CommLang: Communication for Coachable Agents

Davin, John; Riley, Patrick; Veloso, Manuela

doi:10.1007/978-3-540-32256-6_4

Cited by 4 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The players are not limited to exchanging information: co-operation can be enhanced by the intentional exchange of messages to co-ordinate robots' behaviour. One example, from [6], is when a robot well positioned to score a goal decides to ask its team-mate holding the ball to perform a pass. Such interactions rely on the prior existence of a vocabulary defining skills and actions, which can, during the game, be requested.…”

Section: Player Moves and Actionsmentioning

confidence: 99%

An Elementary Communication Framework for Open Co-operative RoboCup Soccer Teams

Mota

Reis

2007

Proceedings of the 3rd International Workshop on Multi-Agent Robotic Systems

View full text Add to dashboard Cite

One of the present day challenges in RoboCup is the development of Open Cooperative teams, where different research labs join efforts to build a common team. In RoboCup Middle-size League, some teams were confronted with a pairwise cooperation scenario in order to qualify to the competition. Such teams bring together robots with heterogeneous hardware, architectures and control software, which hinders straightforward cooperation. The robots in these teams might cooperate through a-priori strategic knowledge and structured communication during the game. This paper presents the kernel of a communication framework, defining a robotic soccer vocabulary, as well as rules to manage communication.

show abstract

Section: Player Moves and Actionsmentioning

confidence: 99%

An Elementary Communication Framework for Open Co-operative RoboCup Soccer Teams

Mota

Reis

2007

Proceedings of the 3rd International Workshop on Multi-Agent Robotic Systems

View full text Add to dashboard Cite

show abstract

“…Communication between agents can be very helpful in terms of cooperation. Without communication, agents must rely on observation-based judgments of their collaborator's intentions [14]. Agents communicate simply to inform others some relevant facts about them.…”

Section: Introductionmentioning

confidence: 99%

A new dialogue strategy in multi-agent systems

Beigi

Mozayani

2014

Journal of Intelligent &Amp; Fuzzy Systems

View full text Add to dashboard Cite

For establishing communications and modeling a framework for dialogue between intelligent agents, it is beneficial to have a well-defined strategy. In a dialogue run, the strategies are the manners to achieve the agents' goals by selecting the best option between the different existent choices. There are not many works which define the strategies for dialogue between agents. In this paper a formal model for dialogue strategy is proposed. The proposed model is a decision making problem of selecting the type of the act and the compatible content to utter at each step of a dialogue. In a given dialogue step, the model can decide the appropriate act and content allowed by the dialogue protocol in order to satisfy the agents' goals. The strength of the decisions which define the best next move is computed by argumentation theory. The proposed model is illustrated through an example of Dutch auction.

show abstract

Coordination in Multi-robot Systems: Applications in Robotic Soccer

Reis

Almeida²,

Mota

et al. 2013

Communications in Computer and Information Science

View full text Add to dashboard Cite

This paper presents in a simple and very concise manner, and accessible to a broad audience, the concepts of Artificial Intelligence (AI), Agents and Multi-Agent Systems (MAS), Coordination in MAS, Intelligent Robotics (IR), Multi-Robot Systems (MRS), Machine Learning (ML), Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL). Emphasis is given on and how AI and ML, with special focus on DRL, may be efficiently used to create efficient robot skills and coordinated robotic teams, capable of performing very complex actions and tasks, as a team, such as playing a game of soccer.The paper also presents the concept of robotic soccer and the vision and structure of the RoboCup initiative and the world robotic soccer championship with emphasis on the Humanoid Simulation 3D league and the new challenges for the AI community that RoboCup, and in particular this competition, poses. The final topics presented at the paper are based on the research developed or coordinated by the author throughout the last 22 years on the areas of multi-agent systems and intelligent robotics with emphasis for its applications in the domain of robotic soccer in the context of the FC Portugal project.Proxy challenge and the Free/Scientific Challenge at RoboCup 2022. In what concerns scientific publications, the FC Portugal project and the works briefly described in this paper enabled us to publish more than 100 papers in indexed international conferences and journals.

show abstract

CommLang: Communication for Coachable Agents

Cited by 4 publications

References 3 publications

An Elementary Communication Framework for Open Co-operative RoboCup Soccer Teams

An Elementary Communication Framework for Open Co-operative RoboCup Soccer Teams

A new dialogue strategy in multi-agent systems

Coordination in Multi-robot Systems: Applications in Robotic Soccer

Contact Info

Product

Resources

About