0


机器人向人类教师学习

Robots learning from human teachers
课程网址: http://videolectures.net/rldm2015_thomaz_human_teachers/  
主讲教师: Andrea Thomaz
开课单位: 乔治亚理工学院
开课时间: 2015-07-28
课程语种: 英语
中文简介:
在这次演讲中,我介绍了乔治亚理工大学社会智能机器实验室的最新工作。我们研究的愿景是使机器人能够在真实的人类环境中工作;例如,服务机器人在家帮忙,同事机器人革命制造业,辅助机器人赋予医疗工作者权力,让老年人在家里活得更长。要做到这一点,我们需要建造智能机器人,这些机器人可以嵌入人类环境中,与日常生活中的人们进行互动。迄今为止,机器人技术的许多成功都依赖于结构化环境和可重复的任务,但所有这些设想的共同点是将机器人部署到动态人类环境中,而在这种环境中,预先编程的控制器将不是一种选择。这些机器人需要与最终用户交互,以便了解他们在工作中需要做什么。我们的研究目的是对人类社会学习的机制进行计算建模,以便建造机器人和其他直观的机器供人们教学。我们采用机器学习交互,重新设计界面和算法,以支持从最终用户而不是ML专家收集学习输入。本演讲涵盖了使用仿人机器人平台为高级任务目标学习、低级技能学习和主动学习交互构建交互模型的结果。
课程简介: In this talk I present recent work from the Socially Intelligent Machines Lab at Georgia Tech. The vision of our research is to enable robots to function in real human environments; such as, service robots helping at home, co-worker robots to revolutionize manufacturing, and assistive robots empowering healthcare workers and enabling aging adults to live longer in their homes. To do this, we need to build intelligent robots that can be embedded into human environments to interact with everyday people. Many of the successes of robotics to date rely on structured environments and repeatable tasks, but what all of these visions have in common is deploying robots into dynamic human environments where pre-programmed controllers won’t be an option. These robots will need to interact with end users in order to learn what they need to do on-the-job. Our research aims to computationally model mechanisms of human social learning in order to build robots and other machines that are intuitive for people to teach. We take Machine Learning interactions and redesign interfaces and algorithms to support the collection of learning input from end users instead of ML experts. This talk covers results on building models of reciprocal interactions for high-level task goal learning, low-level skill learning, and active learning interactions using humanoid robot platforms.
关 键 词: 智能机器; 最终用户交互; 计算建模
课程来源: 视频讲座网
数据采集: 2021-11-20:zkj
最后编审: 2021-11-20:zkj
阅读次数: 33