M. Asada, H. Kitano, I. Noda, M. Veloso, Robocup: today and tomorrow { what we have learned, Arti cial Intelligence Journal 110 (1999) 193-214.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....capabilties of the pursuers. Competition in multi robot systems, such as that found in higher animals including humans, is being studied in domains such as multi robot soccer. A previous special journal issue in Artificial Intelligence on RoboCup discusses many of the advances in this area; see [6] for a general overview of the field, and [49] 7] 61] 64] 5] for some particular examples of this research. Another series of books appears yearly in the Lecture Notes in Artificial Intelligence series on the topic of multi robot soccer, beginning with [38] Two articles in this special ....

M. Asada, H. Kitano, I. Noda, and M. Veloso. RoboCup: Today and tomorrow -- what we have learned. Artificial Intelligence, 110(2):193-- 214, June 1999.

....is not a simulation of a problem domain but the problem domain per se [13] This means that we can omit problems originating from the real world such as noisy sensor data or limitations of motor functions. Consequently, while the related academic work done on military simulations [14] or robotics [1] is valuable, CGs present the AI problems in a much purer form. The motivation behind the AIsHockey platform presented in this paper stems from this observation. Although it is based on a real world game of ice hockey, it is not a simulation ice hockey but a game itself. Because it is abstracted ....

....operation area surrounding the player (radius 0.85 m) To communicate with other players, a player can send messages which all players (even the opponents) can receive. AIsHockey draws inspiration from the simulation league of the RoboCup initiative, where autonomous client programs play soccer [1]. Nevertheless, AIsHockey is fundamentally a CG, whereas RoboCup is a testbench for robotics. The assumptions made in the simulation league yield to the restrictions of real world robots (e.g. sensors and motor systems) As we emphasized earlier, AIsHockey concentrates on the implementation of ....

M. Asada, H. Kitano, I. Noda, and M. Veloso. RoboCup: Today and tomorrow---what we have learned. Artificial Intelligence, 110(2):193--214, 1999.

....recent World Cup. The current state of the art however does not allow any comparison with this goal, yet. The capabilities of current simulation teams are still far behind of any human junior Soccer team. Out of the analysis of recent RoboCup competitions This paper was published at TAINN 02. [1], 12] one can conclude that still much progress is required in all areas of technology used in the multi agent teams. From the perspective of the architecture of the Soccer teams, various approaches are proposed [3] 9] 10] 11] 13] With respect to the movements of the game objects, ....

Asada, Minoru; Kitano, Hiroaki; Noda, Itsuki; Veloso, Manuela; 1999; "RoboCup: today and tomorrow - what we have learned"; Artificial Intelligence; Elsevier

....approach. In section 2 we introduce the basic elements of our architecture. Section 3 is devoted to some of the possibilities to adapt this architecture to dynamical changes. In the end, we discuss some results obtained by embodied robotic agents in a highly dynamical environment, such as RoboCup [7]. 2 The Architecture We propose a coordination mechanism for multi agent systems that relies on a general conceptual architecture. Our aim was to build a framework for designing and developing MAS for a wide range of applications. We approach the problem from a general point of view, pursuing ....

....situation and the action actually done will be strengthened, while it will be weakened if the timeout expired. 4 Case Study In order to validate the proposed architecture, we implemented SCARE (Scare Coordinates Agents in Robotic Environments) and used it in a multi robot application: RoboCup [7]. Robotic soccer affords a complex and complete application domain for MAS, ideal for testing the capabilities of a coordination system; in fact, this kind of application is characterized by dynamic environment, real time constraints, uncertainty, partial and distributed knowledge, autonomous and ....

M. Asada, H. Kitano, I. Noda, and M. Veloso, "Robocup: today and tomorrow -- what we have learned," Articial Intelligence Journal, vol. 110, pp. 193--214, 1999.

.... The RoboCup contest is a new AI challenge, after the remarkable success of the chess playing challenge: After building a computer program that can beat a human world champion, the new challenge is stated as building a robot football (soccer) playing team that will beat the human world champion [1]. Various issues emerged around the new AI challenge, one of them being the issue of training. We stated it in following way: Human football players are trained, not handprogrammed to play football. Is it possible to achieve it with robots Does it make sense to define a RoboCup league in which ....

Asada M., Kitano H., Noda I., Veloso M. 1999. RoboCup: Today and tomorrow - What we have learned. Artificial Intelligence 110: 193-214

No context found.

M. Asada, H. Kitano, I. Noda, M. Veloso, Robocup: today and tomorrow { what we have learned, Arti cial Intelligence Journal 110 (1999) 193-214.

No context found.

M. Asada, H. Kitano, and M. Veloso. Robocup: Today and tomorrow: What we have learned. Artificial Intelligence,

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC