Wireless Robotic Communication for Collaborative Multi-Agent Systems

Collaborative robots as a multi-agent system to complete a common mission without public reference but operate individual decision and learning mechanism represent a wide range of applications in artificial intelligence. With an illustrative example, reinforcement learning with localization and planning capabilities is developed to represent each robot's operation. It is shown that wireless robotic communication can significantly enhance overall performance of collaborative MAS in the distributed operating manner. After identify useful information (i.e. reward map and private reference) to exchange, according to properties of content, p-persistent real-time ALOHA is suggested to serve as the multiple access protocol of the ad-hoc style networking toward ultra-reliability and ultra-low latency, resulting in satisfactory overall performance close to ideal communication. Wireless robotic communication therefore reveals new technological opportunities for robotics, multi-agent systems, artificial intelligence, and communications.

[1]  Mounir Ghogho,et al.  Mobility Diversity-Assisted Wireless Communication for Mobile Robots , 2016, IEEE Transactions on Robotics.

[2]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[3]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[4]  Hai Lin,et al.  Communication-aware motion planning for multi-agent systems from signal temporal logic specifications , 2017, 2017 American Control Conference (ACC).

[5]  Kwang-Cheng Chen,et al.  Carrier Sensing Based Multiple Access Protocols for Cognitive Radio Networks , 2008, 2008 IEEE International Conference on Communications.

[6]  Kwang-Cheng Chen,et al.  Wireless Communications Meets Artificial Intelligence: An Illustration by Autonomous Vehicles on Manhattan Streets , 2018, 2018 IEEE Global Communications Conference (GLOBECOM).

[7]  Leslie Pack Kaelbling,et al.  Planning and Acting in Partially Observable Stochastic Domains , 1998, Artif. Intell..

[8]  Zhu Han,et al.  Machine Learning Paradigms for Next-Generation Wireless Networks , 2017, IEEE Wireless Communications.

[9]  Vivek S. Borkar,et al.  Distributed Reinforcement Learning via Gossip , 2013, IEEE Transactions on Automatic Control.

[10]  Nicholas R. Jennings,et al.  Decentralised channel allocation and information sharing for teams of cooperative agents , 2012, AAMAS.

[11]  Jan Peters,et al.  Reinforcement learning in robotics: A survey , 2013, Int. J. Robotics Res..

[12]  Nikos A. Vlassis,et al.  Collaborative Multiagent Reinforcement Learning by Payoff Propagation , 2006, J. Mach. Learn. Res..

[13]  Victor R. Lesser,et al.  Communication decisions in multi-agent cooperation: model and experiments , 2001, AGENTS '01.

[14]  Sebastian Thrun,et al.  Learning Occupancy Grid Maps with Forward Sensor Models , 2003, Auton. Robots.

[15]  Wolfram Burgard,et al.  A Probabilistic Approach to Collaborative Multi-Robot Localization , 2000, Auton. Robots.