動学習とその効果の証明査読

上野史, 髙玉圭樹

電気学会論文誌C 140 ( 1 ) 2019年

Niche Radius Adaptation in Bat Algorithm for Locating Multiple Optima in Multimodal Functions. 査読

Takuya Iwase, Ryo Takano, Fumito Uwano, Hiroyuki Sato, Keiki Takadama

IEEE Congress on Evolutionary Computation(CEC) 800 - 807 2019年

Novelty Search-based Bat Algorithm: Adjusting Distance among Solutions for Multimodal Optimization 査読

岩瀬拓哉, 髙野諒, 上野史, 佐藤寛之, 髙玉圭樹

Proceedings of the 22nd Asia Pacific Symposium on Intelligent and Evolutionary Systems 2018年12月

Strategy for Learning Cooperative Behavior with Local Information for Multi-agent Systems 査読

上野史, 髙玉圭樹

Proceedings of The 21st International Conference on Principles and Practice of Multi-Agent Systems 663 - 670 2018年10月

Multiple swarm intelligence methods based on multiple population with sharing best solution for drastic environmental change. 査読

Yuta Umenai, Fumito Uwano, Hiroyuki Sato, Keiki Takadama

Proceedings of the Genetic and Evolutionary Computation Conference Companion 97 - 98 2018年7月

Weighted Opinion Sharing Model for Cutting Link and Changing Information among Agents as Dynamic Environment 査読

上野史, 齋藤嶺, 髙玉圭樹

SICE Journal of Control, Measurement, and System Integration 11 ( 4 ) 331 - 340 2018年7月

Multi-Agent Cooperation Based on Reinforcement Learning with Internal Reward in Maze Problem 査読

上野史, 建部尚樹, 田島友祐, 中田雅也, ティム・コバックス, 髙玉圭樹

SICE Journal of Control, Measurement, and System Integration 11 ( 4 ) 321 - 330 2018年7月

Correcting Wrongly Determined Opinions of Agents in Opinion Sharing Model. 査読

Eiki Kitajima, Caili Zhang, Haruyuki Ishii, Fumito Uwano, Keiki Takadama

Human Interface and the Management of Information. Interaction, Visualization, and Analytics - 20th International Conference 658 - 676 2018年7月

Generalizing rules by random forest-based learning classifier systems for high-dimensional data mining. 査読

Fumito Uwano, Koji Dobashi, Keiki Takadama, Tim Kovacs

Proceedings of the Genetic and Evolutionary Computation Conference Companion 1465 - 1472 2018年7月

How to Detect Essential Craters in Camera Shot Image to Increase the Number of Spacecraft Location Estimation while Improving its Accuracy? 査読

Haruyuki Ishii, Yuta Umenai, Kazuma Matsumoto, Fumito Uwano, Takato Tatsumi, Keiki Takadama, Hiroyuki Kamata, Takayuki Ishida, Seisuke Fukuda, Shujiro Sawai, Shinichiro Sakai

Proceedings of The International Symposium on Artificial Intelligence, Robotics and Automation in Space, i-SAIRAS 2018 2018年6月

Analyzing Triangle Matching Method Based on Craters for Spacecraft Localization 査読

Fumito Uwano, Haruyuki Ishii, Yuta Umenai, Kazuma Matsumoto, Takato Tatsumi, Akinori Murata, Keiki Takadama

Proceedings of The International Symposium on Artificial Intelligence, Robotics and Automation in Space, i-SAIRAS 2018 2018年6月

Ensemble Heart Rate Extraction Method for Biological Data from Water Pressure Sensor 査読

Fumito Uwano, Keiki Takadama

Proceedings of 2018 AAAI Spring Symposium Series 304 - 309 2018年3月

Improving Sleep Stage Estimation Accuracy by Circadian Rhythm Extracted from a Low Frequency Component of Heart Rate

Akari Tobaru, Fumito Uwano, Takuya Iwase, Kazuma Matsumoto, Ryo Takano, Yusuke Tajima, Yuta Umenai, Keiki Takadama

Proceedings of 2018 AAAI Spring Symposium Series 297 - 303 2018年3月

Sleep Stage Estimation Comparing Own Past Heartrate or Others' Heartrate

TAJIMA Yusuke, UWANO Fumito, MURATA Akinori, HARADA Tomohiro, TAKADAMA Keiki

SICE Journal of Control, Measurement, and System Integration 11 ( 1 ) 32‐39(J‐STAGE) 2018年

相似な三角形に基づくクレータマッチングによるSLIM探査機の自己位置推定とその精度向上

石井晴之, 村田暁紀, 上野史, 辰巳嵩豊, 梅内祐太, 高玉圭樹, 原田智広, 鎌田弘之, 石田貴行, 福田盛介, 澤井秀次郎, 坂井真一郎

航空宇宙技術 17 ( 0 ) 69 - 78 2018年

記述言語：日本語出版者・発行元：一般社団法人日本航空宇宙学会

This paper focuses on the Evolutional Triangle Similarity Matching (ETSM) method for estimating spacecraft location in Smart Lander for Investigating Moon (SLIM) mission and improves it by adding the functions of elimination of line symmetric triangles between crater map and camera shot image, comparison of rotation relationship of triangles and triangle formation method using Delaunay triangulation and introducing point group matching as a coordinate calculation function. To evaluate the robustness of the improved method, we conduct simulation experiments using the crater map and camera shot images in six situations. This experiments have revealed the following implications: (1) this method improved accuracy of location estimation within 5.1 pixels by the functions of elimination of line symmetric triangles between crater map and camera shot image, (2) this method slight got worse accuracy at low or high altitude of spacecraft, however, this method successfully reduced incorrect spacecraft location estimation by comparison of rotation relationship of triangles, (3) this method improved accuracy of location estimation by triangle formation method using Delaunay triangulation, but possibility of incorrect spacecraft location estimation is slight increased, and (4) integration method of these three mechanism can estimate spacecraft location within 5 pixels without being affected altitude difference and rotation of camera shot image.

CiNii Article

J-GLOBAL

Ensemble Heart Rate Extraction Method for Biological Data from Water Pressure Sensor. 査読

Fumito Uwano, Keiki Takadama

2018 AAAI Spring Symposia 2018年

Improving Sleep Stage Estimation Accuracy by Circadian Rhythm Extracted from a Low Frequency Component of Heart Rate. 査読

Akari Tobaru, Fumito Uwano, Takuya Iwase, Kazuma Matsumoto, Ryo Takano, Yusuke Tajima, Yuta Umenai, Keiki Takadama

2018 AAAI Spring Symposia 2018年

Strategy for Learning Cooperative Behavior with Local Information for Multi-agent Systems. 査読

Fumito Uwano, Keiki Takadama

PRIMA 2018: Principles and Practice of Multi-Agent Systems - 21st International Conference(PRIMA) 663 - 670 2018年

Recovery System Based on Exploration-Biased Genetic Algorithm for Stuck Rover in Planetary Exploration. 査読

Fumito Uwano, Yusuke Tajima, Akinori Murata, Keiki Takadama

Journal of Robotics and Mechatronics 29 ( 5 ) 877 - 886 2017年10月

記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：Fuji Technology Press

Contributing toward continuous planetary surface exploration by a rover (i.e., a space probe), this paper proposes (1) an adaptive learning mechanism as the software system, based on an exploration-biased genetic algorithm (EGA), which intends to explore several behaviors, and (2) a recovery system as the hardware system, which helps a rover exit stuck areas, a kind of immobilized situation, by testing the explored behaviors. We develop a rover-type space probe, which has a stabilizer with two movable joints like an arm, and learns how to use them by employing EGA. To evaluate the effectiveness of the recovery system based on the EGA, the following two field experiments are conducted with the proposed rover: (i) a small field test, including a stuck area created artificially in a park
and (ii) a large field test, including several stuck areas in Black Rock Desert, USA, as an analog experiment for planetary exploration. The experimental results reveal the following implications: (1) the recovery system based on the EGA enables our rover to exit stuck areas by an appropriate sequence of motions of the two movable joints
and (2) the success rate of getting out of stuck areas is 95% during planetary exploration.

DOI： 10.20965/jrm.2017.p0877

Supporting the Exploration of the Learning Goals for a Continuous Learner Toward Creative Learning. 査読

Takato Okudo, Tomohiro Yamaguchi 0002, Akinori Murata, Takato Tatsumi, Fumito Uwano, Keiki Takadama

Journal of Advanced Computational Intelligence and Intelligent Informatics 21 ( 5 ) 907 - 916 2017年9月

記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：Fuji Technology Press

This paper proposes a learning goal space that visualizes the distribution of the obtained solutions to support the exploration of the learning goals for a learner. Subsequently, we examine the method for assisting a learner to present the novelty of the obtained solution. We conduct a learning experiment using a continuous learning task to identify various solutions. To assign the subjects space to explore the learning goals, several parameters related to the success of the task are not instructed to the subjects. In the comparative experiment, three types of learning feedbacks provided to the subjects are compared. These are presenting the learning goal space with obtained solutions mapped on it, directly presenting the novelty of the obtained solutions mapped on it, and presenting some value that is slightly related to the obtained solution. In the experiments, the subjects to whom the learning goal space or novelty of the obtained solution is shown, continue to identify solutions according to their learning goals until the final stage in the experiment is attained. Therefore, in a continuous learning task, our supporting method of directly or indirectly presenting the novelty of the obtained solution through the learning goal space is effective.

DOI： 10.20965/jaciii.2017.p0907

Comparison Between Reinforcement Learning Methods with Different Goal Selections in Multi-Agent Cooperation. 査読

Fumito Uwano, Keiki Takadama

Journal of Advanced Computational Intelligence and Intelligent Informatics 21 ( 5 ) 917 - 929 2017年9月

記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：Fuji Technology Press

This study discusses important factors for zero communication, multi-agent cooperation by comparing different modified reinforcement learning methods. The two learning methods used for comparison were assigned different goal selections for multi-agent cooperation tasks. The first method is called Profit Minimizing Reinforcement Learning (PMRL)
it forces agents to learn how to reach the farthest goal, and then the agent closest to the goal is directed to the goal. The second method is called Yielding Action Reinforcement Learning (YARL)
it forces agents to learn through a Q-learning process, and if the agents have a conflict, the agent that is closest to the goal learns to reach the next closest goal. To compare the two methods, we designed experiments by adjusting the following maze factors: (1) the location of the start point and goal
(2) the number of agents
and (3) the size of maze. The intensive simulations performed on the maze problem for the agent cooperation task revealed that the two methods successfully enabled the agents to exhibit cooperative behavior, even if the size of the maze and the number of agents change. The PMRL mechanism always enables the agents to learn cooperative behavior, whereas the YARL mechanism makes the agents learn cooperative behavior over a small number of learning iterations. In zero communication, multi-agent cooperation, it is important that only agents that have a conflict cooperate with each other.

DOI： 10.20965/jaciii.2017.p0917

The robust spacecraft location estimation algorithm toward the misdetection crater and the undetected crater in SLIM 査読

Haruyuki Ishii, Keiki Takadama, Akinori Murata, Fumito Uwano, Takato Tatsumi, Yuta Umenai, Kazuma Matsumoto, Hiroyuki Kamata, Takayuki Ishida, Seisuke Fukuda, Shujiro Sawai, Shinichiro Sakai

Proceedings of International Symposium on Space Technology and Science, ISTS 2017 2017年6月

Strategies to Improve Cuckoo Search Toward Adapting Randomly Changing Environment. 査読

Yuta Umenai, Fumito Uwano, Hiroyuki Sato, Keiki Takadama

Advances in Swarm Intelligence - 8th International Conference 10385 573 - 582 2017年

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）出版者・発行元：Springer

Cuckoo Search (CS) is the powerful optimization algorithm and has been researched recently. Cuckoo Search for Dynamic Environment (D-CS) has proposed and tested in dynamic environment with multi-modality and cyclically before. It was clear that has the hold capability and can find the optimal solutions in this environment. Although these experiments only provide the valuable results in this environment, D-CS not fully explored in dynamic environment with other dynamism. We investigate and discuss the find and hold capabilities of D-CS on dynamic environment with randomness. We employed the multi-modal dynamic function with randomness and applied D-CS into this environment. We compared D-CS with CS in terms of getting the better fitness. The experimental result shows the D-CS has the good hold capability on dynamic environment with randomness. Introducing the Local Solution Comparison strategy and Concurrent Solution Generating strategy help to get the hold and find capabilities on dynamic environment with randomness.

DOI： 10.1007/978-3-319-61824-1_62

Communication-Less Cooperative Q-Learning Agents in Maze Problem 査読

Fumito Uwano, Keiki Takadama

INTELLIGENT AND EVOLUTIONARY SYSTEMS, IES 2016 8 453 - 467 2017年

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）出版者・発行元：SPRINGER INT PUBLISHING AG

This paper introduces a reinforcement learning technique with an internal reward for a multi-agent cooperation task. The proposed method is an extension of Q-learning which changes the ordinary (external) reward to the internal reward for agent-cooperation under the condition of no communication. To increase the certainty of the proposed methods, we theoretically investigate what values should be set to select the goal for the cooperation among agents. In order to show the effectiveness of the proposed method, we conduct the intensive simulation on the maze problem for the agent-cooperation task, and confirm the following implications: (1) the proposed method successfully enable agents to acquire cooperative behaviors while a conventional method fails to always acquire such behaviors; (2) the cooperation among agents according to their internal rewards is achieved no communication; and (3) the condition for the cooperation among any number of agent is indicated.

DOI： 10.1007/978-3-319-49049-6_33

Reinforcement Learning with Internal Reward for Multi-Agent Cooperation: A Theoretical Approach. 査読

Adaptive Learning Based on Genetic Algorithm for Rover in Planetary Exploration 査読

Fumito Uwano, Akinori Murata, Keiki Takadama

Proceedings of The International Symposium on Artificial Intelligence, Robotics and Automation in Space, i-SAIRAS 2016 2016年6月

Fumito Uwano, Naoki Tatebe, Masaya Nakata, Keiki Takadama, Tim Kovacs

EAI Endorsed Transactions on Collaborative Computing 2 ( 8 ) e2 - 2 2016年5月

記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：Association for Computing Machinery, Inc

This paper focuses on a multi-Agent cooperation which is generally difficult to be achieved without sufficient information of other agents, and proposes the reinforcement learning method that introduces an internal reward for a multi-Agent cooperation without sufficient information. To guarantee to achieve such a cooperation, this paper theoretically derives the condition of selecting appropriate actions by changing internal rewards given to the agents, and extends the reinforcement learning methods (Q-learning and Profit Sharing) to enable the agents to acquire the appropriate Q-values up- dated according to the derived condition. Concretely, the internal rewards change when the agents can only find better solution than the current one. The intensive simulations on the maze problems as one of test beds have revealed the following implications:(1) our proposed method successfully enables the agents to select their own appropriate cooperating actions which contribute to acquiring the minimum steps towards to their goals, while the conventional methods (i.e., Q-learning and Profit Sharing) cannot always acquire the minimum steps
and (2) the proposed method based on Profit Sharing provides the same good performance as the proposed method based on Q-learning.

DOI： 10.4108/eai.3-12-2015.2262878

Real-Time Sleep Stage Estimation from Biological Data with Trigonometric Function Regression Model. 査読

Tomohiro Harada, Fumito Uwano, Takahiro Komine, Yusuke Tajima, Takahiro Kawashima, Morito Morishima, Keiki Takadama

2016 AAAI Spring Symposia 2016年

A modified cuckoo search algorithm for dynamic optimization problems. 査読

Yuta Umenai, Fumito Uwano, Yusuke Tajima, Masaya Nakata, Hiroyuki Sato, Keiki Takadama

IEEE Congress on Evolutionary Computation(CEC) 1757 - 1764 2016年

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）出版者・発行元：IEEE

This paper proposes a simple modification of the Cuckoo Search called CS for a dynamic environment. In this paper, we consider a dynamic optimization problem where the global optimum can be cyclically changed depending on time. Our modified CS algorithm holds good candidates in order to effectively explore the search space near those candidates with an intensive local search. Our first experiment tests the prosed method on a set of static optimization problems, which aims at evaluating the potential performance of the proposed method. Then, we apply it to a dynamic optimization problem. Experimental results on the static problems show that the proposed method derives a better performance than the conventional method, which suggest the proposed method potentially has a good capability of finding a good solution. On the dynamic problem, the proposed method also performs well while the conventional method fails to find a better solution.

DOI： 10.1109/CEC.2016.7744001