Our goal is to train a policy for autonomous driving via imitation learning that is robust enough to drive a real vehicle. We find that standard behavior cloning is insufficient for handling complex driving scenarios, even when we leverage a perception system for preprocessing the input and a controller for executing the output on the car: 30 million examples are still not enough. We propose exposing the learner to synthesized data in the form of perturbations to the expert's driving, which creates interesting situations such as collisions and/or going off the road. Rather than purely imitating all data, we augment the imitation loss with additional losses that penalize undesirable events and encourage progress -the perturbations then provide an important signal for these losses and lead to robustness of the learned model. We show that the ChauffeurNet model can handle complex situations in simulation, and present ablation experiments that emphasize the importance of each of our proposed changes and show that the model is responding to the appropriate causal factors. Finally, we demonstrate the model driving a real car at our test facility.

No abstract

Monte Carlo simulation studies are performed to examine the implications of octahedral cation (Fe, Mo) site disorder for magnetization in the double-perovskite Sr2FeMoO6. Correlations between the near-neighbor cation distributions and the spin distributions are identified to gain insight into the spin arrangement within, and on the periphery of a given transition element cation cluster. It is shown that the drop in the magnetic moment is nearly linear with the increase in the mis-site defect concentration for the case of randomly created defects. Implications of the concomitant presence of mis-site defects and oxygen vacancies are also analyzed.

Our goal is to train a policy for autonomous driving via imitation learning that is robust enough to drive a real vehicle. We find that standard behavior cloning is insufficient for handling complex driving scenarios, even when we leverage a perception system for preprocessing the input and a controller for executing the output on the car: 30 million examples are still not enough. We propose exposing the learner to synthesized data in the form of perturbations to the expert's driving, which creates interesting situations such as collisions and/or going off the road. Rather than purely imitating all data, we augment the imitation loss with additional losses that penalize undesirable events and encourage progress -the perturbations then provide an important signal for these losses and lead to robustness of the learned model. We show that the ChauffeurNet model can handle complex situations in simulation, and present ablation experiments that emphasize the importance of each of our proposed changes and show that the model is responding to the appropriate causal factors. Finally, we demonstrate the model driving a car in the real world.

Investigation on switching kinetics in epitaxial Pb ( Zr 0.2 Ti 0.8 ) O 3 ferroelectric thin films: Role of the 90°d omain walls

Pedestrian detection has been an important problem for decades, given its relevance to a number of applications in robotics, including driver assistance systems, road scene understanding and surveillance systems. The two main practical requirements for fielding such systems are very high accuracy and real-time speed: we need pedestrian detectors that are accurate enough to be relied on and are fast enough to run on systems with limited compute power. This paper addresses both of these requirements by combining very accurate deep-learning-based classifiers within very efficient cascade classifier frameworks.Deep neural networks (DNN) have been shown to excel at classification tasks [5], and their ability to operate on raw pixel input without the need to design special features is very appealing. However, deep nets are notoriously slow at inference time. In this paper, we propose an approach that cascades deep nets and fast features, that is both very fast and accurate. We apply it to the challenging task of pedestrian detection. Our algorithm runs in real-time at 15 frames per second (FPS). The resulting approach achieves a 26.2% average miss rate on the Caltech Pedestrian detection benchmark, which is the first work we are aware of that achieves high accuracy while running in real-time.To achieve this, we combine a fast cascade [2] with a cascade of classifiers, which we propose to be DNNs. Our approach is unique, as it is the only one to produce a pedestrian detector at real-time speeds (15 FPS) that is also very accurate. Figure 1 visualizes existing methods as plotted on the accuracy -computational time axis, measured on the challenging Caltech pedestrian detection benchmark [4]. As can be seen in this figure, our approach is the only one to reside in the high accuracy, high speed region of space, which makes it particularly appealing for practical applications.Fast Deep Network Cascade. Our main architecture is a cascade structure in which we take advantage of the fast features for elimination, VeryFast [2] as an initial stage and combine it with small and large deep networks [1,5] for high accuracy. The VeryFast algorithm is a cascade itself, but of boosting classifiers. It reduces recall with each stage, producing a high average miss rate in the end. Since the goal is eliminate many non-pedestrian patches and at the same time keep the recall high, we used only 10% of the stages in that cascade. Namely, we use a cascade of only 200 stages, instead of the 2000 in the original work.The first stage of our deep cascade processes all image patches that have high confidence values and pass through the VeryFast classifier. We here utilize the idea of a tiny convolutional network proposed by our prior work [1]. The tiny deep network has three layers only and features a 5x5 convolution, a 1x1 convolution and a very shallow fully-connected layer of 512 units. It reduces the massive computational time that is needed to evaluate a full DNN at all candidate locations filtered by the previous stage. The speedup produced ...

We examine the implications of shape on the process of finding dense correspondence and halfocclusions for a stereo pair of images. The desired property of the disparity map is that it should be a piecewise continuous function which is consistent with the images and which has the minimum number of discontinuities. To zeroth order, piecewise continuity becomes piecewise constancy. Using this approximation, we first discuss an approach for dealing with such a fronto-parallel shapeless world, and the problems involved therein. We then introduce horizontal and vertical slant to create a first order approximation to piecewise continuity. In particular, we emphasize the following geometric fact: a horizontally slanted surface (i.e., having depth variation in the direction of the separation of the two cameras) will appear horizontally stretched in one image as compared to the other image. Thus, while corresponding two images, N pixels on a scanline in one image may correspond to a different number of pixels M in the other image. This leads to three important modifications to existing stereo algorithms: (a) due to unequal sampling, existing intensity matching metrics must be modified, (b) unequal numbers of pixels in the two images must be allowed to correspond to each other, and (c) the uniqueness constraint, which is often used for detecting occlusions, must be changed to an interval uniqueness constraint. We also discuss the asymmetry between vertical and horizontal slant, and the central role of non-horizontal edges in the context of vertical slant. Using experiments, we discuss cases where existing algorithms fail, and how the incorporation of these new constraints provides correct results.

By examining the problem of image correspondence (binocular stereo and optical flow) and its relationship with other modules such as segmentation, shape and depth estimation, occlusion detection, and local signal processing, we argue that early visual modules are entangled in chicken-and-egg relationships, and unraveling these necessitates a compositional approach. In this paper, we present compositional algorithms which can match images containing slanted surfaces and images having different contrast, while simultaneously solving other problems as part of the same process. Ultimately, our goal is to motivate the application of the compositional approach to unify many other early visual modules. Experimental results have been presented on a large variety of stereo and motion images, including images with contrast mismatch and images containing untextured slanted surfaces.