11 2020 档案
摘要：Review of Deep Reinforcement Learning for Robot Manipulation Abstract—Reinforcement learning combined with neural net- works has recently led to a wid
阅读全文
摘要：Improving Grounded Natural Language Understanding through Human-Robot Dialog Abstract—Natural language understanding for robotics canrequire substanti
阅读全文
摘要：One-Shot Imitation Learning 项目·地址：Robots that Learn (openai.com) 一眼模仿学习 Imitation learning has been commonly applied to solve different tasks in isola
阅读全文
摘要：Learning Generalizable Surface Cleaning Actions from Demonstration 通过演示学习通用的表面清洁措施 Abstract— When surveyed, potential users often report cleaning as a
阅读全文
摘要：Survey of Model-Based Reinforcement Learning: Applications on Robotics Abstract Reinforcement learning is an appealing approach for allowing robots to
阅读全文
摘要：A Robot 3C Assembly Skill Learning Method by Intuitive Human Demonstration 随着因特网和计算机技术的发展，对诸如手机的3C产品的需求激增。同时，由于人工成本的不断提高，迫切需要使用工业机器人使3C装配线自动化。本文的目的是提出
阅读全文
摘要：One-Shot Visual Imitation Learning via Meta-Learning 通过元学习进行一站式视觉模仿学习 In order for a robot to be a generalist that can perform a wide range of jobs, i
阅读全文
摘要：Unsupervised Visual-Linguistic Reference Resolution in Instructional Videos We propose an unsupervised method for reference res-olution in instruction
阅读全文
摘要：PURPOSIVE VISUAL IMITATION FOR LEARNING STRUCTURED TASKS FROM VIDEOS ADISSERTATION 有目的的视觉模仿，以学习视频中的结构化任务 我们提出有目的的视觉模仿，从视频中了解演示者的目标和意图。 我们证明，与从视频中学习低级轨
阅读全文
摘要：LINS: A Lidar-Inertial State Estimator for Robust and Efficient Navigation LINS：用于鲁棒高效导航的激光雷达惯性状态估计器 —我们介绍了LINS，它是一种轻量级的激光雷达惯性状态估计器，用于实时自我运动估计。 所提出的方法
阅读全文
摘要：基于目标的模仿学习的运动推理 Motion Reasoning for Goal-Based Imitation Learning De-An Huang1,2, Yu-Wei Chao∗,2, Chris Paxton∗,2, Xinke Deng2,3,Li Fei-Fei1, Juan Car
阅读全文
摘要：[7]. Augmenting GAIL with BC for sample efficient imitation learning 作者: Rohit Kumar Jena (Carnegie Mellon University)*; Changliu Liu (Carnegie Mellon
阅读全文
摘要：Robot Learning from Demonstration by Constructing Skill Trees 通过构建技能树从演示中学习机器人 我们描述了CST，这是一种根据演示轨迹构建技能树的在线算法。 CST将演示轨迹划分为组件技能链，其中每个技能都有一个目标，并从抽象库中分配了合
阅读全文
