Takato Motoo
Research Subjects
Takato Motoo has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Shunsuke Saruwatari
Graduate School of Information Science and Technology, The University of Osaka, Suita, Osaka, Japan
2 shared publications - Takashi Watanabe
Graduate School of Information Science and Technology, The University of Osaka, Suita, Japan
2 shared publications - Takuya Fujihashi
The University of Osaka, Suita, Japan
2 shared publications Hiroaki Shinmiya
Graduate School of Information Science and Technology, Osaka University,Japan
1 shared publicationJiei Kawasaki
Graduate School of Information Science and Technology, Osaka University, Osaka, Japan
1 shared publicationKahoko Takahashi
Nippon Telegraph and Telephone Corporation,Network Innovation Laboratories
1 shared publication
Latest Publications
- 8 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 281-286
Robot-Network Co-optimization Using Deep Reinforcement Learning
The evolution of a cell phone network and a wireless local area network (LAN) has enabled various devices to be connected to wireless networks anytime, anywhere. This has led to the emergence of various applications, such as automatic transportation of parts and cargo by automated guided vehicles, remote control of unmanned vehicles, and drones. It will be a challenge to maintain high-quality connections, which satisfy the requirements of such emerging applications, for a large number of intelligent connected devices. To improve the network performance, we must control the wireless network setting and the behavior of the connected vehicles, i.e., robots. From this perspective, this proposes a novel framework, CoRein, that achieves simultaneous optimization of robot behavior and wireless network setting. In contrast to the existing studies, CoRein provides optimal actions for robots and wireless networks using deep reinforcement learning (DRL) architecture. To the best of our knowledge, our study firstly attempts to solve different tasks corresponding to robots and networking with a unique DRL architecture. To evaluate the effectiveness of CoRein, we considered a scenario where two robots were moving back and forth while communicating with one of two access points. CoRein calculates the robot velocities and AP selection. We carried out simulations and indoor experiments with our robot testbeds to evaluate the network performances. Evaluation results confirmed that the two robots adjusted their positions and the access points to increase the wireless network's performance, i.e., throughput and round trip time while changing the speed of their movements.
- 8 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 281-286
Robot-Network Co-optimization Using Deep Reinforcement Learning
The evolution of a cell phone network and a wireless local area network (LAN) has enabled various devices to be connected to wireless networks anytime, anywhere. This has led to the emergence of various applications, such as automatic transportation of parts and cargo by automated guided vehicles, remote control of unmanned vehicles, and drones. It will be a challenge to maintain high-quality connections, which satisfy the requirements of such emerging applications, for a large number of intelligent connected devices. To improve the network performance, we must control the wireless network setting and the behavior of the connected vehicles, i.e., robots. From this perspective, this proposes a novel framework, CoRein, that achieves simultaneous optimization of robot behavior and wireless network setting. In contrast to the existing studies, CoRein provides optimal actions for robots and wireless networks using deep reinforcement learning (DRL) architecture. To the best of our knowledge, our study firstly attempts to solve different tasks corresponding to robots and networking with a unique DRL architecture. To evaluate the effectiveness of CoRein, we considered a scenario where two robots were moving back and forth while communicating with one of two access points. CoRein calculates the robot velocities and AP selection. We carried out simulations and indoor experiments with our robot testbeds to evaluate the network performances. Evaluation results confirmed that the two robots adjusted their positions and the access points to increase the wireless network's performance, i.e., throughput and round trip time while changing the speed of their movements.
- Open Access
- 9 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 125678-125690
Client-Side Network Delay Compensation for Online Shooting Games
In online multiplayer shooting games, a long network delay can adversely impact player performance because it leads to large synchronization errors in the game information, such as location errors, between players. To mitigate synchronization errors between players, we propose a novel client-side delay compensation system for online multiplayer shooting games. The proposed delay compensation system comprises regression-based and reinforcement-based methods, which accurately predict present game information based on past game information from within each player's device. Specifically, the regression-based method utilizes linear regression to accurately predict a player's present location based on past location information, whereas the reinforcement-based method utilizes deep reinforcement learning to predict a player's present commands corresponding to the player's current location, based on past snapshots of the game fields. The advantage of the proposed system over the existing server-side delay compensation methods, e.g., Lag Compensation, is that they display accurate game information in each player's device as if the player devices were synchronized with each other; thus, any unfair advantages to the players are prevented. We developed a shooting game simulator to experimentally compare the proposed system with existing ones under constant and fluctuating network delays in loss-free and loss-prone networks. The movement models of different players were considered in the experiments. The results demonstrate that the proposed system simultaneously achieves a lower synchronization error between players and higher shooting accuracy, compared to Lag Compensation. For example, the average decrease in player shooting hit rate under a constant network delay of 100 ms is 0.55, 0.076, and 0.0039 without delay compensation and with the proposed regression-based and reinforcement-based methods, respectively. Under the same network delay, the proposed regression-based and reinforcement-based methods show the improvement of 16 pixels and 14 pixels in terms of the synchronization error compared to Lag Compensation, respectively.
- 9 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 125678-125690
Open AccessClient-Side Network Delay Compensation for Online Shooting Games
In online multiplayer shooting games, a long network delay can adversely impact player performance because it leads to large synchronization errors in the game information, such as location errors, between players. To mitigate synchronization errors between players, we propose a novel client-side delay compensation system for online multiplayer shooting games. The proposed delay compensation system comprises regression-based and reinforcement-based methods, which accurately predict present game information based on past game information from within each player's device. Specifically, the regression-based method utilizes linear regression to accurately predict a player's present location based on past location information, whereas the reinforcement-based method utilizes deep reinforcement learning to predict a player's present commands corresponding to the player's current location, based on past snapshots of the game fields. The advantage of the proposed system over the existing server-side delay compensation methods, e.g., Lag Compensation, is that they display accurate game information in each player's device as if the player devices were synchronized with each other; thus, any unfair advantages to the players are prevented. We developed a shooting game simulator to experimentally compare the proposed system with existing ones under constant and fluctuating network delays in loss-free and loss-prone networks. The movement models of different players were considered in the experiments. The results demonstrate that the proposed system simultaneously achieves a lower synchronization error between players and higher shooting accuracy, compared to Lag Compensation. For example, the average decrease in player shooting hit rate under a constant network delay of 100 ms is 0.55, 0.076, and 0.0039 without delay compensation and with the proposed regression-based and reinforcement-based methods, respectively. Under the same network delay, the proposed regression-based and reinforcement-based methods show the improvement of 16 pixels and 14 pixels in terms of the synchronization error compared to Lag Compensation, respectively.