Updated on 2022/11/29

写真a

 
YAMAUCHI, Tomoki
 
Scopus Paper Info  
Paper Count: 0  Citation Count: 0  h-index: 1

Citation count denotes the number of citations in papers published for a particular year.

Affiliation
Faculty of Science and Engineering, School of Fundamental Science and Engineering
Job title
Research Associate
Profile

Tomoki Yamauchi is a doctoral student at the Department of Computer Science and Communications Engineering, Waseda University, Japan, since April 2020, and a research associate at the Department of Computer Science and Engineering, Waseda University, Japan, since April 2021. He received his B.S. and M.S. degrees in Engineering, 2019 and 2020 (one-year grade-skipping with excellent grades), respectively, and a certificate of completion in a minor in mathematical sciences, 2019, from Waseda University. His research interests include multi-agent systems and distributed artificial intelligence. He is a member of the Information Processing Society of Japan (IPSJ) and the Japanese Society of Artificial Intelligence (JSAI).

Education

  • 2020.04
    -
    Now

    Waseda University   Graduate School of Fundamental Science and Engineering   Computer Science and Communications Engineering(Doctor)  

  • 2019.04
    -
    2020.03

    Waseda University   Graduate School of Fundamental Science and Engineering   Computer Science and Communications Engineering(Master)  

    one-year grade-skipping with excellent grades

  • 2015.04
    -
    2019.03

    Waseda University   School of Fundamental Science and Engineering   Computer Science and Engineering(Minor in Mathematical Sciences)  

    Completion in a minor in mathematical sciences

Degree

  • 2020.03   Waseda University   Master of Engineering

  • 2019.03   Waseda University   Bachelor of Engineering

 

Research Areas

  • Intelligent informatics   Artificial Intelligence, Multi-agent systems, Cooperation and coordination

Research Interests

  • Artificial Intelligence

  • Multi-Agent Systems

  • Elevator Group Control System

  • Multi-Agent Pickup and Delivery Problem

  • Multi-Agent Path-Finding Problem

  • Decentralized Robot Path Planning Problem

  • Stock Price Prediction

▼display all

Papers

  • Efficient Path and Action Planning Method for Multi-Agent Pickup and Delivery Tasks under Environmental Constraints

    Tomoki Yamauchi, Yuki Miyashita, Toshiharu Sugawara

    SN Computer Science    2023  [Refereed]  [International journal]

    Authorship:Lead author

     View Summary

    (in press)

  • Task Selection Algorithm for Multi-Agent Pickup and Delivery with Time Synchronization

    Tomoki Yamauchi, Yuki Miyashita, Toshiharu Sugawara

    PRIMA 2022: Principles and Practice of Multi-Agent Systems (Proceedings of the 24th International Conference on Principles and Practice of Multi-Agent Systems, PRIMA 2022)   13753   458 - 474  2022.11  [Refereed]  [International journal]

    Authorship:Lead author

     View Summary

    In this paper, we formulate the material transportation problem as a multi-agent pickup and delivery with time synchronization (MAPD-TS) problem, which is an extension of the well-known multi-agent pickup and delivery (MAPD) problem. In MAPD-TS, we consider the synchronization of the movement of transportation agents with that of external agents, such as trucks arriving and departing from time to time in a warehouse and elevators that transfer materials to and from different floors in a construction site. We then propose methods via which agents autonomously select the tasks for improving overall efficiency by reducing unnecessary waiting times. MAPD is an abstract formation of material transportation tasks, and a number of methods have been proposed only for efficiency and collision-free movement in closed systems. However, as warehouses and construction sites are not isolated closed systems, transportation agents must sometimes synchronize with external agents to achieve real efficiency, and our MAPD-TS is the abstract form of this situation. In our proposed methods for MAPD-TS, agents approximately estimate their arrival time at the carry-in/out port connected with external agents and autonomously select the task to perform next for improved synchronization. Thereafter, we evaluate the performance of our methods by comparing them with the baseline algorithms. We demonstrate that our proposed algorithms reduce the waiting times of both agents and external agents and thus could improve overall efficiency.

    DOI

  • Deadlock-Free Method for Multi-Agent Pickup and Delivery Problem Using Priority Inheritance with Temporary Priority

    Yukita Fujitani, Tomoki Yamauchi, Yuki Miyashita, Toshiharu Sugawara

    Procedia Computer Science (Proceedings of 26th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2022)   207   1552 - 1561  2022.09  [Refereed]  [International journal]

     View Summary

    This paper proposes a control method for the multi-agent pickup and delivery problem (MAPD problem) by extending the priority inheritance with backtracking (PIBT) method to make it applicable to more general environments. PIBT is an effective algorithm that introduces a priority to each agent, and at each timestep, the agents, in descending order of priority, decide their next neighboring locations in the next timestep through communications only with the local agents. Unfortunately, PIBT is only applicable to environments that are modeled as a bi-connected area, and if it contains dead-ends, such as tree-shaped paths, PIBT may cause deadlocks. However, in the real-world environment, there are many dead-end paths to locations such as the shelves where materials are stored as well as loading/unloading locations to transportation trucks. Our proposed method enables MAPD tasks to be performed in environments with some tree-shaped paths without deadlock while preserving the PIBT feature; it does this by allowing the agents to have temporary priorities and restricting agents' movements in the trees. First, we demonstrate that agents can always reach their delivery without deadlock. Our experiments indicate that the proposed method is very efficient, even in environments where PIBT is not applicable, by comparing them with those obtained using the well-known token passing method as a baseline.

    DOI

  • Distributed and Asynchronous Planning and Execution for Multi-agent Systems through Short-Sighted Conflict Resolution

    Yuki Miyashita, Tomoki Yamauchi, Toshiharu Sugawara

    Proceedings of 2021 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC 2022)     14 - 23  2022.06  [Refereed]  [International journal]

     View Summary

    We propose a distributed method for a multi-agent pick-up and delivery problem with fluctuations in agent movement speeds while agents perform planning, detect and resolve conflicts (collisions) between the plans, and execute actions in the plans in a distributed manner. Our study assumes that the robot's movement speed can fluctuate, owing to various factors, thus delaying their scheduled tasks. Such delays can rapidly cause other agent conflicts to cascade and render long-term plans useless. Our proposed method allows each agent's plans to be executed and modified using an advanced short-sighted conflict resolution mechanism. Hence, although an agent attempts to follow its given sequence of actions, it performs each one after carefully checking for any conflict in the next few steps. Our method is fully distributed and works effectively, even when the number of task endpoints, which are the pick-up and delivery locations, is small and the agents are concentrated. We experimentally confirm that our method works efficiently without collisions in environments having agent speed fluctuations and deadlocks using example problems from robot movement in a construction site. Further, we compare the performance of our method with that of the baseline method.

    DOI

    Scopus

  • Standby-Based Deadlock Avoidance Method for Multi-Agent Pickup and Delivery Tasks

    Tomoki Yamauchi, Yuki Miyashita, Toshiharu Sugawara

    Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2022)     1427 - 1435  2022.05  [Refereed]  [International journal]

    Authorship:Lead author

     View Summary

    The multi-agent pickup and delivery (MAPD) problem, in which multiple agents iteratively carry materials without collisions, has received significant attention. However, many conventional MAPD algorithms assume a specifically designed grid-like environment, such as an automated warehouse. Therefore, they have many pickup and delivery locations where agents can stay for a lengthy period, as well as plentiful detours to avoid collisions owing to the freedom of movement in a grid. By contrast, because a maze-like environment such as a search-and-rescue or construction site has fewer pickup/delivery locations and their numbers may be unbalanced, many agents concentrate on such locations resulting in inefficient operations, often becoming stuck or deadlocked. Thus, to improve the transportation efficiency even in a maze-like restricted environment, we propose a deadlock avoidance method, called standby-based deadlock avoidance (SBDA). SBDA uses standby nodes determined in real-time using the articulation-point-finding algorithm, and the agent is guaranteed to stay there for a finite amount of time. We demonstrated that our proposed method outperforms a conventional approach. We also analyzed how the parameters used for selecting standby nodes affect the performance.

    DOI

  • 一時的な優先度と退避を用いた効率的なマルチエージェント配送

    藤谷 雪北, 山内 智貴, 宮下 裕貴, 菅原 俊治

    情報処理学会論文誌トランザクション:数理モデル化と応用 (TOM)   15 ( 4 ) 1 - 12  2022  [Refereed]  [Domestic journal]

     View Summary

    (in press)

  • Path and Action Planning in Non-uniform Environments for Multi-agent Pickup and Delivery Tasks

    Tomoki Yamauchi, Yuki Miyashita, Toshiharu Sugawara

    Proceedings of the 18th European Conference on Multi-Agent Systems (EUMAS 2021); Revised and Selected Papers   12802 LNAI   37 - 54  2021.07  [Refereed]  [International journal]

    Authorship:Lead author

     View Summary

    Although the multi-agent pickup and delivery (MAPD) problem, wherein multiple agents iteratively carry materials from some storage areas to the respective destinations without colliding, has received considerable attention, conventional MAPD algorithms use simplified, uniform models without considering constraints, by assuming specially designed environments. Thus, such conventional algorithms are not applicable to some realistic applications wherein agents have to move in a more complicated and restricted environment; for example, in a rescue or a construction site, their paths and orientations are strictly restricted owing to the path width, and the sizes of agents and materials they carry. Therefore, we first formulate an N-MAPD problem, which is an extension of the MAPD problem for a non-uniform environment. We then propose an N-MAPD algorithm, the path and action planning with orientation (PAPO), to effectively generate collision-free paths meeting the environmental constraints. The PAPO is an algorithm that considers not only the direction of movement but also the orientation of agents as well as the cost and timing of rotations in our N-MAPD formulation by considering the agent and material sizes, node sizes, and path widths. We experimentally evaluated the performance of the PAPO using our simulated environments and demonstrated that it could efficiently generate not optimal but acceptable paths for non-uniform environments.

    DOI

    Scopus

    2
    Citation
    (Scopus)
  • Fair and Effective Elevator Car Dispatching Method for Elevator Group Control System Using Noisy Information from Cameras

    Tomoki Yamauchi, Rina Ide, Toshiharu Sugawara

      J103-D ( 11 ) 776 - 787  2020.11  [Refereed]  [Domestic journal]

    Authorship:Lead author

    DOI

  • Fair and Effective Elevator Car Dispatching Method in Elevator Group Control System using Cameras

    Tomoki Yamauchi, Rina Ide, Toshiharu Sugawara

    Procedia Computer Science (Proceedings of 23rd International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2019)   159   455 - 464  2019.09  [Refereed]  [International journal]

    Authorship:Lead author

     View Summary

    We propose a control method for an elevator group control system to allocate elevator cars for all types of passengers, including general passengers and special passengers who are likely to be unfairly treated (e.g., with strollers, wheelchairs, or bulky luggage), in order to achieve fair waiting times as well as efficient transportation. Elevators are necessary for people to move vertically within high-rise buildings. Since the number of elevator cars is fixed, they have to be carefully controlled for effective dispatch. Furthermore, due to the limited capacities of elevator cars, some special passengers who require more space are often forced to wait much longer than general passengers for cars with sufficient empty space to arrive. These days, as cameras and other sensors that monitor the environment have become more common, and thanks to the recent advances in computer vision technologies, we can estimate the number of waiting passengers and the size of their belongings in elevator halls. By using such information gathered from muliple agents that monitor a specific elevator car or elevator hall, the proposed control enables effective dispatch for shorter and fairer waiting times. Experimental results using the simulated elevator control showed that our method could make waiting times fairer and achieved total efficiency to carry passengers. We discuss the reasons for the improvement as well as the limitation of our method.

    DOI

    Scopus

    1
    Citation
    (Scopus)
  • カメラを用いたエレベータ群管理システムにおける優先対象者モデルの提案と検証

    山内智貴, 菅原俊治

    エージェント合同シンポジウム (JAWS2018)予稿集     1 - 7  2018.09  [Refereed]  [Domestic journal]

    Authorship:Lead author

▼display all

Misc

  • 時間同期を伴うマルチエージェント搬送問題のための自律的なタスク選択アルゴリズムの提案

    山内智貴, 宮下裕貴, 菅原俊治

    信学技報   122 ( 186 ) 42 - 47  2022.09

    Authorship:Lead author

    Research paper, summary (national, other academic conference)  

     View Summary

    本研究ではmulti-agent pickup and delivery(MAPD)の拡張であるMAPD with time synchronization(MAPD-TS)問題を定式化する. MAPD-TSでは輸送エージェントの動きと,建設現場の異なるフロア間に資材を輸送するエレベータなどの外部エージェントの動きの同期を考慮した. 次に,不要な待ち時間を削減して全体効率を向上するため,エージェントによる自律的なタスク選択手法を提案する. MAPDは資材輸送などの応用の抽象化であり,それのみを考慮した閉じたシステムにおける効率化と衝突のない移動を目的とした研究が数多くある. しかし,建設現場などは孤立した閉じたシステムではないため,真の効率化達成にはエージェントは時に外部エージェントと同期しなければならず,MAPD-TSはこの状況の抽象化である. MAPD-TSのための提案手法では,エージェントは同期性向上のため,外部エージェントと接続された搬入出ポートへの到着時刻を近似的に推定し,次のタスクを選択する. 従来手法との比較により,提案手法がエージェントと外部エージェント両方の待ち時間を削減して,全体効率を改善できることを示す.

  • 暫時的な優先度を導入したPIBT手法の拡張

    藤谷 雪北, 山内 智貴, 宮下 裕貴, 菅原 俊治

    研究報告バイオ情報学(BIO)   2022-BIO-70 ( 14 ) 1 - 6  2022.06

    Research paper, summary (national, other academic conference)  

     View Summary

    本研究では,MAPD 問題の制御手法である Priority Inheritance with BackTracking (PIBT) に暫時的な優先度を導入した拡張 PIBT を提案し,PIBT の基本的な性質を変えることなく適用環境の制約を緩めることで適用範囲を拡大すると共に,実験的にその効果を示す.PIBT 手法はステップことに優先度を計算し,その優先度の高いエージェントから順番に,次のステップでの移動先を確定させるアルゴリズムである.このアルゴリズムでは,行き止まりや袋小路のような形状を含むマップでは行き詰まり (デッドロック) が発生するため,環境にその発生を防ぐ制約を設けている.そこで本研究では,エージェントに通常の優先度に加えて暫時的な優先度を持たせ,更に不要な部分への移動を禁止する拡張を施し,先行研究で求められる条件を緩めても継続的な搬送ができることを述べる.よく知られた既存手法である Token Passing との比較実験を通し,その効率が優位であること,特に一般的な応用で想定されるような運搬箇所に集中や偏りがある場合にその効果が極めて高いことを示す.

  • Multiple-World Trader-Company Method for Stock Price Prediction and Evaluation of Robustness for Regime Change

    Tomoki Yamauchi, Kei Nakagawa, Kentaro Minami, Kentaro Imajo

    Proceedings of the 36th Annual Conference of JSAI   36   1 - 4  2022.06

    Authorship:Lead author

    Research paper, summary (national, other academic conference)  

     View Summary

    In recent years, many investors have been developed quantitative stock prediction models based on machine learning. It is difficult to put a machine learning-based stock price prediction model into practical use due to two challenges: market efficiency and lack of interpretability. Trader-Company (TC) method is a recently developed evolutionary method that finds interpretable temporal rules with high prediction accuracy. However, the TC method does not take into account regime changes, and the regime changes may worsen the prediction accuracy. Therefore, in this study, we propose the Multiple-World Trader-Company (MWTC) method in order to improve high robustness against regime changes. In the MWTC method, the Company model that manages Trader is used as a weak learner, and multiple companies individually learn the training data divided by regime. Empirical analysis using actual market data shows that the MWTC method achieves better prediction accuracy than the baseline method.

    DOI

  • マルチエージェント搬送問題のためのグラフ理論を活用したデッドロック回避手法の提案

    山内 智貴, 宮下 裕貴, 菅原 俊治

    研究報告知能システム(ICS)   2022-ICS-205 ( 4 ) 1 - 7  2022.02

    Authorship:Lead author

    Research paper, summary (national, other academic conference)  

     View Summary

    本研究では迷路状の制限された環境でも輸送効率を向上するため,multi-agent pickup and delivery(MAPD)問題に対してグラフ理論を活用したデッドロック回避手法 standby-based deadlock avoidance(SBDA)を提案する.複数エージェントが衝突せずに資材を繰り返し回収・運搬する MAPD 問題が注目されているが,従来の MAPD アルゴリズムの多くは自動倉庫のような特別に設計されたグリッド状の環境を想定する.それらの環境にはエージェントが長時間滞在できる集配場所が多く,グリッド内の移動の自由さから,衝突回避のための迂回路も豊富である.一方,災害現場や建設現場のような迷路状の環境には集配場所が少なく,それらの数が偏るため,多くのエージェントが集配場所に集中する結果,輸送効率の悪化や立ち往生,デッドロックに陥りやすい.SBDA はグラフ理論の articulation-point-finding アルゴリズムを用いてリアルタイムに決定される待機ノードを使用し,エージェントが有限時間そこに滞在することを保証する.我々は実験により,提案手法が従来手法の輸送効率を上回ることを示した.

  • マルチエージェント搬送のための環境制約を緩めたPIBT手法の拡張

    藤谷 雪北, 山内 智貴, 宮下 裕貴, 菅原 俊治

    研究報告知能システム(ICS)   2021-ICS-204 ( 6 ) 1 - 8  2021.09

    Research paper, summary (national, other academic conference)  

     View Summary

    本研究では,MAPD 問題の制御手法である Priority Inheritance with BackTracking (PIBT) に暫時的な優先度を導入した拡張 PIBT を提案し,PIBT の能力を下げることなく適用環境の制約を緩めることで適用範囲を拡大すると共に,実験的にその効果を示す.PIBT 手法は毎ステップ優先度を計算し,その優先度の高いエージェントから順番に,次のステップでの移動先を確定させるアルゴリズムである.このアルゴリズムでは,袋小路のような形状を含むマップでは行き詰まりが発生するため,実験環境に対しそれを除外する制約を設けている.そこで本研究では,エージェントに通常の優先度に加えて暫時的な優先度を持たせる拡張を施し,先行研究における環境制約を緩めても搬送を継続できることを実験的に示す.

  • 不均一環境におけるマルチエージェント搬送問題のための効率的な経路・動作計画アルゴリズムの提案

    山内 智貴, 宮下 裕貴, 菅原 俊治

    研究報告知能システム(ICS)   2021-ICS-204 ( 2 ) 1 - 8  2021.09

    Authorship:Lead author

    Research paper, summary (national, other academic conference)  

     View Summary

    複数エージェントが衝突せずに,ある保管場所から各目的地まで繰り返し資材を運ぶ multi-agent pickup and delivery(MAPD)問題が注目されているが,従来の MAPD アルゴリズムは特別に設計された環境を前提とすることで,制約条件を考慮しない単純で均一のモデルを使用する.したがってこのような従来アルゴリズムは,より複雑で制限された環境でエージェントが移動する必要がある現実的なアプリケーションに適用できない.例えば災害現場や建設現場では,エージェントや運搬資材のサイズ,通路幅によってエージェントの経路や向きは厳しく制限される.そこで本研究ではまず,不均一環境に適用するために MAPD 問題を拡張した N-MAPD 問題を定式化する.次に,環境制約を満たす衝突のない経路を効率的に生成するため,N-MAPD アルゴリズムである path and action planning with orientation(PAPO)を提案する.PAPO は我々の N-MAPD 問題の定式化において,エージェント・資材・ノードのサイズ,通路幅を考慮して,進行方向だけでなく自転のコストやタイミングと同様にエージェントの向きも考慮するアルゴリズムである.我々はシミュレーション環境を用いて PAPO の性能を実験的に評価し,不均一環境において,最適ではないが許容可能な経路を効率的に生成できることを示した.

  • Action Planning and Conflict Avoidance Algorithm considering State of Agent for Multi-Agent Pickup and Delivery

    Tomoki Yamauchi, Yuki Miyashita, Toshiharu Sugawara

    Proceedings of the 34th Annual Conference of JSAI   34   1 - 4  2020.06

    Authorship:Lead author

    Research paper, summary (national, other academic conference)  

     View Summary

    In the transportation of materials by the automatic carrier robot, it is necessary to consider the direction of the traveling direction depending on the width and the distance from the road and the size and shape of robots and materials. But in this case, the shortest path length and the shortest path operating time may vary according to the difference in the time cost of each running action. In addition, the avoidance of the conflict between robots in the change of path and action must be considered. In this paper, we propose an agent model considering the direction of travel, and a route and action plan and a conflict avoidance algorithm considering the state of the agent to realize the efficient material transportation considering the shapes of robots and materials in the Multi-Agent Pickup and Delivery problem. Simulation experiments demonstrate that the proposed method can improve the material transport efficiency.

    DOI

  • マルチエージェント搬送問題におけるエージェントの状態を考慮した動作計画

    山内智貴, 宮下裕貴, 菅原俊治

    信学技報   119 ( 317 ) 19 - 24  2019.11

    Authorship:Lead author

    Research paper, summary (national, other academic conference)  

     View Summary

    自動搬送ロボットによる物資の運搬では対象とする環境の道幅や距離,ロボットや運搬物資の大きさ・形状によっては進行方向に対する向きを考慮する必要がある.しかし向きを考慮に入れる場合,走行動作ごとの時間コストの差により経路長最短な経路と動作時間最小な経路が異なる可能性がある.そこで本研究は複数台の自動搬送ロボットによるマルチエージェント搬送問題に対して自動搬送ロボットや運搬資材の形状に対応するため,進行方向に対する向きを考慮したエージェントモデルとエージェントの向きを考慮した MAPD アルゴリズム Conflict-Based Search with Orientation (CBSwO) を提案する.

  • Fairness Improvement of Waiting Time between General Passengers and Priority Access Passengers in Elevator Group Control System using Cameras

    YAMAUCHI Tomoki, IDE Rina, SUGAWARA Toshiharu

    Proceedings of the 33rd Annual Conference of JSAI   33 ( 0 ) 1 - 4  2019.06

    Authorship:Lead author

    Research paper, summary (national, other academic conference)  

     View Summary

    We propose the elevator group control method to fairly allocate the cars to all types of waiting passengers including ordinary passengers and priority access passengers who, for example, have strollers or need wheelchairs, in order to achieve fair waiting time as well as efficient transportation. Elevators are necessary for priority persons to move vertically within the building. However, due to the limited capacities, priority passengers who require more spaces often force to wait for a longer time until cars with vacant space arrive. On the other hand, many cameras that monitor the environments have become common and we can estimate the number of waiting passengers with the sizes of their possessions in elevator halls. Therefore, by using this information on passengers, the proposed control attempt to achieve fair latency. The experimental results using the simulated elevator control indicated that our method could make waiting time fairer and achieved the total efficiency to carry passengers.

    DOI CiNii

  • エレベータ群管理システムにおける人数推定を用いた呼び割当手法とスケジューリング手法

    井手理菜, 山内智貴, 菅原俊治

    エージェント合同シンポジウム (JAWS2017)予稿集     1 - 2  2017.09

    Research paper, summary (national, other academic conference)  

▼display all

Awards

  • JSAI 2022 Annual Conference Student Incentive Award

    2022.07   The Japanese Society for Artificial Intelligence   Multiple-World Trader-Company Method for Stock Price Prediction and Evaluation of Robustness for Regime Change

    Winner: Tomoki Yamauchi, Kei Nakagawa, Kentaro Minami, Kentaro Imajo

  • Best Paper Award -- IEICE

    2022.04   The Institute of Electronics, Information and Communication Engineers   Fair and Effective Elevator Car Dispatching Method for Elevator Group Control System Using Noisy Information from Cameras

    Winner: Tomoki Yamauchi, Rina Ide, Toshiharu Sugawara

  • Encouragement award -- SMASH22 Winter Symposium

    2022.03   Symposium on Multi Agent Systems for Harmonization 2022  

    Winner: Tomoki Yamauchi, Yuki Miyashita, Toshiharu Sugawara

  • First place -- SMASH22 Winter Symposium

    2022.03   Symposium on Multi Agent Systems for Harmonization 2022  

    Winner: Tomoki Yamauchi, Yuki Miyashita, Toshiharu Sugawara

  • Encouragement award -- SMASH21 Summer Symposium

    2021.09   Symposium on Multi Agent Systems for Harmonization 2021  

    Winner: Tomoki Yamauchi, Yuki Miyashita, Toshiharu Sugawara

  • Grand prize -- SMASH21 Summer Symposium

    2021.09   Symposium on Multi Agent Systems for Harmonization 2021  

    Winner: Tomoki Yamauchi, Yuki Miyashita, Toshiharu Sugawara

  • Repayment Exemption for Students with Excellent Grades

    2020.06   Japan Student Services Organization  

    Winner: Tomoki Yamauchi

  • CSCE Department Award

    2020.03   Department of Computer Science and Communications Engineering, Waseda University  

    Winner: Tomoki Yamauchi

▼display all

Specific Research

  • 3次元物資輸送システムにおける協調エージェントによる動的計画生成法の研究

    2021   菅原 俊治

     View Summary

    本研究では主に一階層におけるMulti-Agent Pickup and Delivery(MAPD)問題に関する二つの課題に取り組んだ。まず、AGVや運搬資材等のサイズや通路幅等が不均一な環境での輸送計画をN-MAPD問題と定義し、衝突のない経路・動作計画を効率良く生成可能なアルゴリズムを提案、評価した。次にMAPD問題におけるデッドロック回避手法を改善した。専用にデザイン可能なグリッド状の環境を想定した既存手法は、集配場所や迂回路が少ない迷路状の環境では輸送効率が悪化する。迷路状の環境でも運搬の並列性を向上して輸送効率を改善可能な、グラフ理論を活用したデッドロック回避手法を提案、評価した。