Making the right decision in traffic is a challenging task that is highly dependent on individual preferences as well as the surrounding environment. Therefore it is hard to model solely based on expert knowledge. In this work we use Deep Reinforcement Learning to learn maneuver decisions based on a compact semantic state representation. This ensures a consistent model of the environment across scenarios as well as a behavior adaptation function, enabling on-line changes of desired behaviors without re-training. The input for the neural network is a simulated object list similar to that of Radar or Lidar sensors, superimposed by a relational semantic scene description. The state as well as the reward are extended by a behavior adaptation function and a parameterization respectively. With little expert knowledge and a set of mid-level actions, it can be seen that the agent is capable to adhere to traffic rules and learns to drive safely in a variety of situations.
In a mixed-traffic scenario where both autonomous vehicles and human-driving vehicles exist, a timely prediction of driving intentions of nearby human-driving vehicles is essential for the safe and efficient driving of an autonomous vehicle. In this paper, a driving intention prediction method based on Hidden Markov Model (HMM) is proposed for autonomous vehicles. HMMs representing different driving intentions are trained and tested with field collected data from a flyover. When training the models, either discrete or continuous characterization of the mobility features of vehicles is applied.…
Baidu Apollo Autonomous Driving（百度阿波罗自动驾驶）；University of Cambridge（剑桥大学）
We introduce ApolloRL, an open platform for research in reinforcement learning for autonomous driving. The platform provides a complete closed-loop pipeline with training, simulation, and evaluation components. It comes with 300 hours of real-world data in driving scenarios and popular baselines such as Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) agents. We elaborate in this paper on the architecture and the environment defined in the platform. In addition, we discuss the performance of the baseline agents in the ApolloRL environment.
To improve efficiency and reduce failures in autonomous vehicles, research has focused on developing robust and safe learning methods that take into account disturbances in the environment. Existing literature in robust reinforcement learning poses the learning problem as a two player game between the autonomous system and disturbances. This paper examines two different algorithms to solve the game, Robust Adversarial Reinforcement Learning and Neural Fictitious Self Play, and compares performance on an autonomous driving scenario. We extend the game formulation to a semi-competitive setting a…
Waterloo Artificial Intelligence Institute（滑铁卢人工智能研究所）；Department of Systems Design Engineering, University of Waterloo（滑铁卢大学系统设计工程系）；David Cheriton school of Computer science, University of Waterloo（滑铁卢大学戴维·谢里顿计算机学院）；University of Waterloo（滑铁卢大学）
This paper analyzes the robustness of deep learning models in autonomous driving applications and discusses the practical solutions to address that.
There have been numerous advances in reinforcement learning, but the typically unconstrained exploration of the learning process prevents the adoption of these methods in many safety critical applications. Recent work in safe reinforcement learning uses idealized models to achieve their guarantees, but these models do not easily accommodate the stochasticity or high-dimensionality of real world systems. We investigate how prediction provides a general and intuitive framework to constraint exploration, and show how it can be used to safely learn intersection handling behaviors on an autonomous …
Westview High School（韦斯特维尤高中）；Berkeley DeepDrive Center（伯克利深度驾驶中心）
Autonomous driving requires operation in different behavioral modes ranging from lane following and intersection crossing to turning and stopping. However, most existing deep learning approaches to autonomous driving do not consider the behavioral mode in the training strategy. This paper describes a technique for learning multiple distinct behavioral modes in a single deep neural network through the use of multi-modal multi-task learning. We study the effectiveness of this approach, denoted MultiNet, using self-driving model cars for driving in unstructured environments such as sidewalks and …
To improve the security and robustness of autonomous driving models, this paper presents SMET, a scenariobased metamorphic testing tool for autonomous driving models. The metamorphic relationship is divided into three dimensions (time, space, and event) and demonstrates its effectiveness through case studies in two types of autonomous driving models with different outputs.Experimental results show that this tool can well detect potential defects of the autonomous driving model, and complex scenes are more effective than simple scenes.
Based on the direct perception paradigm of autonomous driving, we investigate and modify the CNNs (convolutional neural networks) AlexNet and GoogLeNet that map an input image to few perception indicators (heading angle, distances to preceding cars, and distance to road centerline) for estimating driving affordances in highway traffic. We also design a controller with these indicators and the short-range sensor information of TORCS (the open racing car simulator) for driving simulated cars to avoid collisions. We collect a set of images from a TORCS camera in various driving scenarios, train t…
PerceptIn（感知创新公司）；South China University of Technology（华南理工大学）；Northwestern University（西北大学）
The infrastructure-vehicle cooperative autonomous driving approach depends on the cooperation between intelligent roads and intelligent vehicles. This approach is not only safer but also more economical compared to the traditional on-vehicle-only autonomous driving approach. In this paper, we introduce our real-world deployment experiences of cooperative autonomous driving, and delve into the details of new challenges and opportunities. Specifically, based on our progress towards commercial deployment, we follow a three-stage development roadmap of the cooperative autonomous driving approach:i…
We describe the computing tasks involved in autonomous driving, examine existing autonomous driving computing platform implementations. To enable autonomous driving, the computing stack needs to simultaneously provide high performance, low power consumption, and low thermal dissipation, at low cost. We discuss possible approaches to design computing platforms that will meet these needs.
Autonomous systems require identifying the environment and it has a long way to go before putting it safely into practice. In autonomous driving systems, the detection of obstacles and traffic lights are of importance as well as lane tracking. In this study, an autonomous driving system is developed and tested in the experimental environment designed for this purpose. In this system, a model vehicle having a camera is used to trace the lanes and avoid obstacles to experimentally study autonomous driving behavior. Convolutional Neural Network models were trained for Lane tracking. For the vehic…
Machine Learning-Based Vehicle Intention Trajectory Recognition and Prediction for Autonomous Driving
University of Southern California（南加州大学）；Virginia Tech（弗吉尼亚理工大学）；Miami University（迈阿密大学）；Northern Arizona University（北亚利桑那大学）；Northeastern University（东北大学）
Motion Comfort Optimization for Autonomous Vehicles: Concepts, Methods, and Techniques
University of North Texas（北德克萨斯大学）；Fordham University（福特汉姆大学）；Qatar University（卡塔尔大学）；University of Nebraska at Kearney（内布拉斯加大学卡尼尔分校）；Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学（MBZUAI））；Hamad Bin Khalifa University（哈马德·本·哈利法大学）
World Models for Autonomous Driving: An Initial Survey
University of Macau（澳门大学）；College of Transportation Engineering, Tongji University（同济大学交通运输工程学院）；Tsinghua University（清华大学）；Macau University of Science and Technology（澳门科技大学）；University of Hawaii at Manoa（夏威夷大学马诺阿分校）
Recent developments in autonomous driving technology have proven that map data may be used, not only for general routing purposes, but also for to enhance and complement common sensor data. This document reviews the most commonly used interfaces and formats at each step of a selfhealing map data chain.
Beijing Institute of Technology（北京理工大学）；Delft University of Technology（代尔夫特理工大学）
Due to the complex and dynamic character of intersection scenarios, the autonomous driving strategy at intersections has been a difficult problem and a hot point in the research of intelligent transportation systems in recent years. This paper gives a brief summary of state-of-the-art autonomous driving strategies at intersections. Firstly, we enumerate and analyze common types of intersection scenarios, corresponding simulation platforms, as well as related datasets. Secondly, by reviewing previous studies, we have summarized characteristics of existing autonomous driving strategies and class…
Autonomous driving clouds provide essential services to support autonomous vehicles. Today these services include but not limited to distributed simulation tests for new algorithm deployment, offline deep learning model training, and High-Definition (HD) map generation. These services require infrastructure support including distributed computing, distributed storage, as well as heterogeneous computing. In this paper, we present the details of how we implement a unified autonomous driving cloud infrastructure, and how we support these services on top of this infrastructure.
In this paper, we develop a safe decision-making method for self-driving cars in a multi-lane, single-agent setting. The proposed approach utilizes deep reinforcement learning (RL) to achieve a high-level policy for safe tactical decision-making. We address two major challenges that arise solely in autonomous navigation. First, the proposed algorithm ensures that collisions never happen, and therefore accelerate the learning process. Second, the proposed algorithm takes into account the unobservable states in the environment. These states appear mainly due to the unpredictable behavior of othe…
ENSTA Paris（巴黎高等先进技术学院）；Institut Polytechnique de Paris（巴黎理工学院）；INRIA（法国国家信息与自动化研究所）；Université Paris-Saclay（巴黎萨克雷大学）；CEA（法国原子能和替代能源委员会）；List（李斯特研究所）
In recent years, we have witnessed increasingly high performance in the field of autonomous end-to-end driving. In particular, more and more research is being done on driving in urban environments, where the car has to follow high level commands to navigate. However, few evaluations are made on the ability of these agents to react in an unexpected situation. Specifically, no evaluations are conducted on the robustness of driving agents in the event of a bad high-level command. We propose here an evaluation method, namely a benchmark that allows to assess the robustness of an agent, and to appr…
In this paper, we continue our prior work on using imitation learning (IL) and model free reinforcement learning (RL) to learn driving policies for autonomous driving in urban scenarios, by introducing a model based RL method to drive the autonomous vehicle in the Carla urban driving simulator. Although IL and model free RL methods have been proved to be capable of solving lots of challenging tasks, including playing video games, robots, and, in our prior work, urban driving, the low sample efficiency of such methods greatly limits their applications on actual autonomous driving. In this work,…
Perceptin LLC（Perceptin有限责任公司）；Northeastern Univ（东北大学）；COCOPLE LLC（COCOPLE有限责任公司）；College of William and Mary（威廉玛丽学院）；North Carolina State University（北卡罗来纳州立大学）
Autonomous driving is of great interest in both research and industry. The high cost has been one of the major roadblocks that slow down the development and adoption of autonomous driving in practice. This paper, for the first-time, shows that it is possible to run level-4 (i.e., fully autonomous driving) software on a single off-the-shelf card (Jetson AGX Xavier) for less than $1k, an order of magnitude less than the state-of-the-art systems, while meeting all the requirements of latency. The success comes from the resolution of some important issues shared by existing practices through a ser…
This paper issues an integrated control system of self-driving autonomous vehicles based on the personal driving preference to provide personalized comfortable driving experience to autonomous vehicle users. We propose an Occupant's Preference Metric (OPM) which is defining a preferred lateral and longitudinal acceleration region with maximum allowable jerk for users. Moreover, we propose a vehicle controller based on control parameters enabling integrated lateral and longitudinal control via preference-aware maneuvering of autonomous vehicles. The proposed system not only provides the criteri…
Our autonomous driving simulation lab produces a high-precision 3D model simulating the parking lot. However, the current model still has poor rendering quality in some aspects. In this work, we develop a system to improve the rendering of the model and evaluate the quality of the rendered model.
Towards Benchmarking and Assessing the Safety and Robustness of Autonomous Driving on Safety-critical Scenarios
Zhongguancun Laboratory（中关村实验室）；Beihang University（北京航空航天大学）；Institute of Data Space, Hefei Comprehensive National Science Center（合肥综合性国家科学中心数据空间研究院）；Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）；A*STAR（新加坡科技研究局）
University of Science and Technology of China（中国科学技术大学）；Carnegie Mellon University（卡内基梅隆大学）
In order to operate safely on the road, autonomous vehicles need not only to be able to identify objects in front of them, but also to be able to estimate the risk level of the object in front of the vehicle automatically. It is obvious that different objects have different levels of danger to autonomous vehicles. An evaluation system is needed to automatically determine the danger level of the object for the autonomous vehicle. It would be too subjective and incomplete if the system were completely defined by humans. Based on this, we propose a framework based on nonparametric Bayesian learni…
Testing autonomous driving algorithms on real autonomous vehicles is extremely costly and many researchers and developers in the field cannot afford a real car and the corresponding sensors. Although several free and open-source autonomous driving stacks, such as Autoware and Apollo are available, choices of open-source simulators to use with them are limited. In this paper, we introduce the LGSVL Simulator which is a high fidelity simulator for autonomous driving. The simulator engine provides end-to-end, full-stack simulation which is ready to be hooked up to Autoware and Apollo. In addition…
Owing to the merits of early safety and reliability guarantee, autonomous driving virtual testing has recently gains increasing attention compared with closed-loop testing in real scenarios. Although the availability and quality of autonomous driving datasets and toolsets are the premise to diagnose the autonomous driving system bottlenecks and improve the system performance, due to the diversity and privacy of the datasets and toolsets, collecting and featuring the perspective and quality of them become not only time-consuming but also increasingly challenging. This paper first proposes a Sys…
This survey reviews explainability methods for vision-based self-driving systems trained with behavior cloning. The concept of explainability has several facets and the need for explainability is strong in driving, a safety-critical application. Gathering contributions from several research fields, namely computer vision, deep learning, autonomous driving, explainable AI (X-AI), this survey tackles several points. First, it discusses definitions, context, and motivation for gaining more interpretability and explainability from self-driving systems, as well as the challenges that are specific t…
We explore the complex design space of behaviour planning for autonomous driving. Design choices that successfully address one aspect of behaviour planning can critically constrain others. To aid the design process, in this work we decompose the design space with respect to important choices arising from the current state of the art approaches, and describe the resulting trade-offs. In doing this, we also identify interesting directions of future work.
Technical University of Crete（克里特理工大学）；University of Malta（马耳他大学）
In this work the problem of path planning for an autonomous vehicle that moves on a freeway is considered. The most common approaches that are used to address this problem are based on optimal control methods, which make assumptions about the model of the environment and the system dynamics. On the contrary, this work proposes the development of a driving policy based on reinforcement learning. In this way, the proposed driving policy makes minimal or no assumptions about the environment, since a priori knowledge about the system dynamics is not required. Driving scenarios where the road is oc…
Since deep neural networks' resurgence, reinforcement learning has gradually strengthened and surpassed humans in many conventional games. However, it is not easy to copy these accomplishments to autonomous driving because state spaces are immensely complicated in the real world and action spaces are continuous and fine control is necessary. Besides, autonomous driving systems must also maintain their functionality regardless of the environment's complexity. The deep reinforcement learning domain (DRL) has become a robust learning framework to handle complex policies in high dimensional surrou…
Autonomous driving technologies are expected to not only improve mobility and road safety but also bring energy efficiency benefits. In the foreseeable future, autonomous vehicles (AVs) will operate on roads shared with human-driven vehicles. To maintain safety and liveness while simultaneously minimizing energy consumption, the AV planning and decision-making process should account for interactions between the autonomous ego vehicle and surrounding human-driven vehicles. In this chapter, we describe a framework for developing energy-efficient autonomous driving policies on shared roads by exp…
This paper presents a noval method that generates optimal trajectories for autonomous vehicles for in-lane driving scenarios. The method computes a trajectory using a two-phase optimization procedure. In the first phase, the optimization procedure generates a close-form driving guide line with differetiable curvatures. In the second phase, the procedure takes the driving guide line as input, and outputs dynamically feasible, jerk and time optimal trajectories for vehicles driving along the guide line. This method is especially useful for generating trajectories at curvy road where the vehicles…
Autonomous driving is a complex undertaking. A common approach is to break down the driving task into individual subtasks through modularization. These sub-modules are usually developed and published separately. However, if these individually developed algorithms have to be combined again to form a full-stack autonomous driving software, this poses particular challenges. Drawing upon our practical experience in developing the software of TUM Autonomous Motorsport, we have identified and derived these challenges in developing an autonomous driving software stack within a scientific environment.…
Wayne State University（韦恩州立大学）；Anhui University（安徽大学）
The recent proliferation of computing technologies (e.g., sensors, computer vision, machine learning, and hardware acceleration), and the broad deployment of communication mechanisms (e.g., DSRC, C-V2X, 5G) have pushed the horizon of autonomous driving, which automates the decision and control of vehicles by leveraging the perception results based on multiple sensors. The key to the success of these autonomous systems is making a reliable decision in real-time fashion. However, accidents and fatalities caused by early deployed autonomous vehicles arise from time to time. The real traffic envir…
This paper presents a novel model-reference reinforcement learning algorithm for the intelligent tracking control of uncertain autonomous surface vehicles with collision avoidance. The proposed control algorithm combines a conventional control method with reinforcement learning to enhance control accuracy and intelligence. In the proposed control design, a nominal system is considered for the design of a baseline tracking controller using a conventional control approach. The nominal system also defines the desired behaviour of uncertain autonomous surface vehicles in an obstacle-free environme…
Georgia Institute of Technology（佐治亚理工学院）；University of Texas at Dallas（德克萨斯大学达拉斯分校）；University of Central Oklahoma（中央俄克拉荷马大学）；UNIST（蔚山国立科学技术院）；University of Virginia（弗吉尼亚大学）
Autonomous driving has become real; semi-autonomous driving vehicles in an affordable price range are already on the streets, and major automotive vendors are actively developing full self-driving systems to deploy them in this decade. Before rolling the products out to the end-users, it is critical to test and ensure the safety of the autonomous driving systems, consisting of multiple layers intertwined in a complicated way. However, while safety-critical bugs may exist in any layer and even across layers, relatively little attention has been given to testing the entire driving system across …
Korea University（高丽大学）；Seoul National University（首尔国立大学）；Department of Artificial Intelligence, Korea University（高丽大学人工智能系）；ASRI, Seoul National University（首尔国立大学先进科学研究中心）；Department of Mechanical Engineering, Seoul National University（首尔国立大学机械工程系）；Department of Computer Science and Engineering, Seoul National University（首尔国立大学计算机科学与工程系）
Designing or learning an autonomous driving policy is undoubtedly a challenging task as the policy has to maintain its safety in all corner cases. In order to secure safety in autonomous driving, the ability to detect hazardous situations, which can be seen as an out-of-distribution (OOD) detection problem, becomes crucial. However, most conventional datasets only provide expert driving demonstrations, although some non-expert or uncommon driving behavior data are needed to implement a safety guaranteed autonomous driving platform. To this end, we present a novel dataset called the R3 Driving …
Institute of Computing Technology, CAS（中国科学院计算技术研究所）；University of Delaware（特拉华大学）；University of Chinese Academy of Sciences（中国科学院大学）
Infrastructure-Vehicle Cooperative Autonomous Driving (IVCAD) is a new paradigm of autonomous driving, which relies on the cooperation between intelligent roads and autonomous vehicles. This paradigm has been shown to be safer and more efficient compared to the on-vehicle-only autonomous driving paradigm. Our real-world deployment data indicates that the effectiveness of IVCAD is constrained by reliability and performance of commercial communication networks. This paper targets this exact problem, and proposes INTERNEURON, a middleware to achieve high communication reliability between intellig…
Given the current point-to-point navigation capabilities of autonomous vehicles, researchers are looking into complex service requests that require the vehicles to visit multiple points of interest. In this paper, we develop a layered planning framework, called GLAD, for complex service requests in autonomous urban driving. There are three layers for service-level, behavior-level, and motion-level planning. The layered framework is unique in its tight coupling, where the different layers communicate user preferences, safety estimates, and motion costs for system optimization. GLAD is visually …
State Key Laboratory of Automotive Safety and Energy, Tsinghua University（清华大学汽车安全与节能国家重点实验室）
With the development of state-of-art deep reinforcement learning, we can efficiently tackle continuous control problems. But the deep reinforcement learning method for continuous control is based on historical data, which would make unpredicted decisions in unfamiliar scenarios. Combining deep reinforcement learning and safety based control can get good performance for self-driving and collision avoidance. In this passage, we use the Deep Deterministic Policy Gradient algorithm to implement autonomous driving without vehicles around. The vehicle can learn the driving policy in a stable and fam…
Deep reinforcement learning is actively used for training autonomous car policies in a simulated driving environment. Due to the large availability of various reinforcement learning algorithms and the lack of their systematic comparison across different driving scenarios, we are unsure of which ones are more effective for training autonomous car software in single-agent as well as multi-agent driving environments. A benchmarking framework for the comparison of deep reinforcement learning in a vision-based autonomous driving will open up the possibilities for training better autonomous car driv…
