图 书 馆
stair：斯坦福人工智能机器人项目STAIR: The STanford Artificial Intelligence Robot Project |
|
| 课程网址: | http://videolectures.net/ijcai09_ng_stair/ |
| 主讲教师: | Andrew Ng, |
| 开课单位: | 斯坦福大学 |
| 开课时间: | 2009-07-22 |
| 课程语种: | 英语 |
| 中文简介: |  此演讲将描述STAIR家庭助理机器人项目以及导致STAIR关键组件的卫星项目，例如（1）机器人抓取以前未知的物体，（2）从单个静止图像进行深度感知，（3）使用多模式传感器的实际目标识别，以及（4）集成AI的软件架构。自1956年诞生以来，AI的梦想一直是构建具有广谱能力和智能的系统。 STAIR重新审视了这个梦想，并寻求将来自学习，视觉，导航，操纵，计划以及语音和NLP的AI各个领域的工具集成到单个机器人平台上。这与30年来致力于零散的AI子领域的趋势形成鲜明对比，也代表着对其进行逆转的尝试。 STAIR的目标是使用一个有用的家庭助理机器人，从长远来看，我们设想一个机器人可以执行诸如整理房间，使用洗碗机，取放物品以及准备饭菜之类的任务。在本次演讲中，Ng将介绍我们让STAIR机器人从办公室周围取物品以及让STAIR盘点办公室物品的进展。具体来说，他将描述如何学会抓住以前看不见的物体（包括从洗碗机中卸下物品）；概率多分辨率地图，使机器人可以打开或使用门；以及一个机器人中央凹加周边视觉系统来进行物体识别和跟踪。 Ng还将概述一些主要技术思想，例如从单个静止图像中学习3D重建，以及用于机器人控制的强化学习算法，这些算法在启用这些STAIR组件中起着关键作用。 |
| 课程简介: | This talk will describe the STAIR home assistant robot project, and the satellite projects that led to key STAIR components such as (1) robotic grasping of previously unknown objects, (2) depth perception from a single still image, (3) practical object recognition using multimodal sensors, and (4) a software architecture for integrative AI. Since its birth in 1956, the AI dream has been to build systems that exhibit broad-spectrum competence and intelligence. STAIR revisits this dream, and seeks to integrate onto a single robot platform tools drawn from all areas of AI including learning, vision, navigation, manipulation, planning, and speech and NLP. This is in distinct contrast to, and also represents an attempt to reverse, the 30 year old trend of working on fragmented AI sub-fields. STAIR’s goal is a useful home assistant robot, and over the long term, we envision a single robot that can perform tasks such as tidying up a room, using a dishwasher, fetching and delivering items, and preparing meals. In this talk, Ng will describe our progress on having the STAIR robot fetch items from around the office, and on having STAIR take inventory of office items. Specifically, he’ll describe learning to grasp previously unseen objects (including unloading items from a dishwasher); probabilistic multi-resolution maps, which enable the robot to open or use doors; and a robotic foveal plus peripheral vision system for object recognition and tracking. Ng will also outline some of the main technical ideas - such as learning 3-D reconstructions from a single still image, and reinforcement learning algorithms for robotic control - that played key roles in enabling these STAIR components. |
| 关 键 词: | 人工智能; AI; 3D重建 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2020-03-31：zhouxj |
| 最后编审: | 2020-05-25：cxin |
| 阅读次数: | 84 |