Design Intention Inference for Virtual Co-Design Agents

Design Intention Inference for Virtual Co-Design Agents
复制标题

虚拟协同设计代理的设计意图推断

DOI:
10.1145/3383652.3423861
复制
发表时间:
2020
期刊:
IVA '20: Proceedings of the 20th ACM International Conference on Intelligent Virtual Agents
影响因子:
--
通讯作者:
Hoffman, Guy
Hoffman, Guy
中科院分区:
--
文献类型:
--
作者:
Law, Matthew V.;Kwatra, Amritansh;Dhawan, Nikhil;Einhorn, Matthew;Rajesh, Amit;Hoffman, Guy

文献摘要

参考文献

被引文献

相似文献

我们解决了通过与人类合作的智能虚拟代理来推断人类设计意图的挑战。首先,我们提出了一个动态贝叶斯网络模型,该模型将人类在探索问题空间期间的设计意图、目标和解决方案联系起来。然后,我们在搜索代理生成的设计行为上训练模型,并使用模型参数在真实人类行为的测试集中推断设计意图。我们发现,我们的模型能够在31.3%的时间内推断出与一系列设计结果相关的三个目标的确切意图。前两个预测的推理准确率为50.9%,前三个预测的推理准确率为67.2%。对于目标上的任何单一意图,模型的平均f1得分为0.719。这为智能虚拟代理纯粹从设计结果推断设计意图,从而与人类设计师建立联合意图提供了合理的基础。这些结果也揭示了使用模拟数据来训练人类设计意图模型的潜在好处和缺陷。
We address the challenge of inferring the design intentions of a human by an intelligent virtual agent that collaborates with the human. First, we propose a dynamic Bayesian network model that relates design intentions, objectives, and solutions during a human's exploration of a problem space. We then train the model on design behaviors generated by a search agent and use the model parameters to infer the design intentions in a test set of real human behaviors. We find that our model is able to infer the exact intentions across three objectives associated with a sequence of design outcomes 31.3% of the time. Inference accuracy is 50.9% for the top two predictions and 67.2% for the top three predictions. For any singular intention over an objective, the model's mean F1-score is 0.719. This provides a reasonable foundation for an intelligent virtual agent to infer design intentions purely from design outcomes toward establishing joint intentions with a human designer. These results also shed light on the potential benefits and pitfalls in using simulated data to train a model for human design intentions.
意图在认知机器人中的作用
DOI: 10.1007/978-3-319-31056-5_3
发表时间: 2016
期刊: Proceedings of the 2019 on Designing Interactive Systems Conference
影响因子: --
作者:
D. Vernon;Serge Thill;T. Ziemke
通讯作者: T. Ziemke
DOI: 10.1145/3322276.3322343
发表时间: 2019
期刊: Proceedings of the 2019 ACM Conference on Designing Interactive Systems
影响因子: --
作者:
Law, Matthew V.;Jeong, JiHyun;Kwatra, Amritansh;Jung, Malte F.;Hoffman, Guy
通讯作者: Hoffman, Guy
DOI: --
发表时间: 2011
期刊: Cognitive Science
影响因子: 2.5
作者:
Chris L. Baker;R. Saxe;J. Tenenbaum
通讯作者: Chris L. Baker;R. Saxe;J. Tenenbaum
什么是意图
DOI: 10.7551/mitpress/3839.003.0004
发表时间: 1987
期刊: Proceedings of the 2019 on Designing Interactive Systems Conference
影响因子: --
作者:
M. Bratman
通讯作者: M. Bratman
DOI: 10.1007/978-1-4471-6681-8_7
发表时间: 2015-01-01
期刊: CREATIVITY IN THE DIGITAL AGE
影响因子: --
作者:
Davis, Nicholas;Hsiao, Chih-Pin;Magerko, Brian
通讯作者: Magerko, Brian