论文标题
在3D环境中学习互动探索的负担能力景观
Learning Affordance Landscapes for Interaction Exploration in 3D Environments
论文作者
论文摘要
在人类空间中运行的体现代理必须能够掌握其环境的工作方式：代理可以使用哪些对象，以及如何使用它们？我们介绍了一种互动探索的增强学习方法，从而自主地发现了新的未覆盖3D环境（例如一个陌生的厨房）的负担得起的景观。给定以Egbb-D相机和高级动作空间的依据，该代理因最大程度地提高了成功的互动而获得奖励，同时训练基于图像的负担能力分割模型。前者产生了在新环境中有效采取行动以准备下游相互作用任务的政策，而后者产生了卷积神经网络，该卷积神经网络将图像区域映射到它们允许的每个动作的可能性，从而使探索的奖励密不可分。我们用ai2-ithor演示了我们的想法。结果表明，代理商可以学习如何智能使用新的家庭环境，并准备好迅速解决各种下游任务，例如“找到刀并将其放在抽屉里”。项目页面：http：//vision.cs.utexas.edu/projects/interaction-exploration/
Embodied agents operating in human spaces must be able to master how their environment works: what objects can the agent use, and how can it use them? We introduce a reinforcement learning approach for exploration for interaction, whereby an embodied agent autonomously discovers the affordance landscape of a new unmapped 3D environment (such as an unfamiliar kitchen). Given an egocentric RGB-D camera and a high-level action space, the agent is rewarded for maximizing successful interactions while simultaneously training an image-based affordance segmentation model. The former yields a policy for acting efficiently in new environments to prepare for downstream interaction tasks, while the latter yields a convolutional neural network that maps image regions to the likelihood they permit each action, densifying the rewards for exploration. We demonstrate our idea with AI2-iTHOR. The results show agents can learn how to use new home environments intelligently and that it prepares them to rapidly address various downstream tasks like "find a knife and put it in the drawer." Project page: http://vision.cs.utexas.edu/projects/interaction-exploration/
