Multimodal emotional intelligence for robots

机器人的多模态情感智能

• 批准号: RGPIN-2019-06908
• 负责人: Lim, Angelica
• 金额: $ 1.68万
• 依托单位: Simon Fraser University
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2022
• 资助国家: 加拿大
• 起止时间: 2022-01-01 至 2023-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=750568
• 关键词: Multimodal; emotional; intelligence; robots

The SFU Rosie Lab (Robots with Social Intelligence and Empathy) aims to build robots and digital agents that can accurately identify our emotions and respond appropriately, towards seamless and humanistic interactions. According to a recent study of college students, empathy has decreased by over 40% over the last 30 years [1]. Researchers suggest that one likely contributor is high consumption of new media and technology through interfaces such as smartphones. What if technology and interfaces could be more human, instead of humans adapting to technology? What if machines could interact with compassion and kindness? Voice-activated digital assistants such as Amazon Echo and Siri are taking the world by storm, and personal robots are poised to be the next generation of helpful devices. In 2017, a study found that people expect the ideal personal robot to be more friendly, soft, honest, trustworthy, gentle, nice, peaceful, competent, happy, emotional, and sensitive compared to a general robot [2]. The proposed research aims to develop software necessary to build these friendly personal robots. Our software will be able to detect common social signals, such as boredom, excitement, frustration or curiosity. Using this software, and in collaboration with psychology labs, we aim to study how this interactive, empathetic technology can improve our happiness, well-being and social connectedness. Like Rosie the Robot from the Jetsons, the resulting robots are anticipated to be useful in domains such as healthcare and therapy, elder care, and education. Furthermore, we aim to build artificial intelligence software in a way that aligns with Canadian values, considering a diversity of expressions rather than one-size-fits-all. Finally, the students trained in the Rosie Lab will be uniquely poised to bring their specialized knowledge of emotion-aware computing to Canada's technological companies and the world. [1] Konrath, S. H., O'Brien, E. H., & Hsing, C. (2011). Changes in Dispositional Empathy in American College Students Over Time: A Meta-Analysis. Personality and Social Psychology Review, 15(2), 180-198. https://doi.org/10.1177/1088868310377395 [2] Kuhnert, B., Ragni, M., & Lindner, F. (2017). The gap between human's attitude towards robots in general and human's expectation of an ideal everyday life robot. In Robot and Human Interactive Communication (RO-MAN), 2017 26th IEEE International Symposium on (pp. 1102-1107).

SFU Rosie Lab（具有社交智能和同理心的机器人）旨在构建能够准确识别我们的情绪并做出适当反应的机器人和数字代理，实现无缝和人性化的互动。 根据最近对大学生的一项研究，在过去的30年里，同情心下降了40%以上[1]。研究人员认为，一个可能的原因是通过智能手机等界面对新媒体和技术的高消费。如果技术和界面可以更人性化，而不是人类适应技术呢？如果机器可以与同情和善良互动呢？亚马逊Echo和Siri等声控数字助理正在席卷全球，个人机器人有望成为下一代有用的设备。2017年，一项研究发现，与一般机器人相比，人们期望理想的个人机器人更友好，柔软，诚实，值得信赖，温柔，善良，和平，有能力，快乐，情感和敏感。这项研究的目的是开发必要的软件来构建这些友好的个人机器人。我们的软件将能够检测常见的社交信号，如无聊、兴奋、沮丧或好奇。使用这个软件，并与心理学实验室合作，我们的目标是研究这种互动的，同情的技术如何提高我们的幸福感，幸福感和社会联系。就像来自Jetsons的Rosie机器人一样，由此产生的机器人预计将在医疗保健和治疗，老年人护理和教育等领域有用。此外，我们的目标是以符合加拿大价值观的方式构建人工智能软件，考虑表达的多样性，而不是一刀切。最后，在罗西实验室接受培训的学生将有能力将他们在情感感知计算方面的专业知识带到加拿大的科技公司和世界。[1]Konrath，S. H、奥布莱恩，E. H、& Hsing，C.（2011年）。随着时间的推移，美国大学生的性格移情变化：一项荟萃分析。Personality and Social Psychology Review，15（2），180-198. https://doi.org/10.1177/1088868310377395 Kuhnert，B.，Ragni，M.，& Lindner，F.（2017年）。人类对机器人的总体态度与人类对理想的日常生活机器人的期望之间的差距。在机器人和人类交互通信（RO-MAN），2017年第26届IEEE国际研讨会上（pp. 1102-1107）。