论文标题
样本-HD：同时采取行动和运动计划学习环境
SAMPLE-HD: Simultaneous Action and Motion Planning Learning Environment
论文作者
论文摘要
人类表现出高水平的多模式理解 - 将视觉线索与阅读或听到的知识相结合，对我们来说很容易，并且可以与周围环境进行非常准确的互动。各种仿真环境着重于为与场景理解，问答，空间探索，视觉导航有关的任务提供数据。在这项工作中，我们提供了一种解决方案，可以在新环境中涵盖模拟的视觉和行为方面，以在操作设置中学习交互推理。样品-HD环境允许生成由小型家庭对象组成的各种场景，以过程制作语言说明进行操纵，并生成作为培训数据的地面真相路径。
Humans exhibit incredibly high levels of multi-modal understanding - combining visual cues with read, or heard knowledge comes easy to us and allows for very accurate interaction with the surrounding environment. Various simulation environments focus on providing data for tasks related to scene understanding, question answering, space exploration, visual navigation. In this work, we are providing a solution to encompass both, visual and behavioural aspects of simulation in a new environment for learning interactive reasoning in manipulation setup. SAMPLE-HD environment allows to generate various scenes composed of small household objects, to procedurally generate language instructions for manipulation, and to generate ground truth paths serving as training data.
