Bingzheng WANG

Address
A435. Kaiwu Bldg. of Mechanical Engineering, Tongji Univ., No. 4800 Cao An Rd., Shanghai 201804, P. R. China

  • Research Interests

      • Swarm Intelligence
      Multiple UAVs decision-making method based on multi-agent reinforcement learning; Bionic flapping-wing aircraft swarm


    About Multi-Agent Reinforcement Learning

           Multi-Agent Reinforcement Learning (MARL) is an extension of reinforcement learning that focuses on the interaction and cooperation between multiple agents, who learn together how to optimally complete a task. Unlike traditional reinforcement learning, MARL involves multiple agents that can interact with each other and affect each other's states and rewards.


  • Presentations

      • [4] 2024.08.01 An Automatic Weighting Decision-making Framework for Trajectory Tracking of the Overactuated UAVs Platform. Qujiang international conference center. Xi'an, China.
      [3] 2024.06.25 Multiple UAVs Moving Object Tracking Based on Cooperative Operating System. Tongji University. Shanghai, China.
      [2] 2023.12.17 Multiple UAVs Moving Object Tracking Based on Cooperative Operating System. Tongji University. Shanghai, China.
      [1] 2022.06.07 Multiple UAVs Cooperative Suspended Transportation. Presentation as part of the Bachelor Defense. Tongji University. Shanghai, China.


  • Publications

      • black: published, green: accepted for publication, red: submitted for publication
      [1] Bingzheng Wang, Yuanzhe Cui, Yuanxiang Wang and Qirong Tang*. An Automatic Weighting Decision-making Framework for Trajectory Tracking of the Overactuated UAVs Platform. In: 17th International Conference on Intelligent Robotics and Applications (ICIRA 2024). (Accepted)


  • Non-academic work

    •        Responsible for 1.the daily shift arrangement of laboratory cleaning and safety and the statistics of student schedule;2.Maintenance and play of video of each group.