There is considerable evidence that deep neural networks are vulnerable to adversarial perturbations applied directly to their digital inputs. However, it remains an open question whether this translates to vulnerabilities in real systems. For example, an attack on self-driving cars would in practice entail modifying the driving environment, which then impacts the video inputs to the car's controller, thereby indirectly leading to incorrect driving decisions. Such attacks require accounting for system dynamics and tracking viewpoint changes. We propose a scalable approach for finding adversarial modifications of a simulated autonomous driving environment using a differentiable approximation for the mapping from environmental modifications (rectangles on the road) to the corresponding video inputs to the controller neural network. Given the parameters of the rectangles, our proposed differentiable mapping composites them onto pre-recorded video streams of the original environment, accounting for geometric and color variations. Moreover, we propose a multiple trajectory sampling approach that enables our attacks to be robust to a car's self-correcting behavior. When combined with a neural network-based controller, our approach allows the design of adversarial modifications through end-to-end gradient-based optimization. Using the Carla autonomous driving simulator, we show that our approach is significantly more scalable and far more effective at identifying autonomous vehicle vulnerabilities in simulation experiments than a state-of-the-art approach based on Bayesian Optimization.
University College London（伦敦大学学院）；Adobe Research（奥多比研究院）
Patterns, which are collections of elements arranged in regular or near-regular arrangements, are an important graphic art form and widely used due to their elegant simplicity and aesthetic appeal. When a pattern is encoded as a flat image without the underlying structure, manually editing the pattern is tedious and challenging as one has to both preserve the individual element shapes and their original relative arrangements. State-of-the-art deep learning frameworks that operate at the pixel level are unsuitable for manipulating such patterns. Specifically, these methods can easily disturb th…
Guaranteeing safety of perception-based learning systems is challenging due to the absence of ground-truth state information unlike in state-aware control scenarios. In this paper, we introduce a safety guaranteed learning framework for vision-based end-to-end autonomous driving. To this end, we design a learning system equipped with differentiable control barrier functions (dCBFs) that is trained end-to-end by gradient descent. Our models are composed of conventional neural network architectures and dCBFs. They are interpretable at scale, achieve great test performance under limited training …
UC San Diego（加州大学圣迭戈分校）；MIT（麻省理工学院）；Peking University（北京大学）；MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）
Simulated virtual environments serve as one of the main driving forces behind developing and evaluating skill learning algorithms. However, existing environments typically only simulate rigid body physics. Additionally, the simulation process usually does not provide gradients that might be useful for planning and control optimizations. We introduce a new differentiable physics benchmark called PasticineLab, which includes a diverse collection of soft body manipulation tasks. In each task, the agent uses manipulators to deform the plasticine into the desired configuration. The underlying physi…
Despite the numerous successes of machine learning over the past decade (image recognition, decision-making, NLP, image synthesis), self-driving technology has not yet followed the same trend. In this paper, we study the history, composition, and development bottlenecks of the modern self-driving stack. We argue that the slow progress is caused by approaches that require too much hand-engineering, an over-reliance on road testing, and high fleet deployment costs. We observe that the classical stack has several bottlenecks that preclude the necessary scale needed to capture the long tail of rar…
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…
University of Michigan（密歇根大学）；NVIDIA Research（英伟达研究院）；Arizona State University（亚利桑那州立大学）；Inceptio（嬴彻科技）；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）；University of California, Irvine（加州大学欧文分校）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
In Autonomous Driving (AD) systems, perception is both security and safety critical. Despite various prior studies on its security issues, all of them only consider attacks on camera- or LiDAR-based AD perception alone. However, production AD systems today predominantly adopt a Multi-Sensor Fusion (MSF) based design, which in principle can be more robust against these attacks under the assumption that not all fusion sources are (or can be) attacked at the same time. In this paper, we present the first study of security issues of MSF-based perception in AD systems. We directly challenge the bas…
NVIDIA（英伟达）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）
We consider the challenging problem of outdoor lighting estimation for the goal of photorealistic virtual object insertion into photographs. Existing works on outdoor lighting estimation typically simplify the scene lighting into an environment map which cannot capture the spatially-varying lighting effects in outdoor scenes. In this work, we propose a neural approach that estimates the 5D HDR light field from a single image, and a differentiable object insertion formulation that enables end-to-end training with image-based losses that encourage realism. Specifically, we design a hybrid lighti…
Uber ATG（Uber 先进技术集团）；University of Toronto（多伦多大学）
In this paper we propose a novel end-to-end learnable network that performs joint perception, prediction and motion planning for self-driving vehicles and produces interpretable intermediate representations. Unlike existing neural motion planners, our motion planning costs are consistent with our perception and prediction estimates. This is achieved by a novel differentiable semantic occupancy representation that is explicitly used as cost by the motion planning process. Our network is learned end-to-end from human demonstrations. The experiments in a large-scale manual-driving dataset and clo…
Predicting a vehicle's trajectory is an essential ability for autonomous vehicles navigating through complex urban traffic scenes. Bird's-eye-view roadmap information provides valuable information for making trajectory predictions, and while state-of-the-art models extract this information via image convolution, auxiliary loss functions can augment patterns inferred from deep learning by further encoding common knowledge of social and legal driving behaviors. Since human driving behavior is inherently multimodal, models which allow for multimodal output tend to outperform single-prediction mod…
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 …
Real2Sim: A Physics-driven and Editable Gaussian Splatting Framework for Autonomous Driving Scenes
Department of Civil and Environmental Engineering, Rensselaer Polytechnic Institute（拉特克利夫理工学院土木与环境工程系）；Department of Computer and Information Sciences, University of Delaware（德雷塞尔大学计算机与信息科学系）
Motion planning for safe autonomous driving requires learning how the environment around an ego-vehicle evolves with time. Ego-centric perception of driveable regions in a scene not only changes with the motion of actors in the environment, but also with the movement of the ego-vehicle itself. Self-supervised representations proposed for large-scale planning, such as ego-centric freespace, confound these two motions, making the representation difficult to use for downstream motion planners. In this paper, we use geometric occupancy as a natural alternative to view-dependent representations suc…
MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation Learning
School of EIC, Huazhong University of Science & Technology（华中科技大学电子信息与通信学院）；Institute of Artificial Intelligence, Huazhong University of Science & Technology（华中科技大学人工智能研究院）；Horizon Robotics
Monocular visual-inertial odometry (VIO) is a critical problem in robotics and autonomous driving. Traditional methods solve this problem based on filtering or optimization. While being fully interpretable, they rely on manual interference and empirical parameter tuning. On the other hand, learning-based approaches allow for end-to-end training but require a large number of training data to learn millions of parameters. However, the non-interpretable and heavy models hinder the generalization ability. In this paper, we propose a fully differentiable, and interpretable, bird-eye-view (BEV) base…
Efficient processing of high-res video streams is safety-critical for many robotics applications such as autonomous driving. To maintain real-time performance, many practical systems downsample the video stream. But this can hurt downstream tasks such as (small) object detection. Instead, we take inspiration from biological vision systems that allocate more foveal "pixels" to salient parts of the scene. We introduce FOVEA, an approach for intelligent downsampling that ensures salient image regions remain "magnified" in the downsampled output. Given a high-res image, FOVEA applies a differentia…
UniPAD: A Universal Pre-training Paradigm for Autonomous Driving
Zhejiang University（浙江大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；University of Science and Technology of China（中国科学技术大学）；The University of Sydney（悉尼大学）；HongKong University（香港大学）；Zhejiang Lab（之江实验室）；School of Software Technology, Zhejiang University（浙江大学软件学院）；Fullong Inc.（福龙公司）
Uber Advanced Technologies Group (ATG)（优步先进技术集团）；University of Florida（佛罗里达大学）
Motion prediction is a critical part of self-driving technology, responsible for inferring future behavior of traffic actors in autonomous vehicle's surroundings. In order to ensure safe and efficient operations, prediction models need to output accurate trajectories that obey the map constraints. In this paper, we address this task and propose a novel ellipse loss that allows the models to better reason about scene compliance and predict more realistic trajectories. Ellipse loss penalizes off-road predictions directly in a supervised manner, by projecting the output trajectories into the top-…
UncAD: Towards Safe End-to-end Autonomous Driving via Online Map Uncertainty
Key Laboratory of Safety Intelligent Mining in Non-coal Open-pit Mines, National Mine safety Administration, Guangdong Guangzhou, 510000, China（安全智能采矿非煤矿山重点实验室，国家矿山安全监察局，广东广州，510000，中国）；The State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China（人工智能学院，中国科学院大学，北京，中国）；EACON, Fujian, China（福建中国EACON）
SV-WAM: An Efficient Surround-View World-Action Model for End-to-End Autonomous Driving
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Chongqing Changan Technology Co., Ltd.（重庆长安科技有限公司）；Civil Aviation University of China（中国民航大学）；Beihang University（北京航空航天大学）；Guilin University of Electronic Technology（桂林电子科技大学）
Uber Advanced Technologies Group（优步先进技术集团）；University of Toronto（多伦多大学）
In this paper, we tackle the problem of relational behavior forecasting from sensor data. Towards this goal, we propose a novel spatially-aware graph neural network (SpAGNN) that models the interactions between agents in the scene. Specifically, we exploit a convolutional neural network to detect the actors and compute their initial states. A graph neural network then iteratively updates the actor states via a message passing process. Inspired by Gaussian belief propagation, we design the messages to be spatially-transformed parameters of the output distributions from neighboring agents. Our m…
We present a method to estimate lighting from a single image of an indoor scene. Previous work has used an environment map representation that does not account for the localized nature of indoor lighting. Instead, we represent lighting as a set of discrete 3D lights with geometric and photometric parameters. We train a deep neural network to regress these parameters from a single image, on a dataset of environment maps annotated with depth. We propose a differentiable layer to convert these parameters to an environment map to compute our loss; this bypasses the challenge of establishing corres…
ETH Zürich（苏黎世联邦理工学院）；Delft University of Technology（代尔夫特理工大学）；NVIDIA（英伟达）；University of Birmingham（伯明翰大学）
We propose GazeNeRF, a 3D-aware method for the task of gaze redirection. Existing gaze redirection methods operate on 2D images and struggle to generate 3D consistent results. Instead, we build on the intuition that the face region and eyeballs are separate 3D structures that move in a coordinated yet independent fashion. Our method leverages recent advancements in conditional image-based neural radiance fields and proposes a two-stream architecture that predicts volumetric features for the face and eye regions separately. Rigidly transforming the eye features via a 3D rotation matrix provides…
Information Technologies Institute (ITI), Centre for Research and Technology Hellas (CERTH)（希腊研究与技术中心信息技术研究所）；Universidad Politécnica de Madrid (UPM)（马德里理工大学）
Estimating a scene's lighting is a very important task when compositing synthetic content within real environments, with applications in mixed reality and post-production. In this work we present a data-driven model that estimates an HDR lighting environment map from a single LDR monocular spherical panorama. In addition to being a challenging and ill-posed problem, the lighting estimation task also suffers from a lack of facile illumination ground truth data, a fact that hinders the applicability of data-driven methods. We approach this problem differently, exploiting the availability of surf…
ETH Zürich（苏黎世联邦理工学院）；The University of Sydney（悉尼大学）；KU Leuven（鲁汶大学）
Network pruning has been the driving force for the acceleration of neural networks and the alleviation of model storage/transmission burden. With the advent of AutoML and neural architecture search (NAS), pruning has become topical with automatic mechanism and searching based architecture optimization. Yet, current automatic designs rely on either reinforcement learning or evolutionary algorithm. Due to the non-differentiability of those algorithms, the pruning algorithm needs a long searching stage before reaching the convergence. To circumvent this problem, this paper introduces a differenti…
LIGM, École des Ponts, Univ Gustave Eiffel, CNRS（LIGM，巴黎高科路桥学校，古斯塔夫·埃菲尔大学，法国国家科学研究中心）；Inria and DIENS (ENS-PSL, CNRS, Inria)（法国国家信息与自动化研究所和DIENS（巴黎高等师范学院-巴黎文理研究大学，法国国家科学研究中心，法国国家信息与自动化研究所））；Center for Data Science, New York University（纽约大学数据科学中心）
We present an unsupervised learning framework for decomposing images into layers of automatically discovered object models. Contrary to recent approaches that model image layers with autoencoder networks, we represent them as explicit transformations of a small set of prototypical images. Our model has three main components: (i) a set of object prototypes in the form of learnable images with a transparency channel, which we refer to as sprites; (ii) differentiable parametric functions predicting occlusions and transformation parameters necessary to instantiate the sprites in a given image; (ii…
