Over the past few years there is a growing interest in the learning-based self driving system. To ensure safety, such systems are first developed and validated in simulators before being deployed in the real world. However, most of the existing driving simulators only contain a fixed set of scenes and a limited number of configurable settings. That might easily cause the overfitting issue for the learning-based driving systems as well as the lack of their generalization ability to unseen scenarios. To better evaluate and improve the generalization of end-to-end driving, we introduce an open-ended and highly configurable driving simulator called PGDrive, following a key feature of procedural generation. Diverse road networks are first generated by the proposed generation algorithm via sampling from elementary road blocks. Then they are turned into interactive training environments where traffic flows of nearby vehicles with realistic kinematics are rendered. We validate that training with the increasing number of procedurally generated scenes significantly improves the generalization of the agent across scenarios of different traffic densities and road networks. Many applications such as multi-agent traffic simulation and safe driving benchmark can be further built upon the simulator. To facilitate the joint research effort of end-to-end driving, we release the simulator and pretrained models at https://decisionforce.github.io/pgdrive
ETH Zurich（苏黎世联邦理工学院）；The Chinese University of Hong Kong（香港中文大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Centre for Perceptual and Interactive Intelligence（感知与交互智能研究中心）
Driving safely requires multiple capabilities from human and intelligent agents, such as the generalizability to unseen environments, the safety awareness of the surrounding traffic, and the decision-making in complex multi-agent settings. Despite the great success of Reinforcement Learning (RL), most of the RL research works investigate each capability separately due to the lack of integrated environments. In this work, we develop a new driving simulation platform called MetaDrive to support the research of generalizable reinforcement learning algorithms for machine autonomy. MetaDrive is hig…
Recent work has shown the benefits of synthetic data for use in computer vision, with applications ranging from autonomous driving to face landmark detection and reconstruction. There are a number of benefits of using synthetic data from privacy preservation and bias elimination to quality and feasibility of annotation. Generating human-centered synthetic data is a particular challenge in terms of realism and domain-gap, though recent work has shown that effective machine learning models can be trained using synthetic face data alone. We show that this can be extended to include the full body …
Imagine a City: CityGenAgent for Procedural 3D City Generation
Lingnan University, Hong Kong SAR, China（岭南大学）；Zhejiang University, Hangzhou, China（浙江大学）；The Chinese University of Hong Kong, Hong Kong SAR, China（香港中文大学）；Autodesk AI Lab, Canada（Autodesk AI实验室）；The University of Hong Kong, Hong Kong SAR, China（香港大学）
University of Maryland（马里兰大学）；University of Memphis（孟菲斯大学）
For safety of autonomous driving, vehicles need to be able to drive under various lighting, weather, and visibility conditions in different environments. These external and environmental factors, along with internal factors associated with sensors, can pose significant challenges to perceptual data processing, hence affecting the decision-making and control of the vehicle. In this work, we address this critical issue by introducing a framework for analyzing robustness of the learning algorithm w.r.t varying quality in the image input for autonomous driving. Using the results of sensitivity ana…
Practical learning-based autonomous driving models must be capable of generalizing learned behaviors from simulated to real domains, and from training data to unseen domains with unusual image properties. In this paper, we investigate transfer learning methods that achieve robustness to domain shifts by taking advantage of the invariance of spatio-temporal features across domains. In this paper, we propose a transfer learning method to improve generalization across domains via transfer of spatio-temporal features and salient data augmentation. Our model uses a CNN-LSTM network with Inception m…
TrafficSignBench: Rule-Centric Closed-Loop Evaluation of Traffic-Sign Compliance in Autonomous Driving
Lomonosov Moscow State University（罗蒙诺索夫莫斯科国立大学）；FusionBrain Lab（FusionBrain实验室）；Moscow Institute of Physics and Technology（莫斯科物理技术学院）；HSE University（高等经济大学）；Innopolis University（因诺波利斯大学）；NUST MISIS（国立研究型技术大学莫斯科国立钢铁合金学院）
Deep Neural Networks (DNNs) are a critical component for self-driving vehicles. They achieve impressive performance by reaping information from high amounts of labeled data. Yet, the full complexity of the real world cannot be encapsulated in the training data, no matter how big the dataset, and DNNs can hardly generalize to unseen conditions. Robustness to various image corruptions, caused by changing weather conditions or sensor degradation and aging, is crucial for safety when such vehicles are deployed in the real world. We address this problem through a novel type of layer, dubbed StyleLe…
Semantic segmentation on driving-scene images is vital for autonomous driving. Although encouraging performance has been achieved on daytime images, the performance on nighttime images are less satisfactory due to the insufficient exposure and the lack of labeled data. To address these issues, we present an add-on module called dual image-adaptive learnable filters (DIAL-Filters) to improve the semantic segmentation in nighttime driving conditions, aiming at exploiting the intrinsic features of driving-scene images under different illuminations. DIAL-Filters consist of two parts, including an …
We present a simple and flexible object detection framework optimized for autonomous driving. Building on the observation that point clouds in this application are extremely sparse, we propose a practical pillar-based approach to fix the imbalance issue caused by anchors. In particular, our algorithm incorporates a cylindrical projection into multi-view feature learning, predicts bounding box parameters per pillar rather than per point or per anchor, and includes an aligned pillar-to-point projection module to improve the final prediction. Our anchor-free approach avoids hyperparameter search …
Robust motion forecasting of the dynamic scene is a critical component of an autonomous vehicle. It is a challenging problem due to the heterogeneity in the scene and the inherent uncertainties in the problem. To improve the accuracy of motion forecasting, in this work, we identify a new consistency constraint in this task, that is an agent's future trajectory should be coherent with its history observations and visa versa. To leverage this property, we propose a novel cycle consistency training scheme and define a novel cycle loss to encourage this consistency. In particular, we reverse the p…
Deep neural networks are a key component of behavior prediction and motion generation for self-driving cars. One of their main drawbacks is a lack of transparency: they should provide easy to interpret rationales for what triggers certain behaviors. We propose an architecture called Attentional Bottleneck with the goal of improving transparency. Our key idea is to combine visual attention, which identifies what aspects of the input the model is using, with an information bottleneck that enables the model to only use aspects of the input which are important. This not only provides sparse and in…
Uber Advanced Technologies Group（优步先进技术集团）；University of Toronto（多伦多大学）；Massachusetts Institute of Techonology（麻省理工学院）
We tackle the problem of producing realistic simulations of LiDAR point clouds, the sensor of preference for most self-driving vehicles. We argue that, by leveraging real data, we can simulate the complex world more realistically compared to employing virtual worlds built from CAD/procedural models. Towards this goal, we first build a large catalog of 3D static maps and 3D dynamic objects by driving around several cities with our self-driving fleet. We can then generate scenarios by selecting a scene from our catalog and "virtually" placing the self-driving vehicle (SDV) and a set of dynamic o…
Knowledge distillation is an effective approach for training compact recognizers required in autonomous driving. Recent studies on image classification have shown that matching student and teacher on a wide range of data points is critical for improving performance in distillation. This concept (called function matching) is suitable for driving scene recognition, where generally an almost infinite amount of unlabeled data are available. In this study, we experimentally investigate the impact of using such a large amount of unlabeled data for distillation on the performance of student models in…
Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving
Donald Bren School of Information and Computer Sciences, University of California, Irvine（加州大学欧文分校唐纳德·布伦信息与计算机科学学院）；School of Computing, National University of Singapore（新加坡国立大学计算学院）；Nanyang Technological University（南洋理工大学）；Shanghai AI Laboratory（上海人工智能实验室）
End-to-End Autonomous Driving through V2X Cooperation
The University of Hong Kong（香港大学）；AIR, Tsinghua University（清华大学智能产业研究院）；Beijing Institute of Technology（北京理工大学）；University of Science and Technology Beijing（北京科技大学）
Seoul National University（首尔国立大学）；Seoul National University of Science and Technology（首尔科学技术大学）
The use of object detection algorithms is becoming increasingly important in autonomous vehicles, and object detection at high accuracy and a fast inference speed is essential for safe autonomous driving. A false positive (FP) from a false localization during autonomous driving can lead to fatal accidents and hinder safe and efficient driving. Therefore, a detection algorithm that can cope with mislocalizations is required in autonomous driving applications. This paper proposes a method for improving the detection accuracy while supporting a real-time operation by modeling the bounding box (bb…
University of Toronto（多伦多大学）；FZI Research Center for Information Technology（FZI信息技术研究中心）；University of Cambridge（剑桥大学）；Uber Advanced Technologies Group（优步先进技术集团）
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. Our approach is very simple, can be trained end-to-end and performs extremely well in the challenging KITTI dataset, outperforming the state-of-the-art in the road segmentation task. Our approach i…
An accurate model of the environment and the dynamic agents acting in it offers great potential for improving motion planning. We present MILE: a Model-based Imitation LEarning approach to jointly learn a model of the world and a policy for autonomous driving. Our method leverages 3D geometry as an inductive bias and learns a highly compact latent space directly from high-resolution videos of expert demonstrations. Our model is trained on an offline corpus of urban driving data, without any online interaction with the environment. MILE improves upon prior state-of-the-art by 31% in driving sco…
Human-vehicle cooperative driving has become the critical technology of autonomous driving, which reduces the workload of human drivers. However, the complex and uncertain road environments bring great challenges to the visual perception of cooperative systems. And the perception characteristics of autonomous driving differ from manual driving a lot. To enhance the visual perception capability of human-vehicle cooperative driving, this paper proposed a cooperative visual perception model. 506 images of complex road and traffic scenarios were collected as the data source. Then this paper improv…
Baidu Research（百度研究院）；National Engineering Laboratory of Deep Learning Technology and Application（深度学习技术及应用国家工程实验室）
The clustering of autonomous driving scenario data can substantially benefit the autonomous driving validation and simulation systems by improving the simulation tests' completeness and fidelity. This article proposes a comprehensive data clustering framework for a large set of vehicle driving data. Existing algorithms utilize handcrafted features whose quality relies on the judgments of human experts. Additionally, the related feature compression methods are not scalable for a large data-set. Our approach thoroughly considers the traffic elements, including both in-traffic agent objects and m…
Woven Planet United Kingdom Limited（Woven Planet英国有限公司）；Woven Planet North America, Inc.（Woven Planet北美公司）
The imitation learning of self-driving vehicle policies through behavioral cloning is often carried out in an open-loop fashion, ignoring the effect of actions to future states. Training such policies purely with Empirical Risk Minimization (ERM) can be detrimental to real-world performance, as it biases policy networks towards matching only open-loop behavior, showing poor results when evaluated in closed-loop. In this work, we develop an efficient and simple-to-implement principle called Closed-loop Weighted Empirical Risk Minimization (CW-ERM), in which a closed-loop evaluation procedure is…
This work examines the hypothesis that partially observable Markov decision process (POMDP) planning with human driver internal states can significantly improve both safety and efficiency in autonomous freeway driving. We evaluate this hypothesis in a simulated scenario where an autonomous car must safely perform three lane changes in rapid succession. Approximate POMDP solutions are obtained through the partially observable Monte Carlo planning with observation widening (POMCPOW) algorithm. This approach outperforms over-confident and conservative MDP baselines and matches or outperforms QMDP…
Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification Algorithms
ITU Artificial Intelligence and Data Science Research Center（伊斯坦布尔技术大学人工智能与数据科学研究中心）；Department of Aeronautical Engineering（航空工程系）；Eatron Technologies（Eatron技术公司）；Department of Electronics and Communication Engineering（电子与通信工程系）；ITU Artificial Intelligence and Data Science Application and Research Center（伊斯坦布尔技术大学人工智能与数据科学应用与研究中心）；Department of Computer Engineering（计算机工程系）
Risk-Aware Reinforcement Learning for Autonomous Driving: Improving Safety When Driving through Intersection
School of Automotive Studies, Tongji University（同济大学汽车学院）；Department of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University（香港理工大学航空及航空工程系）
Improving Driver Satisfaction with a Driving Function Learning from Implicit Human Feedback -- a Test Group Study
Dr. Ing. h.c. F. Porsche AG（德意志联邦汽车工业联合会）；University of Catania（卡塔尼亚大学）；Technical University of Munich（慕尼黑技术大学）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
Automated lane changing is a critical feature for advanced autonomous driving systems. In recent years, reinforcement learning (RL) algorithms trained on traffic simulators yielded successful results in computing lane changing policies that strike a balance between safety, agility and compensating for traffic uncertainty. However, many RL algorithms exhibit simulator bias and policies trained on simple simulators do not generalize well to realistic traffic scenarios. In this work, we develop a data driven traffic simulator by training a generative adverserial network (GAN) on real life traject…
Improving Autonomous Driving Safety with POP: A Framework for Accurate Partially Observed Trajectory Predictions
The Hong Kong University of Science and Technology（香港科技大学）；HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute（香港科技大学深圳产学研合作研究院）；Lotus Technology Ltd（路特斯科技有限公司）
Learning Through Retrospection: Improving Trajectory Prediction for Automated Driving with Error Feedback
Robert Bosch GmbH（罗伯特·博世有限公司）；Institute for Neuro- and Bioinformatics, University of Lübeck（吕贝克大学神经与生物信息学研究所）；Department of Computer Science, University of Freiburg（弗赖堡大学计算机科学系）；Cognitive Systems Group, University of Tübingen（图宾根大学认知系统组）
Interactive Double Deep Q-network: Integrating Human Interventions and Evaluative Predictions in Reinforcement Learning of Autonomous Driving
Center for Applied Autonomous Sensor Systems (AASS)（应用自主传感器系统中心）；Örebro University（奥雷布罗大学）；Computer Vision Laboratory（计算机视觉实验室）；Linköping University（利德斯霍尔大学）
MTRDrive: Memory-Tool Synergistic Reasoning for Robust Autonomous Driving in Corner Cases
School of Vehicle and Mobility, Tsinghua University（清华大学车辆与移动系统学院）；Automotive and Robotics, Xiaomi Corporation（小鹏汽车与机器人部）；McGill University（麦吉尔大学）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
IFTD: Image Feature Triangle Descriptor for Loop Detection in Driving Scenes
Huazhong University of Science and Technology（华中科技大学）；Institute of Artificial Intelligence, Huazhong University of Science and Technology（华中科技大学人工智能研究院）
Michigan State University（密歇根州立大学）；National Technical University of Athens（雅典国立技术大学）；Massachusetts Institute of Technology（麻省理工学院）
We identify the need for a gamified self-driving simulator where game mechanics encourage high-quality data capture, and design and apply such a simulator to collecting lane-following training data. The resulting synthetic data enables a Convolutional Neural Network (CNN) to drive an in-game vehicle. We simultaneously develop a physical test platform based on a radio-controlled vehicle and the Robotic Operating System (ROS) and successfully transfer the simulation-trained model to the physical domain without modification. The cross-platform simulator facilitates unsupervised crowdsourcing, hel…
