Team Edinferno Description Paper for RoboCup 2011 SPL

This paper outlines the organization and architecture of a robotic soc- cer team, Team Edinferno, making its international debut at the 2011 RoboCup Standard Platform League competitions. We are a completely new team, the first SPL team to come from the United Kingdom. Our primary research interests are centered on issues of autonomous robotics and robot learning, especially for effective autonomous decision making and strategic behaviour in continually changing worlds. This is supported by solid foundations in robotic locomotion and full-body behaviours, on-board computer vision and communications soft- ware infrastructure.

[1]  Subramanian Ramamoorthy,et al.  Motion Synthesis through Randomized Exploration on Submanifolds of Configuration Space , 2009, RoboCup.

[2]  Subramanian Ramamoorthy,et al.  Online Motion Planning for Multi-robot Interaction Using Composable Reachable Sets , 2011, RoboCup.

[3]  Subramanian Ramamoorthy,et al.  Comparative evaluation of MAL algorithms in a diverse set of ad hoc team problems , 2012, AAMAS.

[4]  M. M. Hassan Mahmud,et al.  Learning in non-stationary MDPs as transfer learning , 2013, AAMAS.

[5]  Subramanian Ramamoorthy,et al.  Intent inference and strategic escape in multi-robot games with physical limitations and uncertainty , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[6]  Subramanian Ramamoorthy,et al.  Bayesian interaction shaping: learning to influence strategic interactions in mixed robotic domains , 2013, AAMAS.

[7]  Subramanian Ramamoorthy,et al.  Constrained geodesic trajectory generation on learnt skill manifolds , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[8]  Subramanian Ramamoorthy,et al.  BRISK-Based Visual Feature Extraction for Resource Constrained Robots , 2013, RoboCup.

[9]  Sebastian Thrun,et al.  Probabilistic robotics , 2002, CACM.

[10]  Subramanian Ramamoorthy,et al.  Motion planning and reactive control on learnt skill manifolds † , 2013, Int. J. Robotics Res..

[11]  Benjamin Kuipers,et al.  Trajectory generation for dynamic bipedal walking through qualitative model based manifold learning , 2008, 2008 IEEE International Conference on Robotics and Automation.

[12]  Luca Iocchi,et al.  Induction and learning of finite-state controllers from simulation , 2012, AAMAS.

[13]  Sethu Vijayakumar,et al.  Learning nullspace policies , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[14]  Subramanian Ramamoorthy,et al.  NaOISIS: A 3-D Behavioural Simulator for the NAO Humanoid Robot , 2011, RoboCup.