arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.00326cs.CVcs.RO
收藏

PERCH 2.0:通过搜索物体姿态估计实现快速准确的基于GPU的感知

PERCH 2.0 : Fast and Accurate GPU-based Perception via Search for Object Pose Estimation

The Robotics Institute, Carnegie Mellon University(卡内基梅隆大学机器人研究所)

Aditya Agarwal, Yupeng Han, Maxim Likhachev

摘要:

已知物体的位姿估计是机器人抓取和操纵等任务的基础。可靠抓取的需要对动态环境中的杂乱、遮挡场景中的姿态估计提出了严格的精度要求。现代方法采用大量的训练数据来学习特征,以便找到3D模型和观察数据之间的对应关系。然而,这些方法需要大量的地面实况姿态注释。另一种方法是使用算法,在可能的渲染场景空间中搜索观察到的场景的最佳解释。最近开发的算法,PERCH(PERception通过SeaRCH)这样做,使用深度数据收敛到一个全局最优的解决方案,使用搜索一个专门构造的树。虽然PERCH提供了强有力的保证准确性,目前的配方遭受低的可扩展性,由于其高运行时间。此外,仅依赖于用于姿态估计的深度数据将该算法限制于其中没有两个对象具有相同形状的场景。在这项工作中,我们提出了PERCH 2.0,一种新的感知通过搜索策略,利用GPU加速和RGB数据。我们表明,我们的方法可以实现100倍的速度比PERCH,以及更好的准确性比国家的最先进的数据驱动的方法对6自由度姿态估计,而不需要注释地面实况构成的训练数据。我们的代码和视频可以在https://sbpl-cruz.github.io/perception/上找到。

英文摘要:

Pose estimation of known objects is fundamental to tasks such as robotic grasping and manipulation. The need for reliable grasping imposes stringent accuracy requirements on pose estimation in cluttered, occluded scenes in dynamic environments. Modern methods employ large sets of training data to learn features in order to find correspondence between 3D models and observed data. However these methods require extensive annotation of ground truth poses. An alternative is to use algorithms that search for the best explanation of the observed scene in a space of possible rendered scenes. A recently developed algorithm, PERCH (PErception Via SeaRCH) does so by using depth data to converge to a globally optimum solution using a search over a specially constructed tree. While PERCH offers strong guarantees on accuracy, the current formulation suffers from low scalability owing to its high runtime. In addition, the sole reliance on depth data for pose estimation restricts the algorithm to scenes where no two objects have the same shape. In this work, we propose PERCH 2.0, a novel perception via search strategy that takes advantage of GPU acceleration and RGB data. We show that our approach can achieve a speedup of 100x over PERCH, as well as better accuracy than the state-of-the-art data-driven approaches on 6-DoF pose estimation without the need for annotating ground truth poses in the training data. Our code and video are available at https://sbpl-cruz.github.io/perception/.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑