12 Hits in 4.0 sec

Vision-based robot learning towards RoboCup: Osaka University "Trackies" [chapter]

S. Suzuki, Y. Takahashi, E. Uchibe, M. Nakamura, C. Mishima, H. Ishizuka, T. Kato, M. Asada
1998 Lecture Notes in Computer Science  
The authors have applied reinforcement learning methods to real robot tasks in several aspects. We selected a skill of soccer as a task for a vision-based mobile robot.  ...  These behaviors were obtained by a robot in simulation and tested in a real environment in RoboCup-97. We discuss current limitations and future work along with the results of RoboCup-97.  ...  Simulation Based on the LEM algorithm, we limit the opponent's behavior when the robot learns.  ... 
doi:10.1007/3-540-64473-3_69 fatcat:cuisclaabfcpbj6ngislo24s74

RoboCup 2001

P. Lima, T. Balch, M. Fujita, R. Rojas, M. Veloso, H.A. Yanco
2002 IEEE robotics & automation magazine  
Keywords Autonomous robotrs, RoboCup, humanoid robots.  ...  Acknowledgments The following people contributed descriptions of their rescue robot entries: Amir Hossein Jahangir (EMDAD1, Sharif University), Bruce Maxwell and Edward G.  ...  N Trackies, Osaka University, Japan.  ... 
doi:10.1109/mra.2002.1019487 fatcat:2ioav3j7qzfczer4mkfxgyblka

Overview of RoboCup-98 [chapter]

M. Asada, M. Veloso, M. Tambe, I. Noda, H. Kitano, G. K. Kraetzschmar
1999 Lecture Notes in Computer Science  
RoboCup is an increasingly successful attempt to promote the full integration of AI and robotics research.  ...  Following the astonishing success of the first RoboCup-97 at Nagoya [1], the Second Robot World Cup Soccer Games and Conferences, RoboCup-98, was held at Paris during July 2nd and 9th, 1998 at the partly  ...  Figure 6 shows a quarter final match between Osaka Trackies and NAIST.  ... 
doi:10.1007/3-540-48422-1_1 fatcat:prffna2hajeefkum4ehj2rtwta

Overview of RoboCup-97 [chapter]

Itsuki Noda, Shoji Suzuki, Hitoshi Matsubara, Minoru Asada, Hiroaki Kitano
1998 Lecture Notes in Computer Science  
Figure 6 shows visual images from four out of five robots being used by Osaka University Trackies.  ...  Trackies, Osaka Univ. Japan (Asada Lab.) : remote brain systems, nonholonomic vehicles, four attackers and one goalee with omnidirectional vision system.  ... 
doi:10.1007/3-540-64473-3_47 fatcat:ov62fvvjzfaz3bhoyyw74zlt5i

Overview of RoboCup-99 [chapter]

Manuela Veloso, Hiroaki Kitano, Enrico Pagello, Gerhard Kraetzschmar, Peter Stone, Tucker Balch, Minoru Asada, Silvia Coradeschi, Lars Karlsson, Masahiro Fujita
2000 Lecture Notes in Computer Science  
There were four RoboCup-99 competitions: the simulation league, the small-size robot league, the middle-size robot league, and, for the first time officially, the Sony legged robot league.  ...  RoboCup-99, the third Robot World Cup Soccer Games and Conferences, was held in conjunction with IJCAI-99 in Stockholm.  ...  The team from Osaka University has already significant experience in methods for generating cooperative playing skills and in applying reinforcement learning techniques to this problem.  ... 
doi:10.1007/3-540-45327-x_1 fatcat:pwybfd4nivgddgcyope2oo4bte

RoboCup-97: The First Robot World Cup Soccer Games and Conferences

Itsuki Noda, Sho'ji Suzuki, Hitoshi Matsubara, Minoru Asada, Hiroaki Kitano
1998 The AI Magazine  
The world champions are CMUNITED (Carnegie Mellon University) for the small-size league, DREAMTEAM (University of Southern California) and TRACKIES (Osaka University, Japan) for the middle-size league,  ...  RoboCup-98, the Second Robot World Cup Soccer, was held in conjunction with the  ...  This year, we had five teams in the middle-size league, each of which has its own features in several aspects: First was TRACKIES from Osaka University, Japan (Asada Lab.).  ... 
doi:10.1609/aimag.v19i3.1391 dblp:journals/aim/NodaSMAK98 fatcat:3p4grn3grnabzeuuckn4zzer6q

Neural Robot Detection in RoboCup [chapter]

Gerd Mayer, Ulrich Kaufmann, Gerhard Kraetzschmar, Günther Palm
2005 Lecture Notes in Computer Science  
Improving the game play in RoboCup middle size league requires a fast and robust visual robot detection system.  ...  The presented multilevel approach documents, that the combination of a simple color based attention control and a subsequent neural object classification can be applied successfully in real world scenarios  ...  The network is trained with the following robot types: AIS/BIT-Robots, Osaka University Trackies, Attempto Tübingen, Clockwork Orange Delft and Mostly Harmless Graz (and the usual negative examples).  ... 
doi:10.1007/11521082_21 fatcat:rjnkkiubabgfjijhsqqujn3utq

RoboCup: Today and tomorrow—What we have learned

Minoru Asada, Hiroaki Kitano, Itsuki Noda, Manuela Veloso
1999 Artificial Intelligence  
This article describes what we have learned from the past RoboCup activities, mainly the first and the second RoboCups, and overviews the future perspectives of RoboCup in the next century.  ...  RoboCup is an increasingly successful attempt to promote the full integration of AI and robotics research.  ...  Kraetzschmar (University of Ulm, Germany) are appreciated.  ... 
doi:10.1016/s0004-3702(99)00024-7 fatcat:noiwpb42bbh6nnbcceisvzre74

RoboCup-2000: The Fourth Robotic Soccer World Championships

Peter Stone
2001 The AI Magazine  
There were two robots, one of which was Carnegie Mellon University (CMU), (4) Osaka put in the defensive half of the field (passer); University (Japan), (5) Humboldt University the other  ...  - robots could demonstrate dribbling capabili- ED from Melbourne, Australia; the Osaka Uni- ties, such as taking the ball around an oppo- versity TRACKIES from Japan; and the three Ger- nent in  ... 
doi:10.1609/aimag.v22i1.1541 dblp:journals/aim/Stone01 fatcat:sbbel7aksjh6tcgoopzxcy7qq4

Medium Size League: 2002 Assessment and Achievements [chapter]

Andrea Bonarini
2003 Lecture Notes in Computer Science  
Robots in the Robocup Middle Size League (MSL) have dimensions comparable with robots that could be used in other real world applications.  ...  MSL provides a framework to test these robots in a challenging environment where actions should be decided in real-time.  ...  Vision is implemented either by single front cameras, single mobile cam-eras (e.g., Osaka Trackies), multiple cameras (e.g., Philips), or panoramic sensors (e.g., [5] , Artisti Veneti, and Osaka Trackies  ... 
doi:10.1007/978-3-540-45135-8_42 fatcat:zldpz4voa5ea3jct4xu2zkwidq

CS Freiburg: coordinating robots for successful soccer playing

T. Weigel, J.-S. Gutmann, M. Dietl, A. Kleiner, B. Nebel
2002 IEEE Transactions on Robotics and Automation  
of basic skills allowing to respond to large range of situations in an appropriate way, an action selection method based on behavior networks as well as a method to learn the skills and their selection  ...  This paper presents the CS Freiburg team, the winner in the middle size league at RoboCup 1998, 2000 and 2001. The paper focuses on multi-agent coordination for both perception and action.  ...  Similarly, during the final game at RoboCup 2001, the Osaka Trackies put CS Freiburg under a lot of pressure. They also used an omni-directional camera, but no omni-directional drive.  ... 
doi:10.1109/tra.2002.804041 fatcat:he5zdjbasva7ljmjlybwjgb5ve

Towards a Life-Long Learning Soccer Agent [chapter]

Alexander Kleiner, Markus Dietl, Bernhard Nebel
2003 Lecture Notes in Computer Science  
We applied hierarchical reinforcement learning in an SMDP framework learning on all levels simultaneously.  ...  One problem in robotic soccer (and in robotics in general) is to adapt skills and the overall behavior to a changing environment and to hardware improvements.  ...  One team applying RL in the mid size league are Osaka Trackies, which use a method building self-organized hierarchical structures [14] .  ... 
doi:10.1007/978-3-540-45135-8_10 fatcat:opwbqpkxvfdufegt77hyhzbhdi