Recent Advances on Multi-Agent Collaboration: A Cross-Perspective of Game and Control Theory

• QIN Jia-Hu^{1 ,}  , 
• MA Qi-Chao^{1 ,}  , 
• LI Man^{1 ,}  , 
• ZHANG Cong^{1 ,}  , 
• FU Wei-Ming^{1, 2 ,}  , 
• LIU Qing-Chen^{1 ,}  , 
• ZHENG Wei-Xin^{2 ,} 

• 1.

  Department of Automation, University of Science and Technology of China, Hefei 230027, China

• 2.

  School of Computer, Data and Mathematical Sciences, Western Sydney University, Sydney, NSW 2751, Australia

Author Bio:

QIN Jia-Hu　Professor at Department of Automation, University of Science and Technology of China. His research interests include networked control systems, autonomous intelligent systems, and human–robot interaction

MA Qi-Chao　Research Associate Professor at Department of Automation, University of Science and Technology of China. His research interests include decision and control of multi-agent systems, with applications to robotics

LI Man　Research Associate Professor at Department of Automation, University of Science and Technology of China. Her research interests include multi-agent games, reinforcement learning, and human–robot interaction

CONG Zhang　Post-Doctoral Researcher at Department of Automation, University of Science and Technology of China. Her research interests include multi-agent cooperation, distributed state estimation, and SLAM

FU Wei-Ming　Professor at Department of Automation, University of Science and Technology of China. His research interests include consensus in multi-agent systems and energy management in smart grids

LIU Qing-Chen　Professor at Department of Automation, University of Science and Technology of China. His research interests include networked systems, multi-robotics system and learning based control

ZHENG Wei-Xing　Distinguished professor at Western Sydney University, Australia. IEEE Fellow. His research interest covers system identification, networked control systems, multi-agent systems, neural networks, and signal processing



1¹ 这里的交互指的是信息流动, 例如智能体通过通信或者传感装置获取其他个体的信息² 除非特别声明, 下文均以这里的连续型动力学系统为讨论对象.
2³ 如果矩阵$ A $的特征值实部小于等于零, 且实部为零的特征值代数重数等于几何重数, 就称$ A $是边缘稳定的.⁴ 如果矩阵$ A $的特征值实部均为零, 且代数重数等于几何重数, 就称$ A $是中立型稳定的.
3⁵有界输入下渐近零可控的定义见文献[42]
4⁶ 除非特别说明, 本小节所述时间$ t\in[t_k^i,\;t_{k+1}^i) $.