CRII: CPS: A Bi-Trust Framework for Collaboration-Quality Improvement in Human-Robot Collaborative Contexts

协作机器人在越来越多的领域被广泛应用于协助人类。就像人与人之间的合作一样，人与人之间的信任也具有双向性。然而，在人-机器人协作的统一框架下，对人-信任机器人问题和机器人-信任人问题的研究却很少。该项目通过开发一个新的系统Bi-Trust框架来解决这一挑战，将人类对机器人的信任和机器人对人类的信任整合到人机协作过程中。在建立的Bi-Trust框架的基础上，建立了基于信任的计算协作模型，对机器人的动作进行优化和规划。提出的方法将减少不确定故障，提高人机共享任务的协作质量。该项目的目标是为人机团队开发一个系统的双信任框架，并创建信任动态和基于信任级别的协作的新计算模型，以增强人机伙伴关系。拟开展的研究活动包括：(1)研究影响人类对机器人信任的因素，利用多模态物理和生理数据分析人类对机器人的信任；(2)建立了基于人机团队的计算人-信任-机器人模型和机器人-信任-人模型的新型Bi-Trust框架，并通过trust-local-maximum方法建立了计算人-机器人协作模型；(3)将Bi-Trust框架应用于真实的人机协作环境并评估其有效性。该项目的研究结果将提高新一代智能制造等协作环境中人机团队的协作质量，并可能通过培养越来越多的机器人和人工智能劳动力来促进国民经济增长。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

Collaborative robots have been widely employed to assist humans in an increasing number of areas. Just as human-human collaboration, the trust in human-robot teams has a property of bidirectional. However, few studies have been conducted on both human-trusting-robot issue and robot-trusting-human issue in a unified framework for human-robot collaboration. The project addresses this challenge by developing a new systematic Bi-Trust framework to integrate humans’ trust in robots and robots’ trust in humans into the human-robot collaboration process. With the established Bi-Trust framework, a trust-level-based computational collaboration model is created to optimize and plan robot actions. The proposed approaches will reduce uncertain failures and improve the collaboration-quality of human-robot shared tasks.The goal of this project is to develop a systematic Bi-Trust framework for human-robot teams and create new computational models of trust dynamics and trust-level-based collaboration in order to enhance the human-robot partnership. The proposed research activities include: (1) investigating the factors that affect humans’ trust in robots and analyzing humans’ trust using multimodal physical and physiological data; (2) developing a new Bi-Trust framework entailing computational human-trusting-robot model and robot-trusting-human model for human-robot teams and establishing a computational human-robot collaboration model via the trust-local-maximum method; and (3) applying the Bi-Trust framework in real-world human-robot collaborative contexts and assessing its effectiveness. The findings of this project will improve the collaboration-quality for human-robot teams in collaborative contexts such as the new generation of smart manufacturing and potentially benefit the national economic growth by fostering increasing robotics and AI workforce.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.