In this thesis, deep reinforcement learning is applied to the problem of formation control to enhance performance. The current state-of-the-art formation control algorithms are often not adaptive and require a high degree of expertise to tune. By introducing reinforcement learning in combination with a behavior-based formation control algorithm, simply tuning a reward function can change the entire dynamics of a group. In the experiments, a group of three agents moved to a goal which had its direct path blocked by obstacles. The degree of randomness in the environment varied: in some experiments, the obstacle positions and agent start positions were fixed between episodes, whereas in others they were completely random. The greatest improvements were seen in environments which did not change between episodes; in these experiments, agents could more than double their performance with regards to the reward. These results could be applicable to both simulated agents and physical agents operating in static areas, such as farms or warehouses. By adjusting the reward function, agents could improve the speed with which they approach a goal, obstacle avoidance, or a combination of the two. Two different and popular reinforcement algorithms were used in this work: Deep Double Q-Networks (DDQN) and Proximal Policy Optimization (PPO). Both algorithms showed similar success.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Intelligent Formation Control using Deep Reinforcement Learning


    Beteiligte:

    Erscheinungsdatum :

    2018-01-01


    Medientyp :

    Hochschulschrift


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Intelligent Robust Disturbance Rejection Control via Deep Reinforcement Learning

    Huang, Hanqiao / Xu, Feihong / Cheng, Haoyu et al. | Springer Verlag | 2022


    Intelligent Control of Manipulator Based on Deep Reinforcement Learning

    Zhou, Jiangtao / Zheng, Hua / Zhao, Dongzhu et al. | IEEE | 2021


    GPS-Denied Three Dimensional Leader-Follower Formation Control Using Deep Reinforcement Learning

    Selje, Robert A. / Al-Radaideh, Amer / Dutta, Rajdeep et al. | TIBKAT | 2022


    Modular production control using deep reinforcement learning

    Mayer, Sebastian / Classen, Tobias / Endisch, Christian | BASE | 2022

    Freier Zugriff

    GPS-Denied Three Dimensional Leader-Follower Formation Control Using Deep Reinforcement Learning

    Selje, Robert A. / Al-Radaideh, Amer / Dutta, Rajdeep et al. | AIAA | 2022