论文信息 - CM μ s 2018 Team Description

CM μ s 2018 Team Description

In this paper, we present our team’s recent work in expanding our team strategy to comply with the RoboCup Small-Size League’s recent rule changes and in learning new policies for our robots. In regards to the new rules, we have expanded our offensive strategy to utilize all of the robots across the larger field size. Our defensive strategy was changed to handle the new rectangular defense area. In learning new policies, we focused on using machine learning to automate the process of creating different parts of the Skills, Tactics, and Plays hierarchy. Lastly, we discuss new robots and hardware.

[1] Manuela M. Veloso,et al. Layered Disclosure: Revealing Agents' Internals , 2000, ATAL.

[2] Manuela M. Veloso,et al. Real-Time Randomized Path Planning for Robot Navigation , 2002, RoboCup.

[3] Brett Browning,et al. STP: Skills, tactics, and plays for multi-robot control in adversarial environments , 2005 .

[4] Peter Stone,et al. Keepaway Soccer: From Machine Learning Testbed to Benchmark , 2005, RoboCup.

[5] Manuela M. Veloso,et al. Efficient physics-based planning: sampling search via non-deterministic tactics and skills , 2009, AAMAS.

[6] Steven D. Klee,et al. CMDragons 2013 Team Description , 2013 .

[7] Shane Legg,et al. Human-level control through deep reinforcement learning , 2015, Nature.

[8] Manuela M. Veloso,et al. Selectively Reactive Coordination for a Team of Robot Soccer Champions , 2016, AAAI.

[9] Manuela M. Veloso,et al. Opponent-Aware Ball-Manipulation Skills for an Autonomous Soccer Robot , 2016, RoboCup.

[10] Steven D. Klee,et al. CMDragons 2016 Extended Team Description Paper , 2016 .

[11] Manuela M. Veloso,et al. Intra-robot replanning to enable team plan conditions , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).