Generative state estimators based on probabilistic filters and smoothers are one of the most popular classes of state estimators for robots and autonomous vehicles. However, generative models have limited capacity to handle rich sensory observations, such as camera images, since they must model the entire distribution over sensor readings. Discriminative models do not suffer from this limitation, but are typically more complex to train as latent variable models for state estimation. We present an alternative approach where the parameters of the latent state distribution are directly optimized as a deterministic computation graph, resulting in a simple and effective gradient descent algorithm for training discriminative state estimators. We show that this procedure can be used to train state estimators that use complex input, such as raw camera images, which must be processed using expressive nonlinear function approximators such as convolutional neural networks. Our model can be viewed as a type of recurrent neural network, and the connection to probabilistic filtering allows us to design a network architecture that is particularly well suited for state estimation. We evaluate our approach on tracking task with raw image inputs. The results show significant improvement over both standard generative approaches and regular recurrent neural networks.

本文提出了一种基于确定性计算图的梯度下降算法，用于训练判别式状态估计器，该模型可以有效处理复杂的输入，如原始摄像头图像，并用于视觉里程计任务和合成跟踪任务中进行评估。

反向传播 Kalman 滤波器：学习判别式确定性状态估计器