The CMUnited-97 robotic soccer team: Perception and multi-agent control

Abstract

Robotic soccer is a challenging research domain which involves multiple agents that need to collaborate in an adversarial environment to achieve specific objectives. In this paper, we describe CMUnited, the team of small robotic agents that we developed to enter the RoboCup-97 competition. We designed and built the robotic agents, devised the appropriate vision algorithm, and developed and implemented algorithms for strategic collaboration between the robots in an uncertain and dynamic environment. The robots can organize themselves in formations, hold specific roles, and pursue their goals. In game situations, they have demonstrated their collaborative behaviors on multiple occasions. The robots can also switch roles to maximize the overall performance of the team. We present an overview of the vision processing algorithm which successfully tracks multiple moving objects and predicts trajectories. The paper then focusses on the agent behaviors ranging from low-level individual behaviors to coordinated, strategic team behaviors. CMUnited won the RoboCup-97 small-robot competition at IJCAI-97 in Nagoya, Japan.Content Areas: autonomous robots; multi-agent teams; coordinating perception, thought, and action; multi-agent communication, coordination, and collaboration; real-time performance. £We thank Sorin Achim for developing and building the robots.

Results in cooperative control and implicit consensus

“…However, most of these papers only focus on so-called unconstrained consensus applications. When the consensus, that the system is to reach, should fulfil external conditions (such as a common heading of a flock of agents, but in a particular direction), three approaches are usually taken, see Beard et al (2001), Lawton et al (2003), Ren and Beard (2004) and citations therein: leader-following (Wang 1989, Singh et al 2000, Mesbahi and Hadaegh 1999, Fax and Murray 2004, Ji et al 2006, virtual structure based (Lewis and Tan 1997, Beard et al 2000, Shi et al 2005 or behaviour based (Balch and Arkin 1998, Anderson and Robbins 1998, Lawton et al 2003, Parker 1998, Chen and Luh 1994, Veloso et al 2000 approaches. The first concept presents a common technique used typically to make formations of autonomous mobile agents follow desired trajectories.…”

Distributed intelligence: overview of the field and its application in multi-robot systems

“…This defines the adversarial domain, in which entities actively work against each other. In multi-robot systems, this topic is studied extensively in the multi-robot soccer application domain (e.g., [55], [15], [118], [101]). This form of interaction also has clear relevance for many security and military applications.…”

“…An easy division of work is achieved by assigning roles according to the skills and capabilities of the individual team members. For instance, in multi-robot soccer [100], [67], [118], positions played by the different robots are often defined as roles, such as goal keeper, left defender, right defender, left forward, right forward, and so forth. The robot best suited, and perhaps in closest proximity, to the available roles/positions then selects to perform that role.…”

STP: Skills, tactics, and plays for multi-robot control in adversarial environments

“…Figure 2 shows the major components of the control system developed for our CMDragons SSL team. This architecture is the result of a long series of developments since RoboCup 1997 [37,36,35,10,12]. Figure 3 shows the robot team members.…”