Maximally informative interaction learning for scene exploration
Maximally informative interaction learning for scene exploration
复制标题
用于场景探索的最大信息交互学习
DOI：
--
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
Jan Peters
中科院分区：
文献类型：
--
作者：
H. V. Hoof;Oliver Kroemer;H. B. Amor;Jan Peters
创造能够在动态、非结构化环境中自主行动的机器人是一项重大挑战。在这样的环境中，学习识别和操纵新物体是一种重要的能力。一个真正的自主机器人通过与环境的交互来获取知识，而不使用机器人或编码人类领域洞察力的先验信息。静态图像通常提供不足以用于推断场景中的对象的相关属性的信息。因此，机器人需要通过与它们交互来探索这些对象。然而，可能存在许多可能的探索性操作，并且这些操作中的大部分可能是非信息性的。为了快速有效地学习，机器人必须选择预期具有最多信息结果的动作。在所提出的自下而上的方法中，机器人通过量化其自身动作的预期信息量来实现这一目标。我们使用这种方法将场景分割成其组成对象，作为学习对象的属性和启示的第一步。评估表明，所提出的信息理论方法允许机器人有效地推断其环境的复合结构。
Creating robots that can act autonomously in dynamic, unstructured environments is a major challenge. In such environments, learning to recognize and manipulate novel objects is an important capability. A truly autonomous robot acquires knowledge through interaction with its environment without using heuristics or prior information encoding human domain insights. Static images often provide insufficient information for inferring the relevant properties of the objects in a scene. Hence, a robot needs to explore these objects by interacting with them. However, there may be many exploratory actions possible, and a large portion of these actions may be non-informative. To learn quickly and efficiently, a robot must select actions that are expected to have the most informative outcomes. In the proposed bottom-up approach, the robot achieves this goal by quantifying the expected informativeness of its own actions. We use this approach to segment a scene into its constituent objects as a first step in learning the properties and affordances of objects. Evaluations showed that the proposed information-theoretic approach allows a robot to efficiently infer the composite structure of its environment.