Kostas Kostiadis
University of Essex, UK
Huosheng Hu
University of Essex, UK
Download article
Published in: RobocCup-99 Team Descriptions. Simulation League
Linköping Electronic Conference Proceedings 4:5, p. 17-26
Linköping Electronic Articles in Computer and Information Science vol. 4 4:5, p. 17-26
Published: 1999-12-15
ISBN:
ISSN: 1650-3686 (print), 1650-3740 (online)
This article is to describe the Essex Wizards team attending the simulation league of RoboCup99 in Stockholm. A long-term research goal of this team is to focus on cooperative behaviours; team roles and formations; sensor fusion and machine learning capabilities. Therefore; the initial efforts for participating at RoboCup99 are mainly concentrated on a multi-threaded implementation to simulated soccer agents for the RoboCup competition in order to meet the timing requirements set by the RoboCup soccer server simulator. Since robot agents work at three distinct phases: sensing; thinking and acting; POSIX threads are adopted to break down these phases and implement them concurrently. Implementation results have shown that it outperforms traditional single-threaded approaches in terms of efficiency; responsiveness and scalability. To handle a complex; dynamic; adversarial environment like the one of a football game; this article also describes how machine learning techniques and agent technology have been used in the current implementation; to tackle the decision-making and co-operation problems. By gathering useful experience from earlier stages; an agent can significantly improve its performance and by distributing the responsibilities among the agents; an efficient way of co-operation emerges.
1 Balch T. R.; Integrating RL and Behaviour-based Control for Soccer: Proc. IJCAI Workshop on RoboCup; 1997.
2 Burns A. and Wellings: A.; Real-time Systems and Programming Languages; Addison-Wesley; 1997.
3 Butenhof R.D: Programming with POSIX Threads; Harlow; Addison-Wesley; 1997.
4 Ch’ng S.; Padgham L.: From Roles to Teamwork: A Framework and Architecture; Applied Arti cial Intelligence Journal; 1997.
5 Ch’ng S.; Padgham L.: Team description: Building Teams Using Roles; Responsibilities; and Strategies; Proc. IJCAI- 97 on RoboCup; 1997.
6 Hu H.; Gu D.; Brady M.: A Modular Computing Architecture for Autonomous Robots; in the Int. Journal of Microprocessors and Microsystems; Vol. 21; No. 6 (March 1998); pages 349-362.
7 Hu H.; Kelly I.; Keating D.; Vinagre D.: Coordination of Multiple Mobile Robots via Communication; Proc. SPIE’98; Mobile Robots XIII Conference; Boston; pages 94-103; Nov. 1998.
8 Kitano H.; RoboCup: The Robot World Cup Initiative; In proceedings of The First International Conference on Autonomous Agent (Agents-97)); Marina del Ray; The ACM Press; 1997.
9 Kitano H.; Tambe M.; Stone P.; Veloso M.; Coradeschi S.; Osawa E.; Matsubara H.; Noda I.; and Asada M.: The RoboCup Synthetic Agent Challenge; 97. Int. Joint Conference on Arti cial Intelligence (IJCAI97); 1997.
10 Kostiadis K. and Hu H.: Reinforcement Learning and Cooperation in a Simulated Multi-agent System; Submitted to IROS’99; Korea; October 1999.
11 Kostiadis K. and Hu H.: A multi-threaded approach to simulated soccer agents for the RoboCup competition; Submitted to RoboCup ’99 Workshop; 1999.
12 Mataric; J. M.: Interaction and Intelligent Behaviour; PhD Thesis; Massachusetts Institute of Technology; 1994.
13 Nissanke N.: Realtime Systems; London; Prentice Hall; 1997.
14 Noda I.: Soccer Server: A Simulator for RoboCup; JSAI AI-Symposium 95: Special Session on RoboCup; 1995.
15 Stevens W.R.: Unix Network Programming: Networking APIs: Sockets and XTI (Volume 1); London; Prentice-Hall International; 1998.
16 Stone Peter and Veloso Manuela: Team-Partitioned; Opaque- Transition Reinforcement Learning; Proc. 15th Int. Conf. on Machine Learning; 1998.
17 Uchibe E.; Asada M.; Noda S.; Takahashi Y.; Hosoda K.: Vision-Based Reinforcement Learning for RoboCup: Towards Real Robot Competition; Proc. of IROS 96 Workshop on RoboCup; 1996.
18 Uchibe E.; Asada M.; Hosoda K.; Strategy Classiffication in Multi-Agent Environment - Applying Reinforcement Learning to Soccer Agents. ICMASS’96 workshop 2: RC Workshop; 1996.
