Agent teams for design problems

Lecture Notes in Computer Science, 2016

Design imposes a novel social choice problem: using a team of voting agents, maximize the number of optimal solutions; allowing a user to then take an aesthetical choice. In an open system of design agents, team formation is fundamental. We present the first model of agent teams for design. For maximum applicability, we envision agents that are queried for a single opinion, and multiple solutions are obtained by multiple iterations. We show that diverse teams composed of agents with different preferences maximize the number of optimal solutions, while uniform teams composed of multiple copies of the best agent are in general suboptimal. Our experiments study the model in bounded time; and we also study a real system, where agents vote to design buildings.

Systems and Computers in Japan, 1998

In this paper, we propose a group decision support system based on persuasion among agents. In the system, each user manages an analytic hierarchy process (AHP) system and an agent. Each user subjectively constructs a decision hierarchy and determines the various weights of alternatives by using AHP. Based on the hierarchy and weights, agents negotiate with each other on behalf of their users. In general, existing systems use a voting method for negotiating among agents. However, the result of voting are often inconsistent, largely due to the inconsistency of voting rules. Therefore, we propose a persuasion mechanism, rather than voting methods, for negotiation among agents. Adopting some of the features of AHP, we implement a new persuasion mechanism. The agents have an explanation mechanism. They can explain to their users why they have been persuaded, when they are persuaded, who persuaded them, and how they are persuaded. Finally, we describe the results from our current experiments. The results demonstrate that the persuasion mechanism is an effective method for a group decision support system based on multi-agent negotiation.

Web-enabled collective intelligence in design invites anyone to contribute to a design process through crowdsourcing. We use a protocol analysis method to analyse the forum data on a collective intelligence web site, studying communication among individuals who are motivated to participate in the design process. A protocol analysis allows us to compare collective intelligence in design to similar studies of individual and team design. Our analysis shows that a design process that includes collective intelligence shares processes of ideation and evaluation with individual and team design, and also includes a significant amount of social networking. Including collective intelligence in design can extend the typical design team to include potential users and amateur perspectives that direct the design to be more sensitive to users’ needs and social issues, and can serve a marketing purpose.

8th AAAI Multidisciplinary Workshop on Advances in Preference Handling (M-PREF 2014)

In this research-in-progress paper we present a new real world domain for studying the aggregation of different opinions: early stage architectural design of buildings. This is an important real world application, not only because building design and construction is one of the world’s largest industries measured by global expenditures, but also because the early stage design decision making has a significant impact on the energy consumption of buildings. We present a mapping between the do- main of architecture and engineering research and that of the agent models present in the literature. We study the importance of forming diverse teams when aggregating the opinions of different agents for architectural design, and also the effect of having agents optimizing for different factors of a multi-objective optimization design problem. We find that a diverse team of agents is able to provide a higher number of top ranked solutions for the early stage designer to choose from. Finally, we present the next steps for a deeper exploration of our questions.

Frontiers in Robotics and AI, 2019

Autonomous decision-making is a fundamental requirement for the intelligent behavior of individual agents and systems. For artificial systems, one of the key design prerequisites is providing the system with the ability to make proper decisions. Current literature on collective artificial systems designs decision-making mechanisms inspired mostly by the successful natural systems. Nevertheless, most of the approaches focus on voting mechanisms and miss other fundamental aspects. In this paper, we aim to draw attention to the missed pieces for the design of efficient collective decision-making, mainly information processes in its two types of stimuli and options set.

2018

Novel design methodologies are often evaluated through empirical studies involving human designers. However, such empirical studies can incur a high personnel cost. Further, it can be difficult to isolate the effects of specific team or individual characteristics. These limitations could be bypassed by employing a computational model of design teams. This work introduces the Cognitively-Inspired Simulated Annealing Teams (CISAT) modeling framework, an agent-based platform that provides a means for efficiently simulating human design teams. A number of empirically demonstrated cognitive phenomena are modeled within the platform, striking a balance between model simplicity and direct applicability to engineering design problems. This paper discusses the composition of the CISAT modeling framework and demonstrates how it can be used to simulate the performance of human design teams in a cognitive study. Results simulated with CISAT are compared directly to the results derived from human designers. Finally, the CISAT model is also used to investigate the characteristics that were most and least helpful to teams during the cognitive study.

There is no presumption that a collective action of interacting agents leads to collectively satisfactory results without any central authority. Agents normally react to others' decisions, and the resulting volatile collective action is often far from being efficient. It is also common to exist a conflict between an individual and a collective. An agent wishes to maximize her own utility and a system designer wishes to implement a decentralized algorithm for maximizing the whole utility of a collective system. The system performance of interacting agents, however, crucially depends on the type of interactions among agents as well as how they adapt to others. We investigate how do interacting agents with heterogeneous preferences can generate an efficient collective action. We develop a model to examine the interaction between partner choice and an individual action. Agents choose their partners and also decide on a mode of behavior in interactions with partners. We show a collection of heterogeneous agents with diverse preference can realize the most efficient collective action by selecting their partners to interact. We also consider a collection of interacting agents with homogeneous preferences. We show a collection of homogeneous agents with the same preferences evolves into heterogeneous agents with diverse preferences by realizing the most efficient and equitable collective action.

Artificial Intelligence in Design'00, Kluwer, …, 2000

1. In this paper we refer to the experts in charge of creating design systems as developers, and to the experts that create design artifacts in a particular design domain as designers.

Multiagent Systems, Artificial Societies, and Simulated Organizations, 2003

AAAI Workshop on Computational Sustainability (AAAI 2015)

Saving energy is a major concern. Hence, it is fundamental to design and construct buildings that are energy-efficient. It is known that the early stage of architectural design has a significant impact on this matter. However, it is complex to create designs that are optimally energy efficient, and at the same time balance other essential criterias such as economics, space, and safety. One state-of-the art approach is to create parametric designs, and use a genetic algorithm to optimize across different objectives. We further improve this method, by aggregating the solutions of multiple agents. We evaluate diverse teams, composed by different agents; and uniform teams, composed by multiple copies of a single agent. We test our approach across three design cases of increasing complexity, and show that the diverse team provides a significantly larger percentage of optimal solutions than single agents.