Jeffrey Hawke, Richard Shen, Corina Gurau, Siddharth Sharma, Daniele Reda, Nikolay Nikolov, Przemyslaw Mazur, Sean Micklethwaite, Nicolas Griffiths, Amar Shah, Alex Kendall
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 majority of such systems have been primarily evaluated in simulation - a simple domain, which lacks real-world complexities. Motivated by these challenges, we focus on learning representations of semantics, geometry and motion with computer vision for IL from human driving demonstrations. As our main contribution, we present an end-to-end conditional imitation learning approach, combining both lateral and longitudinal control on a real vehicle for following urban routes with simple traffic. We address inherent dataset bias by data balancing, training our final policy on approximately 30 hours of demonstrations gathered over six months. We evaluate our method on an autonomous vehicle by driving 35km of novel routes in European urban streets.
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…
The decision and planning system for autonomous driving in urban environments is hard to design. Most current methods manually design the driving policy, which can be expensive to develop and maintain at scale. Instead, with imitation learning we only need to collect data and the computer will learn and improve the driving policy automatically. However, existing imitation learning methods for autonomous driving are hardly performing well for complex urban scenarios. Moreover, the safety is not guaranteed when we use a deep neural network policy. In this paper, we proposed a framework to learn …
Autonomous driving is a complex task, which has been tackled since the first self-driving car ALVINN in 1989, with a supervised learning approach, or behavioral cloning (BC). In BC, a neural network is trained with state-action pairs that constitute the training set made by an expert, i.e., a human driver. However, this type of imitation learning does not take into account the temporal dependencies that might exist between actions taken in different moments of a navigation trajectory. These type of tasks are better handled by reinforcement learning (RL) algorithms, which need to define a rewar…
Intel Labs（英特尔实验室）；Computer Vision Center & Univ. Autonoma de Barcelona（计算机视觉中心与巴塞罗那自治大学）；King Abdullah University of Science & Technology（阿卜杜拉国王科技大学）
Deep networks trained on demonstrations of human driving have learned to follow roads and avoid obstacles. However, driving policies trained via imitation learning cannot be controlled at test time. A vehicle trained end-to-end to imitate an expert cannot be guided to take a specific turn at an upcoming intersection. This limits the utility of such systems. We propose to condition imitation learning on high-level command input. At test time, the learned driving policy functions as a chauffeur that handles sensorimotor coordination but continues to respond to navigational commands. We evaluate …
In recent years, great efforts have been devoted to deep imitation learning for autonomous driving control, where raw sensory inputs are directly mapped to control actions. However, navigating through densely populated intersections remains a challenging task due to uncertainty caused by uncertain traffic participants. We focus on autonomous navigation at crowded intersections that require interaction with pedestrians. A multi-task conditional imitation learning framework is proposed to adapt both lateral and longitudinal control tasks for safe and efficient interaction. A new benchmark called…
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；University of Macau（澳门大学）
Existing imitation learning methods suffer from low efficiency and generalization ability when facing the road option problem in an urban environment. In this paper, we propose a yaw-guided imitation learning method to improve the road option performance in an end-to-end autonomous driving paradigm in terms of the efficiency of exploiting training samples and adaptability to changing environments. Specifically, the yaw information is provided by the trajectory of the navigation map. Our end-to-end architecture, Yaw-guided Imitation Learning with ResNet34 Attention (YILRatt), integrates the Res…
Imitation learning is a promising approach to end-to-end training of autonomous vehicle controllers. Typically the driving process with such approaches is entirely automatic and black-box, although in practice it is desirable to control the vehicle through high-level commands, such as telling it which way to go at an intersection. In existing work this has been accomplished by the application of a branched neural architecture, since directly providing the command as an additional input to the controller often results in the command being ignored. In this work we overcome this limitation by lea…
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…
University of Tübingen（图宾根大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
How should we integrate representations from complementary sensors for autonomous driving? Geometry-based fusion has shown promise for perception (e.g. object detection, motion forecasting). However, in the context of end-to-end driving, we find that imitation learning based on existing sensor fusion methods underperforms in complex driving scenarios with a high density of dynamic agents. Therefore, we propose TransFuser, a mechanism to integrate image and LiDAR representations using self-attention. Our approach uses transformer modules at multiple resolutions to fuse perspective view and bird…
Tsinghua University（清华大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Pennsylvania（宾夕法尼亚大学）；Shanghai Qi Zhi Institute（上海期智研究院）
Imitation learning trains control policies by mimicking pre-recorded expert demonstrations. In partially observable settings, imitation policies must rely on observation histories, but many seemingly paradoxical results show better performance for policies that only access the most recent observation. Recent solutions ranging from causal graph learning to deep information bottlenecks have shown promising results, but failed to scale to realistic settings such as visual imitation. We propose a solution that outperforms these prior approaches by upweighting demonstration keyframes corresponding …
The American University in Cairo（开罗美国大学）；Valeo Schalter und Sensoren GmbH（法雷奥开关与传感器有限公司）；Valeo Egypt（法雷奥埃及公司）
Conditional imitation learning (CIL) trains deep neural networks, in an end-to-end manner, to mimic human driving. This approach has demonstrated suitable vehicle control when following roads, avoiding obstacles, or taking specific turns at intersections to reach a destination. Unfortunately, performance dramatically decreases when deployed to unseen environments and is inconsistent against varying weather conditions. Most importantly, the current CIL fails to avoid static road blockages. In this work, we propose a solution to those deficiencies. First, we fuse the laser scanner with the regul…
Imitation learning is becoming more and more successful for autonomous driving. End-to-end (raw signal to command) performs well on relatively simple tasks (lane keeping and navigation). Mid-to-mid (environment abstraction to mid-level trajectory representation) or direct perception (raw signal to performance) approaches strive to handle more complex, real life environment and tasks (e.g. complex intersection). In this work, we show that complex urban situations can be handled with raw signal input and mid-level representation. We build a hybrid end-to-mid approach predicting trajectories for …
We demonstrate the first large-scale application of model-based generative adversarial imitation learning (MGAIL) to the task of dense urban self-driving. We augment standard MGAIL using a hierarchical model to enable generalization to arbitrary goal routes, and measure performance using a closed-loop evaluation framework with simulated interactive agents. We train policies from expert trajectories collected from real vehicles driving over 100,000 miles in San Francisco, and demonstrate a steerable policy that can navigate robustly even in a zero-shot setting, generalizing to synthetic scenari…
In this paper, we propose Sparse Imitation Reinforcement Learning (SIRL), a hybrid end-to-end control policy that combines the sparse expert driving knowledge with reinforcement learning (RL) policy for autonomous driving (AD) task in CARLA simulation environment. The sparse expert is designed based on hand-crafted rules which is suboptimal but provides a risk-averse strategy by enforcing experience for critical scenarios such as pedestrian and vehicle avoidance, and traffic light detection. As it has been demonstrated, training a RL agent from scratch is data-inefficient and time consuming pa…
Mines Paris - PSL University（巴黎矿业学院-PSL大学）；Valeo DAR（法雷奥DAR）
Deep reinforcement learning (DRL) has been demonstrated to be effective for several complex decision-making applications such as autonomous driving and robotics. However, DRL is notoriously limited by its high sample complexity and its lack of stability. Prior knowledge, e.g. as expert demonstrations, is often available but challenging to leverage to mitigate these issues. In this paper, we propose General Reinforced Imitation (GRI), a novel method which combines benefits from exploration and expert data and is straightforward to implement over any off-policy RL algorithm. We make one simplify…
Control policies from imitation learning can often fail to generalize to novel environments due to imperfect demonstrations or the inability of imitation learning algorithms to accurately infer the expert's policies. In this paper, we present rigorous generalization guarantees for imitation learning by leveraging the Probably Approximately Correct (PAC)-Bayes framework to provide upper bounds on the expected cost of policies in novel environments. We propose a two-stage training method where a latent policy distribution is first embedded with multi-modal expert behavior using a conditional var…
HTNav: A Hybrid Navigation Framework with Tiered Structure for Urban Aerial Vision-and-Language Navigation
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education（教育部脑机智能技术重点实验室）
ETH Zurich（苏黎世联邦理工学院）；Southern University of Science and Technology（南方科技大学）；The Chinese University of Hong Kong（香港中文大学）
Interactions with either environments or expert policies during training are needed for most of the current imitation learning (IL) algorithms. For IL problems with no interactions, a typical approach is Behavior Cloning (BC). However, BC-like methods tend to be affected by distribution shift. To mitigate this problem, we come up with a Robust Model-Based Imitation Learning (RMBIL) framework that casts imitation learning as an end-to-end differentiable nonlinear closed-loop tracking problem. RMBIL applies Neural ODE to learn a precise multi-step dynamics and a robust tracking controller via No…
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 …
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…
Beijing University of Posts and Telecommunications（北京邮电大学）；Beijing Information Science and Technology University（北京信息科技大学）
Intelligent Transportation System (ITS) has become one of the essential components in Industry 4.0. As one of the critical indicators of ITS, efficiency has attracted wide attention from researchers. However, the next generation of urban traffic carried by multiple transport service providers may prohibit the raw data interaction among multiple regions for privacy reasons, easily ignored in the existing research. This paper puts forward a federated learning-based vehicle control framework to solve the above problem, including interactors, trainers, and an aggregator. In addition, the density-a…
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Tübingen（图宾根大学）
How should representations from complementary sensors be integrated for autonomous driving? Geometry-based sensor fusion has shown great promise for perception tasks such as object detection and motion forecasting. However, for the actual driving task, the global context of the 3D scene is key, e.g. a change in traffic light state can affect the behavior of a vehicle geometrically distant from that traffic light. Geometry alone may therefore be insufficient for effectively fusing representations in end-to-end driving models. In this work, we demonstrate that imitation learning policies based o…
In this paper we present the first safe system for full control of self-driving vehicles trained from human demonstrations and deployed in challenging, real-world, urban environments. Current industry-standard solutions use rule-based systems for planning. Although they perform reasonably well in common scenarios, the engineering complexity renders this approach incompatible with human-level performance. On the other hand, the performance of machine-learned (ML) planning solutions can be improved by simply adding more exemplar data. However, ML methods cannot offer safety guarantees and someti…
The Hong Kong University of Science and Technology（香港科技大学）
Traditional model-based reinforcement learning (RL) methods generate forward rollout traces using the learnt dynamics model to reduce interactions with the real environment. The recent model-based RL method considers the way to learn a backward model that specifies the conditional probability of the previous state given the previous action and the current state to additionally generate backward rollout trajectories. However, in this type of model-based method, the samples derived from backward rollouts and those from forward rollouts are simply aggregated together to optimize the policy via th…
University of Washington（华盛顿大学）；NVIDIA（英伟达）；KTH Royal Institute of Technology（瑞典皇家理工学院）；Allen Institute for AI（艾伦人工智能研究所）
Widespread adoption of self-driving cars will depend not only on their safety but largely on their ability to interact with human users. Just like human drivers, self-driving cars will be expected to understand and safely follow natural-language directions that suddenly alter the pre-planned route according to user's preference or in presence of ambiguities, particularly in locations with poor or outdated map coverage. To this end, we propose a language-grounded driving agent implementing a hierarchical policy using recurrent layers and gated attention. The hierarchical approach enables us to …
Restoring Noisy Demonstration for Imitation Learning With Diffusion Models
Graduate Institute of Communication Engineering, National Taiwan University（国立台湾大学通信工程研究所）；Data Science Degree Program, National Taiwan University and Academia Sinica（国立台湾大学数据科学学士学位计划）；Department of Electrical Engineering, National Taiwan University（国立台湾大学电子工程系）
Toyohashi University of Technology（丰桥技术科学大学）；University of Eastern Finland（东芬兰大学）
Autonomous driving systems need to handle complex scenarios such as lane following, avoiding collisions, taking turns, and responding to traffic signals. In recent years, approaches based on end-to-end behavioral cloning have demonstrated remarkable performance in point-to-point navigational scenarios, using a realistic simulator and standard benchmarks. Offline imitation learning is readily available, as it does not require expensive hand annotation or interaction with the target environment, but it is difficult to obtain a reliable system. In addition, existing methods have not specifically …
