Robust Object Estimation using Generative-Discriminative Inference for Secure Robotics Applications
Robust Object Estimation using Generative-Discriminative Inference for Secure Robotics Applications
复制标题
使用生成判别推理进行安全机器人应用的鲁棒对象估计
DOI：
10.1145/3240765.3243493
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
O. C. Jenkins
中科院分区：
文献类型：
--
作者：
Yanqi Liu;A. Costantini;R. I. Bahar;Zhiqiang Sui;Zhefan Ye;Shiyang Lu;O. C. Jenkins
卷积神经网络（cnn）在机器人领域的应用越来越广泛，尤其是在物体识别方面。然而，这样的cnn仍然缺乏机器人在不确定和潜在对抗的环境中正确感知和自主运行所必需的几个关键特性。在本文中，我们研究了准确、可靠和资源高效的目标和姿态识别的因素，适合机器人在对抗杂波中操作。我们的探索是在基于cnn的判别识别、生成概率估计和机器人操作的三阶段管道的背景下进行的。该管道提出使用采样网络密度过滤器或SAND过滤器，通过生成概率推理从CNN产生的潜在错误决策中恢复。我们展示了在桌面场景中具有良性和对抗性杂波的机器人操作的SAND滤波器感知的实验结果。这些实验改变了CNN模型用于对象识别的复杂性，并评估了可以通过生成姿态推理恢复的不准确性水平。这个场景被扩展到考虑对抗性的环境变化，包括不同的照明、遮挡和表面变化。
Convolutional neural networks (CNNs) are of increasing widespread use in robotics, especially for object recognition. However, such CNNs still lack several critical properties necessary for robots to properly perceive and function autonomously in uncertain, and potentially adversarial, environments. In this paper, we investigate factors for accurate, reliable, and resource-efficient object and pose recognition suitable for robotic manipulation in adversarial clutter. Our exploration is in the context of a three-stage pipeline of discriminative CNN-based recognition, generative probabilistic estimation, and robot manipulation. This pipeline proposes using a SAmpling Network Density filter, or SAND filter, to recover from potentially erroneous decisions produced by a CNN through generative probabilistic inference. We present experimental results from SAND filter perception for robotic manipulation in tabletop scenes with both benign and adversarial clutter. These experiments vary CNN model complexity for object recognition and evaluate levels of inaccuracy that can be recovered by generative pose inference. This scenario is extended to consider adversarial environmental modifications with varied lighting, occlusions, and surface modifications.