This paper presents the first active object mapping framework for complex robotic grasping tasks. The framework is built on an object SLAM system integrated with a simultaneous multi-object pose estimation process. Aiming to reduce the observation uncertainty on target objects and increase their pose estimation accuracy, we also design an object-driven exploration strategy to guide the object mapping process. By combining the mapping module and the exploration strategy, an accurate object map that is compatible with robotic grasping can be generated. Quantitative evaluations also show that the proposed framework has a very high mapping accuracy. Manipulation experiments, including object grasping, object placement, and the augmented reality, significantly demonstrate the effectiveness and advantages of our proposed framework.

翻译：本文件介绍了用于复杂机器人掌握任务的首个主动物体绘图框架。框架建在目标物体SLAM系统上,结合一个同时的多物体构成估计过程。为了减少目标物体的观测不确定性并提高其构成估计的准确性,我们还设计了一个由物体驱动的勘探战略,以指导物体绘图进程。通过将绘图模块和勘探战略结合起来,可以产生一个与机器人掌握相符的准确的物体地图。定量评估还表明,拟议的框架具有很高的绘图准确性。操纵实验,包括物体捕捉、物体放置和扩大的现实,极大地显示了我们拟议框架的有效性和优势。