Collaborating Authors

Generalizing Multi-Agent Path Finding for Heterogeneous Agents

AAAI Conferences

Multi-Agent Path Finding (MAPF) is the problem of finding non-colliding paths for multiple agents. The classical problem assumes that all agents are homogeneous, with a fixed size and behavior. However, in reality agents are heterogeneous, with different sizes and behaviors. In this paper, we generalize MAPF to G-MAPF for the case of heterogeneous agents. We then show how two previous settings of large agents and k-robust agents are special cases of G-MAPF. Finally, we introduce G-CBS, a variant of the Conflict-Based Search (CBS) algorithm for G-MAPF, which does not cause significant extra overhead.

Explanations as Model Reconciliation — A Multi-Agent Perspective

AAAI Conferences

In this paper, we demonstrate how a planner (or a robot as an embodiment of it) can explain its decisions to multiple agents in the loop together considering not only the model that it used to come up with its decisions but also the (often misaligned) models of the same task that the other agents might have had. To do this, we build on our previous work on multi-model explanation generation and extend it to account for settings where there is uncertainty of the robot's model of the explainee and/or there are multiple explainees with different models to explain to. We will illustrate these concepts in a demonstration on a robot involved in a typical search and reconnaissance scenario with another human teammate and an external human supervisor.

Social Norms for Self-Policing Multi-agent Systems and Virtual Societies

AAAI Conferences

Social norms are one of the mechanisms for decentralized societies to achieve coordination amongst individuals. Such norms are conflict resolution strategies that develop from the population interactions instead of a centralized entity dictating agent protocol.One of the most important characteristics of social norms is that they are imposed by the members of the society, and they are responsible for the fulfillment and defense of these norms. By allowing agents to manage (impose, abide by and defend) social norms, societies achieve a higher degree of freedom by lacking the necessity of authorities supervising all the interactions amongst agents. In this article we summarize the contributions of my dissertation, where we provide an unifying framework for the analysis of social norms in virtual societies, providing an strong emphasis on virtual agents and humans.

The Many Uses of Multi-Agent Intelligent Systems


In professional cycling, it's well known that a pack of 40 or 50 riders can ride faster and more efficiently than a single rider or small group. As such, you'll often see cycling teams with different goals in a race work together to chase down a breakaway before the finish line. This analogy is one way to think about collaborative multi-agent intelligent systems, which are poised to change the technology landscape for individuals, businesses, and governments, says Dr. Mehdi Dastani, a computer scientist at Utrecht University. The proliferation of these multi-agent systems could lead to significant systemic changes across society in the next decade. "Multi-agent systems are basically a kind of distributed system with sets of software.

How to Improve Multi-Agent Recommendations Using Data from Social Networks?

AAAI Conferences

User profiles have an important role in multi-agent recommender systems. The information stored in them improves the system's generated recommendations. Multi-agent recommender systems learn from previous recommendations to update users' profiles and improving next recommendations according to the user feedback. However, when the user does not evaluate the recommendations the system may deliver poor recommendations in the future. This paper presents a mechanism that explores user information from social networks to update the user profile and to generate implicit evaluations on behalf of the user. The mechanism was validated with travel packages recommendations and some preliminary results illustrate how user information gathered from social networks may help to improve recommendations in multi-agent recommender systems.