4.3 Article Proceedings Paper

A study of argumentation-based negotiation in collaborative design

出版社

CAMBRIDGE UNIV PRESS
DOI: 10.1017/S0890060409990151

关键词

Argumentation; Collaborative Design; Experiment Study; Negotiation

向作者/读者索取更多资源

Engineering of complex systems often involves teamwork. The members of an engineering team must Work to-ether to identify design requirements, explore design spaces, generate design alternatives, and make both interactive and joint design decisions. Because of the latency of information and the disciplinary differences, it is often a difficult process for the members of a team to reach agreements when needed. Negotiation has been studied as a method for facilitating information exchange, mutual understanding, and joint decision making. An argumentation-based negotiation approach was previously proposed by the authors to support collaborative engineering design. In this paper, we present in experiment study that Was conducted to evaluate the impact of this negotiation support approach oil the process and the outcome of collaborative design. The results of the experiment show both positive effects and limitations of the approach.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.3
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

Article Engineering, Mechanical

Data Driven Uncertainty Evaluation for Complex Engineered System Design

Liu Boyuan, Huang Shuangxi, Fan Wenhui, Xiao Tianyuan, James Humann, Lai Yuyang, Jin Yan

CHINESE JOURNAL OF MECHANICAL ENGINEERING (2016)

Article Engineering, Mechanical

Effect of Social Structuring in Self-Organizing Systems

Newsha Khani, James Humann, Yan Jin

JOURNAL OF MECHANICAL DESIGN (2016)

Article Computer Science, Artificial Intelligence

Reinforcement learning-based collision avoidance: impact of reward function and knowledge transfer

Xiongqing Liu, Yan Jin

AI EDAM-ARTIFICIAL INTELLIGENCE FOR ENGINEERING DESIGN ANALYSIS AND MANUFACTURING (2020)

Article Computer Science, Artificial Intelligence

Evaluating the learning and performance characteristics of self-organizing systems with different task features

Hao Ji, Yan Jin

Summary: Self-organizing systems (SOS) are developed for complex tasks in unforeseen situations, using a multiagent reinforcement learning (RL) model to solve the rule generation problem. A rotation reward function is introduced to regulate agent behavior and different weights of such reward are tested on SOS performance in two case studies. Three metrics are proposed to evaluate SOS: learning stability, quality of knowledge, and scalability, showing that optimal weights of rotation reward can enhance agent learning capability.

AI EDAM-ARTIFICIAL INTELLIGENCE FOR ENGINEERING DESIGN ANALYSIS AND MANUFACTURING (2021)

Article Computer Science, Interdisciplinary Applications

Knowledge Acquisition of Self-Organizing Systems With Deep Multiagent Reinforcement Learning

Hao Ji, Yan Jin

Summary: This paper proposes a multiagent reinforcement learning-based model for solving the rule generation problem in complex SOS tasks. Through investigating team sizes and task variations, it is found that there is an optimal range for the number of agents in a team to achieve good learning stability. The learned knowledge shows strong robustness to external noises.

JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN ENGINEERING (2022)

Article Computer Science, Interdisciplinary Applications

Engineering Document Summarization: A Bidirectional Language Model-Based Approach

Yunjian Qiu, Yan Jin

Summary: This study investigates extractive summarization using sentence embeddings generated by finetuned BERT models and the k-means clustering method. The results demonstrate that BERT models, when finetuned with domain-specific datasets, can generate summaries with more domain terminologies and better content overlap with original documents than other non-BERT-based models.

JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN ENGINEERING (2022)

Article Engineering, Mechanical

Exploring Visual Cues for Design Analogy: A Deep Learning Approach

Zijian Zhang, Yan Jin

Summary: The goal of this research is to develop a computer-aided visual analogy support framework to enhance designers' visual analogical thinking by providing relevant visual cues. This study focuses on developing a computational framework and conducting human-based behavioral studies to validate visual cue exploration tools. A visual cue exploration framework and deep clustering model are proposed to reveal shape patterns of sketches and cluster them for preserving category information.

JOURNAL OF MECHANICAL DESIGN (2022)

Article Computer Science, Artificial Intelligence

Social learning in self-organizing systems for complex assembly tasks

Bingling Huang, Yan Jin

Summary: Self-organizing systems have the potential to adapt and handle system degradations. Integrating social learning into multiagent reinforcement learning can improve training and task performance.

ADVANCED ENGINEERING INFORMATICS (2023)

Article Engineering, Mechanical

Document Understanding-Based Design Support: Application of Language Model for Design Knowledge Extraction

Yunjian Qiu, Yan Jin

Summary: In this study, a method for extracting design knowledge from documents is proposed, which utilizes a specific domain labeled dataset to fine-tune a BERT model. The method also uncovers internal relationships and definitions to enhance understanding. The case study demonstrates the effectiveness of this approach in extracting relevant design knowledge points.

JOURNAL OF MECHANICAL DESIGN (2023)

Article Computer Science, Artificial Intelligence

Reward shaping in multiagent reinforcement learning for self-organizing systems in assembly tasks

Bingling Huang, Yan Jin

Summary: This paper investigates the impact of reward shaping in the context of an L-shape assembly task. The experimental results show that reward shaping can be highly effective for training agent teams, but the singularities, proper forms, and suitable gradients of the shaping fields are essential for successful training, and the effectiveness of reward shaping functions also highly depends on the size of agent teams.

ADVANCED ENGINEERING INFORMATICS (2022)

Article Computer Science, Artificial Intelligence

Data-enabled sketch search and retrieval for visual design stimuli generation

Zijian Zhang, Yan Jin

Summary: This paper proposes a computational framework for searching and retrieving visual stimulation cues to help designers generate more creative ideas. By using a deep neural network model and a cluster detection-based method, visual relationships between different categories of sketches can be discovered and quantified, effectively ranking the categories.

AI EDAM-ARTIFICIAL INTELLIGENCE FOR ENGINEERING DESIGN ANALYSIS AND MANUFACTURING (2022)

Proceedings Paper Computer Science, Interdisciplinary Applications

Enhance the Simulation of Architecture and Engineering Design Process: A Data-Driven Based Approach

Yu Hou, Lucio Soibelman, Yan Jin

COMPUTING IN CIVIL ENGINEERING 2019: VISUALIZATION, INFORMATION MODELING, AND SIMULATION (2019)

Proceedings Paper Engineering, Industrial

MODELING TRUST IN SELF-ORGANIZING SYSTEMS WITH HETEROGENEITY

Hao Ji, Yan Jin

PROCEEDINGS OF THE ASME INTERNATIONAL DESIGN ENGINEERING TECHNICAL CONFERENCES AND COMPUTERS AND INFORMATION IN ENGINEERING CONFERENCE, 2018, VOL 7 (2018)

Proceedings Paper Engineering, Electrical & Electronic

Use of Situation and Risk Modeling in Guidance Solutions

Edwin A. Williams, Yan Jim

2018 IEEE/ION POSITION, LOCATION AND NAVIGATION SYMPOSIUM (PLANS) (2018)

Article Computer Science, Artificial Intelligence

A quantitative approach to design alternative evaluation based on data-driven performance prediction

Zi-jian Zhang, Lin Gong, Yan Jin, Jian Xie, Jia Hao

ADVANCED ENGINEERING INFORMATICS (2017)

暂无数据