Probable Multi-hypothesis Blind Spot Estimation for Driving Risk Prediction
Probable Multi-hypothesis Blind Spot Estimation for Driving Risk Prediction
复制标题
DOI：
10.1109/itsc.2019.8917490
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Takayuki Sugiura;Tomoki Watanabe
中科院分区：
文献类型：
--
作者：
Takayuki Sugiura;Tomoki Watanabe
我们提出了一种方法来估计自由空间和障碍物的盲点从一个单一的观点闭塞。有关盲点的知识有助于自动驾驶汽车做出更好的决策，例如避免可能的碰撞风险。它本质上是不适定的，以估计是否不可观察的区域被唯一指定为自由或被占用的空间。因此，我们的框架被设计成能够根据盲点环境的后验分布从单帧输入产生可能的多假设占用网格图（OGM）。与确定性的单一结果相比，每种假设OGM即使在不确定的区域也能明确地显示其他可能的环境。为了解决这个问题，我们引入了生成对抗网络（GAN）和蒙特卡洛采样的组合。我们的深度卷积神经网络（CNN）经过训练，可以对具有对抗性损失和丢弃层的近似后验分布进行建模。当在推理步骤中激活dropout时，网络通过Monte Carlo抽样从分布中抽样生成不同的多假设OGM。我们证明，该方法估计不同的闭塞自由空间和障碍物在多假设OGM从二维（2D）的距离传感器测量或单目摄像机图像。我们的方法也可以检测到车辆前方的盲点作为驾驶风险在真实的户外数据集。
We present a method for estimating free spaces and obstacles in blind spots occluded from a single view. Knowledge about blind spots helps autonomous vehicles make better decisions, such as avoiding a probable collision risk. It is essentially ill-posed to estimate whether unobservable areas are uniquely assigned as free or occupied spaces. Therefore, our framework is designed to be able to produce probable multi-hypothesis occupancy grid maps (OGM) from a single-frame input based on posterior distribution of blind spot environments. Compared to deterministic single result, each hypothesis OGM can show other probable environments explicitly even in uncertain areas. In order to handle this, we introduce a combination of generative adversarial networks (GANs) and Monte Carlo sampling. Our deep convolutional neural network (CNN) is trained to model an approximate posterior distribution with an adversarial loss and dropout layers. While activating dropout even at inference step, the network generates diverse multi-hypothesis OGMs sampled from the distribution by Monte Carlo sampling. We demonstrate that the proposed method estimates diverse occluded free spaces and obstacles in multi-hypothesis OGMs from either a two-dimensional (2D) range sensor measurement or a monocular camera image. Our method can also detect blind spots ahead of vehicle as driving risks in real outdoor dataset.