Unlike popular modularized framework, end-to-end autonomous driving seeks to solve the perception, decision and control problems in an integrated way, which can be more adapting to new scenarios and easier to generalize at scale. However, existing end-to-end approaches are often lack of interpretability, and can only deal with simple driving tasks like lane keeping. In this paper, we propose an interpretable deep reinforcement learning method for end-to-end autonomous driving, which is able to handle complex urban scenarios. A sequential latent environment model is introduced and learned jointly with the reinforcement learning process. With this latent model, a semantic birdeye mask can be generated, which is enforced to connect with a certain intermediate property in today's modularized framework for the purpose of explaining the behaviors of learned policy. The latent space also significantly reduces the sample complexity of reinforcement learning. Comparison tests with a simulated autonomous car in CARLA show that the performance of our method in urban scenarios with crowded surrounding vehicles dominates many baselines including DQN, DDPG, TD3 and SAC. Moreover, through masked outputs, the learned policy is able to provide a better explanation of how the car reasons about the driving environment. The codes and videos of this work are available at our github repo and project website.
Urban autonomous driving decision making is challenging due to complex road geometry and multi-agent interactions. Current decision making methods are mostly manually designing the driving policy, which might result in sub-optimal solutions and is expensive to develop, generalize and maintain at scale. On the other hand, with reinforcement learning (RL), a policy can be learned and improved automatically without any manual designs. However, current RL methods generally do not work well on complex urban scenarios. In this paper, we propose a framework to enable model-free deep reinforcement lea…
The majority of current approaches in autonomous driving rely on High-Definition (HD) maps which detail the road geometry and surrounding area. Yet, this reliance is one of the obstacles to mass deployment of autonomous vehicles due to poor scalability of such prior maps. In this paper, we tackle the problem of online road map extraction via leveraging the sensory system aboard the vehicle itself. To this end, we design a structured model where a graph representation of the road network is generated in a hierarchical fashion within a fully convolutional network. The method is able to handle co…
Computer Vision Center（计算机视觉中心）；Intel Labs（英特尔研究院）；Toyota Research Institute（丰田研究院）
We introduce CARLA, an open-source simulator for autonomous driving research. CARLA has been developed from the ground up to support development, training, and validation of autonomous urban driving systems. In addition to open-source code and protocols, CARLA provides open digital assets (urban layouts, buildings, vehicles) that were created for this purpose and can be used freely. The simulation platform supports flexible specification of sensor suites and environmental conditions. We use CARLA to study the performance of three approaches to autonomous driving: a classic modular pipeline, an…
Hand-crafting generalised decision-making rules for real-world urban autonomous driving is hard. Alternatively, learning behaviour from easy-to-collect human driving demonstrations is appealing. Prior work has studied imitation learning (IL) for autonomous driving with a number of limitations. Examples include only performing lane-following rather than following a user-defined route, only using a single camera view or heavily cropped frames lacking state observability, only lateral (steering) control, but not longitudinal (speed) control and a lack of interaction with traffic. Importantly, the…
University of Freiburg（弗莱堡大学）；Toyota Research Institute（丰田研究所）
Lane-level scene annotations provide invaluable data in autonomous vehicles for trajectory planning in complex environments such as urban areas and cities. However, obtaining such data is time-consuming and expensive since lane annotations have to be annotated manually by humans and are as such hard to scale to large areas. In this work, we propose a novel approach for lane geometry estimation from bird's-eye-view images. We formulate the problem of lane shape and lane connections estimation as a graph estimation problem where lane anchor points are graph nodes and lane segments are graph edge…
MINES ParisTech（巴黎高等矿业学院）；PSL（巴黎文理研究大学）；Valeo Driving Assistance Research Valeo.ai（法雷奥驾驶辅助研究法雷奥人工智能）
Reinforcement Learning (RL) aims at learning an optimal behavior policy from its own experiments and not rule-based control methods. However, there is no RL algorithm yet capable of handling a task as difficult as urban driving. We present a novel technique, coined implicit affordances, to effectively leverage RL for urban driving thus including lane keeping, pedestrians and vehicles avoidance, and traffic light detection. To our knowledge we are the first to present a successful RL agent handling such a complex task especially regarding the traffic light detection. Furthermore, we have demons…
In this work we are the first to present an offline policy gradient method for learning imitative policies for complex urban driving from a large corpus of real-world demonstrations. This is achieved by building a differentiable data-driven simulator on top of perception outputs and high-fidelity HD maps of the area. It allows us to synthesize new driving experiences from existing demonstrations using mid-level representations. Using this simulator we then train a policy network in closed-loop employing policy gradients. We train our proposed method on 100 hours of expert demonstrations on urb…
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,…
We introduce a motion forecasting (behavior prediction) method that meets the latency requirements for autonomous driving in dense urban environments without sacrificing accuracy. A whole-scene sparse input representation allows StopNet to scale to predicting trajectories for hundreds of road agents with reliable latency. In addition to predicting trajectories, our scene encoder lends itself to predicting whole-scene probabilistic occupancy grids, a complementary output representation suitable for busy urban environments. Occupancy grids allow the AV to reason collectively about the behavior o…
Contextual Robotics Institute, University of California, San Diego（加州大学圣地亚哥分校语境机器人研究所）
Calibration of sensors is fundamental to robust performance for intelligent vehicles. In natural environments, disturbances can easily challenge calibration. One possibility is to use natural objects of known shape to recalibrate sensors. An approach based on recognition of traffic signs, such as stop signs, and use of them for recalibration of cameras is presented. The approach is based on detection, geometry estimation, calibration, and recursive updating. Results from natural environments are presented that clearly show convergence and improved performance.
Autonomous driving is a challenging domain that entails multiple aspects: a vehicle should be able to drive to its destination as fast as possible while avoiding collision, obeying traffic rules and ensuring the comfort of passengers. In this paper, we present a deep learning variant of thresholded lexicographic Q-learning for the task of urban driving. Our multi-objective DQN agent learns to drive on multi-lane roads and intersections, yielding and changing lanes according to traffic rules. We also propose an extension for factored Markov Decision Processes to the DQN architecture that provid…
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…
FZI Research Center for Information Technology（FZI信息技术研究中心）；IPG Automotive GmbH（IPG汽车有限公司）
Verification and validation are major challenges for developing automated driving systems. A concept that gets more and more recognized for testing in automated driving is scenario-based testing. However, it introduces the problem of what scenarios are relevant for testing and which are not. This work aims to find relevant, interesting, or critical parameter sets within logical scenarios by utilizing Bayes optimization and Gaussian processes. The parameter optimization is done by comparing and evaluating six different metrics in two urban intersection scenarios. Finally, a list of ideas this w…
Central European Institute of Technology (CEITEC)（中欧理工学院 (CEITEC)）；Brno University of Technology（布尔诺理工大学）
Autonomous driving is a dynamically growing field of research, where quality and amount of experimental data is critical. Although several rich datasets are available these days, the demands of researchers and technical possibilities are evolving. Through this paper, we bring a new dataset recorded in Brno, Czech Republic. It offers data from four WUXGA cameras, two 3D LiDARs, inertial measurement unit, infrared camera and especially differential RTK GNSS receiver with centimetre accuracy which, to the best knowledge of the authors, is not available from any other public dataset so far. In add…
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…
Autonomous driving in an unregulated urban crowd is an outstanding challenge, especially, in the presence of many aggressive, high-speed traffic participants. This paper presents SUMMIT, a high-fidelity simulator that facilitates the development and testing of crowd-driving algorithms. By leveraging the open-source OpenStreetMap map database and a heterogeneous multi-agent motion prediction model developed in our earlier work, SUMMIT simulates dense, unregulated urban traffic for heterogeneous agents at any worldwide locations that OpenStreetMap supports. SUMMIT is built as an extension of CAR…
Chalmers | University of Gothenburg（查尔姆斯理工大学 | 哥德堡大学）；RWTH Aachen University（亚琛工业大学）
In November 2007 the international competition DARPA Urban Challenge took place on the former George Airforce Base in Victorville, California to significantly promote the research and development on autonomously driving vehicles for urban environments. In the final race only eleven out of initially 89 competitors participated and "Boss" from Carnegie Mellon University succeeded. This paper summarizes results of the research carried out by all finalists within the last five years after the competition and provides an outlook where further investigation especially for software engineering is now…
University of Freiburg（弗赖堡大学）；Woven by Toyota（丰田编织公司）；University of Technology Nuremberg（纽伦堡工业大学）
Lane graph estimation is an essential and highly challenging task in automated driving and HD map learning. Existing methods using either onboard or aerial imagery struggle with complex lane topologies, out-of-distribution scenarios, or significant occlusions in the image space. Moreover, merging overlapping lane graphs to obtain consistent large-scale graphs remains difficult. To overcome these challenges, we propose a novel bottom-up approach to lane graph estimation from aerial imagery that aggregates multiple overlapping graphs into a single consistent graph. Due to its modular design, our…
Computer Vision Lab, ETH Zürich（计算机视觉实验室，苏黎世联邦理工学院）；MPI for Informatics（马克斯·普朗克信息研究所）；PSI, KU Leuven（PSI，鲁汶大学）
End-to-end approaches to autonomous driving commonly rely on expert demonstrations. Although humans are good drivers, they are not good coaches for end-to-end algorithms that demand dense on-policy supervision. On the contrary, automated experts that leverage privileged information can efficiently generate large scale on-policy and off-policy demonstrations. However, existing automated experts for urban driving make heavy use of hand-crafted rules and perform suboptimally even on driving simulators, where ground-truth information is available. To address these issues, we train a reinforcement …
Autonomous driving in an unregulated urban crowd is an outstanding challenge, especially, in the presence of many aggressive, high-speed traffic participants. This paper presents SUMMIT, a high-fidelity simulator that facilitates the development and testing of crowd-driving algorithms. SUMMIT simulates dense, unregulated urban traffic at any worldwide locations as supported by the OpenStreetMap. The core of SUMMIT is a multi-agent motion model, GAMMA, that models the behaviours of heterogeneous traffic agents, and a real-time POMDP planner, Context-POMDP, that serves as a driving expert. SUMMI…
Short-term future of automated driving can be imagined as a hybrid scenario in which both automated and human-driven vehicles co-exist in the same environment. In order to address the needs of such road configuration, many technology solutions such as vehicular communication and predictive control for automated vehicles have been introduced in the literature. Both aforementioned solutions rely on driving data of the human driver. In this work, we investigate the currently available driving datasets and introduce a real-world maneuver-based driving dataset that is collected during our urban dri…
Avoiding unseen or partially occluded vulnerable road users (VRUs) is a major challenge for fully autonomous driving in urban scenes. However, occlusion-aware risk assessment systems have not been widely studied. Here, we propose a pedestrian emergence estimation and occlusion-aware risk assessment system for urban autonomous driving. First, the proposed system utilizes available contextual information, such as visible cars and pedestrians, to estimate pedestrian emergence probabilities in occluded regions. These probabilities are then used in a risk assessment framework, and incorporated into…
Hong Kong University of Science and Technology（香港科技大学）
Traditional methods for autonomous driving are implemented with many building blocks from perception, planning and control, making them difficult to generalize to varied scenarios due to complex assumptions and interdependencies. Recently, the end-to-end driving method has emerged, which performs well and generalizes to new environments by directly learning from export-provided data. However, many existing methods on this topic neglect to check the confidence of the driving actions and the ability to recover from driving mistakes. In this paper, we develop an uncertainty-aware end-to-end traje…
Multi-LiDAR Localization and Mapping Pipeline for Urban Autonomous Driving
Institute of Automotive Technology, Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich（慕尼黑工业大学汽车技术研究所，慕尼黑机器人与机器智能研究所）；Professorship Autonomous Vehicle Systems, Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich（慕尼黑工业大学自动驾驶车辆系统教授席，慕尼黑机器人与机器智能研究所）
Netherlands Organisation for Applied Scientific Research（荷兰应用科学研究组织）；Eindhoven University of Technology（埃因霍温理工大学）
The urban environment is amongst the most difficult domains for autonomous vehicles. The vehicle must be able to plan a safe route on challenging road layouts, in the presence of various dynamic traffic participants such as vehicles, cyclists and pedestrians and in various environmental conditions. The challenge remains to have motion planners that are computationally fast and that account for future movements of other road users proactively. This paper describes an computationally efficient sampling-based trajectory planner for safe and comfortable driving in urban environments. The planner i…
Decision making for autonomous driving in urban environments is challenging due to the complexity of the road structure and the uncertainty in the behavior of diverse road users. Traditional methods consist of manually designed rules as the driving policy, which require expert domain knowledge, are difficult to generalize and might give sub-optimal results as the environment gets complex. Whereas, using reinforcement learning, optimal driving policy could be learned and improved automatically through several interactions with the environment. However, current research in the field of reinforce…
End-to-end approaches to autonomous driving have high sample complexity and are difficult to scale to realistic urban driving. Simulation can help end-to-end driving systems by providing a cheap, safe, and diverse training environment. Yet training driving policies in simulation brings up the problem of transferring such policies to the real world. We present an approach to transferring driving policies from simulation to reality via modularity and abstraction. Our approach is inspired by classic driving systems and aims to combine the benefits of modular architectures and end-to-end deep lear…
Learning-based approaches, such as reinforcement learning (RL) and imitation learning (IL), have indicated superiority over rule-based approaches in complex urban autonomous driving environments, showing great potential to make intelligent decisions. However, current RL and IL approaches still have their own drawbacks, such as low data efficiency for RL and poor generalization capability for IL. In light of this, this paper proposes a novel learning-based method that combines deep reinforcement learning and imitation learning from expert demonstrations, which is applied to longitudinal vehicle…
Navigating safely in urban environments remains a challenging problem for autonomous vehicles. Occlusion and limited sensor range can pose significant challenges to safely navigate among pedestrians and other vehicles in the environment. Enabling vehicles to quantify the risk posed by unseen regions allows them to anticipate future possibilities, resulting in increased safety and ride comfort. This paper proposes an algorithm that takes advantage of the known road layouts to forecast, quantify, and aggregate risk associated with occlusions and limited sensor range. This allows us to make predi…
Traditional autonomous vehicle pipelines that follow a modular approach have been very successful in the past both in academia and industry, which has led to autonomy deployed on road. Though this approach provides ease of interpretation, its generalizability to unseen environments is limited and hand-engineering of numerous parameters is required, especially in the prediction and planning systems. Recently, deep reinforcement learning has been shown to learn complex strategic games and perform challenging robotic tasks, which provides an appealing framework for learning to drive. In this work…
How autonomous vehicles and human drivers share public transportation systems is an important problem, as fully automatic transportation environments are still a long way off. Understanding human drivers' behavior can be beneficial for autonomous vehicle decision making and planning, especially when the autonomous vehicle is surrounded by human drivers who have various driving behaviors and patterns of interaction with other vehicles. In this paper, we propose an LSTM-based trajectory prediction method for human drivers which can help the autonomous vehicle make better decisions, especially in…
ETH Zürich（苏黎世联邦理工学院）；Politecnico di Milano（米兰理工大学）
This paper presents a trajectory planner for autonomous driving based on a Nonlinear Model Predictive Control (NMPC) algorithm that accounts for Pacejka's nonlinear lateral tyre dynamics as well as for zero speed conditions through a novel slip angles calculation. In the NMPC framework, road boundaries and obstacles (both static and moving) are taken into account thanks to soft and hard constraints implementation. The numerical solution of the NMPC problem is carried out using ACADO toolkit coupled with the quadratic programming solver qpOASES. The effectiveness of the proposed NMPC trajectory…
The Hong Kong University of Science and Technology（香港科技大学）；The Hong Kong Polytechnic University（香港理工大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
Recently, deep-learning based approaches have achieved impressive performance for autonomous driving. However, end-to-end vision-based methods typically have limited interpretability, making the behaviors of the deep networks difficult to explain. Hence, their potential applications could be limited in practice. To address this problem, we propose an interpretable end-to-end vision-based motion planning approach for autonomous driving, referred to as IVMP. Given a set of past surrounding-view images, our IVMP first predicts future egocentric semantic maps in bird's-eye-view space, which are th…
SenseTime Research（商汤科技研究院）；University of Toronto（多伦多大学）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Large-scale deployment of autonomous vehicles has been continually delayed due to safety concerns. On the one hand, comprehensive scene understanding is indispensable, a lack of which would result in vulnerability to rare but complex traffic situations, such as the sudden emergence of unknown objects. However, reasoning from a global context requires access to sensors of multiple types and adequate fusion of multi-modal sensor signals, which is difficult to achieve. On the other hand, the lack of interpretability in learning models also hampers the safety with unverifiable failure causes. In t…
Australian Institute for Machine Learning（澳大利亚机器学习研究所）；University of Adelaide（阿德莱德大学）；Singapore Management University（新加坡管理大学）
State-of-the-art (SOTA) anomaly segmentation approaches on complex urban driving scenes explore pixel-wise classification uncertainty learned from outlier exposure, or external reconstruction models. However, previous uncertainty approaches that directly associate high uncertainty to anomaly may sometimes lead to incorrect anomaly predictions, and external reconstruction models tend to be too inefficient for real-time self-driving embedded systems. In this paper, we propose a new anomaly segmentation method, named pixel-wise energy-biased abstention learning (PEBAL), that explores pixel-wise a…
RLAD: Reinforcement Learning from Pixels for Autonomous Driving in Urban Environments
University of Aveiro（阿威罗大学）；Intelligent System Associate Laboratory (LASI)（智能系统联合实验室（LASI））；Institute of Electronics and Informatics Engineering of Aveiro (IEETA)（阿威罗电子与信息工程研究所（IEETA））
FiveAI Ltd（FiveAI有限公司）；University of Oxford（牛津大学）；University of Edinburgh（爱丁堡大学）
Recent road trials have shown that guaranteeing the safety of driving decisions is essential for the wider adoption of autonomous vehicle technology. One promising direction is to pose safety requirements as planning constraints in nonlinear, non-convex optimization problems of motion synthesis. However, many implementations of this approach are limited by uncertain convergence and local optimality of the solutions achieved, affecting overall robustness. To improve upon these issues, we propose a novel two-stage optimization framework: in the first stage, we find a solution to a Mixed-Integer …
Motional（莫雄公司）；Boston University（波士顿大学）；Iowa State University（爱荷华州立大学）
Autonomous vehicles must balance a complex set of objectives. There is no consensus on how they should do so, nor on a model for specifying a desired driving behavior. We created a dataset to help address some of these questions in a limited operating domain. The data consists of 92 traffic scenarios, with multiple ways of traversing each scenario. Multiple annotators expressed their preference between pairs of scenario traversals. We used the data to compare an instance of a rulebook, carefully hand-crafted independently of the dataset, with several interpretable machine learning models such …
MTA-RL: Robust Urban Driving via Multi-modal Transformer-based 3D Affordances and Reinforcement Learning
Dongguan Key Laboratory of Intelligent Equipment and Smart Industry, School of Advanced Engineering, Great Bay University（东莞智能装备与智能制造重点实验室，先进工程学院，大湾大学）；Chair of Applied Statistics, Technische Universität Dresden（应用统计学教授职位，德累斯顿技术大学）；Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI)（可扩展数据解析与人工智能中心（ScaDS.AI））；College of Automation, Guangdong University of Technology（自动化学院，广东技术大学）
本文提出MTA-RL框架，通过多模态Transformer-based 3D affordances和强化学习实现可靠的城市自动驾驶，提升样本效率和稳定性，优于现有基线方法。
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…
Oxford Robotics Institute, Dept. Engineering Science, University of Oxford（牛津大学工程科学系牛津机器人研究所）
We present a weakly-supervised approach to segmenting proposed drivable paths in images with the goal of autonomous driving in complex urban environments. Using recorded routes from a data collection vehicle, our proposed method generates vast quantities of labelled images containing proposed paths and obstacles without requiring manual annotation, which we then use to train a deep semantic segmentation network. With the trained network we can segment proposed paths and obstacles at run-time using a vehicle equipped with only a monocular camera without relying on explicit modelling of road or …
