论文标题
互动语言：实时与机器人交谈
Interactive Language: Talking to Robots in Real Time
论文作者
论文摘要
我们提出了一个框架，用于在现实世界中构建交互式，实时，自然的可实施机器人，并开放相关资产（数据集，环境，基准和政策）。在数十万个语言轨迹的数据集上进行了行为克隆培训，制定的政策可以熟练地执行比以前的作品更大的命令：具体来说，我们估计，我们在87,000个独特的自然语言中估计，在87,000个独特的自然语言串上，指定原始的端端到端到端的Visuo-Linguo-linguo-Motor技能。我们发现，同一政策能够通过实时语言被人类指导，以解决广泛的精确的长远重排目标，例如“用块来弄清楚笑脸”。我们发布的数据集包含近600,000个语言标记的轨迹，该轨迹比以前可用的数据集大的数量级。我们希望所证明的结果和相关资产能够进一步发展有用，有能力，自然的可互关系机器人。请参阅https://interactive-language.github.io的视频。
We present a framework for building interactive, real-time, natural language-instructable robots in the real world, and we open source related assets (dataset, environment, benchmark, and policies). Trained with behavioral cloning on a dataset of hundreds of thousands of language-annotated trajectories, a produced policy can proficiently execute an order of magnitude more commands than previous works: specifically we estimate a 93.5% success rate on a set of 87,000 unique natural language strings specifying raw end-to-end visuo-linguo-motor skills in the real world. We find that the same policy is capable of being guided by a human via real-time language to address a wide range of precise long-horizon rearrangement goals, e.g. "make a smiley face out of blocks". The dataset we release comprises nearly 600,000 language-labeled trajectories, an order of magnitude larger than prior available datasets. We hope the demonstrated results and associated assets enable further advancement of helpful, capable, natural-language-interactable robots. See videos at https://interactive-language.github.io.
