Autonomous driving is the task of driving a vehicle without human conduction.
Visual and inertial fusion is a popular technology for 6-DOF state estimation in recent years. Time instants at which different sensors' measurements are recorded are of crucial importance to the system's robustness and accuracy.
We present a traffic simulation named DeepTraffic where the planning systems for a subset of the vehicles are handled by a neural network as part of a model-free, off-policy reinforcement learning process. The primary goal of DeepTraffic is to make the hands-on study of deep reinforcement learning accessible to thousands of students, educators, and researchers in order to inspire and fuel the exploration and evaluation of deep Q-learning network variants and hyperparameter configurations through large-scale, open competition.
Given realistic frames as input, driving policy trained by reinforcement learning can nicely adapt to real world driving. To our knowledge, this is the first successful case of driving policy trained by reinforcement learning that can adapt to real world driving data.
While most approaches to semantic reasoning have focused on improving performance, in this paper we argue that computational times are very important in order to enable real time applications such as autonomous driving. Towards this goal, we present an approach to joint classification, detection and semantic segmentation via a unified architecture where the encoder is shared amongst the three tasks.
In addition to requiring high accuracy to ensure safety, object detection for autonomous driving also requires real-time inference speed to guarantee prompt vehicle control, as well as small model size and energy efficiency to enable embedded system deployment. In this work, we propose SqueezeDet, a fully convolutional neural network for object detection that aims to simultaneously satisfy all of the above constraints.
Most of the research on semantic segmentation is only on increasing the accuracy of segmentation models with little attention to computationally efficient solutions. In this paper, we address this gap by presenting a real-time semantic segmentation benchmarking framework with a decoupled design for feature extraction and decoding methods.
We present AVOD, an Aggregate View Object Detection network for autonomous driving scenarios. The proposed neural network architecture uses LIDAR point clouds and RGB images to generate features that are shared by two subnetworks: a region proposal network (RPN) and a second stage detector network.
#2 best model for 3D Object Detection on KITTI Cars Hard
In this paper, we address semantic segmentation of road-objects from 3D LiDAR point clouds. To obtain extra training data, we built a LiDAR simulator into Grand Theft Auto V (GTA-V), a popular video game, to synthesize large amounts of realistic training data.
Therefore, additional processing steps have to be performed in order to obtain pixel-accurate segmentation masks at the full image resolution. Without additional processing steps and without pre-training, our approach achieves an intersection-over-union score of 71.8% on the Cityscapes dataset.
#3 best model for Real-Time Semantic Segmentation on Cityscapes
Real-time scene understanding has become crucial in many applications such as autonomous driving. In this paper, we propose a deep architecture, called BlitzNet, that jointly performs object detection and semantic segmentation in one forward pass, allowing real-time computations.
#2 best model for Real-Time Object Detection on PASCAL VOC 2007