NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
NVIDIA（英伟达）
Aarti Basant, Amlan Kar, Despoina Paschalidou, Fangyin Wei, Francesco Ferroni, Guillermo Garcia Cobo, Haithem Turki, Huan Ling, Jaewoo Seo, James Lucas, Jay Zha… 展开作者
Aarti Basant, Amlan Kar, Despoina Paschalidou, Fangyin Wei, Francesco Ferroni, Guillermo Garcia Cobo, Haithem Turki, Huan Ling, Jaewoo Seo, James Lucas, Jay Zhangjie Wu, Jialiang Wang, Jonathan Lorraine, Jun Gao, Kai He, Katarina Tothova, Kevin Xie, Michal Tyszkiewicz, Qi Wu, Riccardo de Lutio, Ruilong Li, Sanja Fidler, Seung Wook Kim, Tianchang Shen, Tianshi Cao, Tobias Pfaff, William Lew, Xindi Wu, Xuanchi Ren, Yifan Lu, Yuxuan Zhang, Zan Gojcic, Zian Wang
As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-loop simulation, the driving policy model actively interacts with the environment, where its actions dynamically update the simulator state and directly influence the next set of generated sensor observations. While recent reconstruction-based neural simulators offer photorealism, they are fundamentally constrained by their initial captured data and struggle to generalize to highly dynamic or novel scenes. To overcome these limitations, we introduce OmniDreams, a foundation generative world model mid- and post-trained from the Cosmos diffusion model to autoregressively generate action-conditioned videos in real time. By leveraging the rich visual priors of Cosmos and mid- and post-training on 21k hours of driving scenarios, OmniDreams synthesizes complex, unobserved phenomena that are hard for traditional simulators to capture, such as extreme weather and unpredictable dynamic agent behaviors. Crucially, it autoregressively conditions its photorealistic sensor generation on past frames, the current simulator state, and immediate driving actions. Deployed in a closed-loop system with the Alpamayo 1 policy model and AlpaSim orchestrator, OmniDreams acts as a highly responsive, reactive environment, providing a scalable and comprehensive solution for training and evaluating next-generation autonomous driving policies. We additionally show preliminary results indicating that a world-action model (WAM) post-trained from OmniDreams achieves strong performance on the Physical AI Autonomous Vehicles NuRec dataset, surpassing the VLA-based Alpamayo 1.5 research policy model while using only 1/5 the total parameters. These results highlight the potential for a real-time world model like OmniDreams to also serve as a backbone for policy architectures.
Virtual Roads, Smarter Safety: A Digital Twin Framework for Mixed Autonomous Traffic Safety Analysis
Zachry Department of Civil and Environmental Engineering, Texas A&M University（土木与环境工程系，德克萨斯A&M大学）；Department of Landscape Architecture and Urban Planning（景观建筑与城市规划系）
A Semantic Observer Layer for Autonomous Vehicles: Pre-Deployment Feasibility Study of VLMs for Low-Latency Anomaly Detection
The City College of New York, Grove School of Engineering（纽约市立学院格罗夫工程学院）；Department of Mechanical and Aerospace Engineering, Tandon School of Engineering, New York University（纽约大学坦登工程学院机械与航空航天工程系）；Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University（纽约大学坦登工程学院电气与计算机工程系）
A convolutional neural network (CNN) approach is used to implement a level 2 autonomous vehicle by mapping pixels from the camera input to the steering commands. The network automatically learns the maximum variable features from the camera input, hence requires minimal human intervention. Given realistic frames as input, the driving policy trained on the dataset by NVIDIA and Udacity can adapt to real-world driving in a controlled environment. The CNN is tested on the CARLA open-source driving simulator. Details of a beta-testing platform are also presented, which consists of an ultrasonic se…
Esslingen University of Applied Sciences（埃斯林根应用科学大学）
Environmental perception is an important aspect within the field of autonomous vehicles that provides crucial information about the driving domain, including but not limited to identifying clear driving areas and surrounding obstacles. Semantic segmentation is a widely used perception method for self-driving cars that associates each pixel of an image with a predefined class. In this context, several segmentation models are evaluated regarding accuracy and efficiency. Experimental results on the generated dataset confirm that the segmentation model FasterSeg is fast enough to be used in realti…
Webank（微众银行）；Hong Kong University of Science and Technology（香港科技大学）
Reinforcement learning (RL) is widely used in autonomous driving tasks and training RL models typically involves in a multi-step process: pre-training RL models on simulators, uploading the pre-trained model to real-life robots, and fine-tuning the weight parameters on robot vehicles. This sequential process is extremely time-consuming and more importantly, knowledge from the fine-tuned model stays local and can not be re-used or leveraged collaboratively. To tackle this problem, we present an online federated RL transfer process for real-time knowledge extraction where all the participant age…
The condition assessment of road surfaces is essential to ensure their serviceability while still providing maximum road traffic safety. This paper presents a robust stereo vision system embedded in an unmanned aerial vehicle (UAV). The perspective view of the target image is first transformed into the reference view, and this not only improves the disparity accuracy, but also reduces the algorithm's computational complexity. The cost volumes generated from stereo matching are then filtered using a bilateral filter. The latter has been proved to be a feasible solution for the functional minimi…
German Aerospace Center (DLR)（德国航空航天中心（DLR））；Technical University of Munich（慕尼黑工业大学）
On-board real-time vehicle detection is of great significance for UAVs and other embedded mobile platforms. We propose a computationally inexpensive detection network for vehicle detection in UAV imagery which we call ShuffleDet. In order to enhance the speed-wise performance, we construct our method primarily using channel shuffling and grouped convolutions. We apply inception modules and deformable modules to consider the size and geometric shape of the vehicles. ShuffleDet is evaluated on CARPK and PUCPR+ datasets and compared against the state-of-the-art real-time object detection networks…
Despite the rapid improvement of autonomous driving technology in recent years, automotive manufacturers must resolve liability issues to commercialize autonomous passenger car of SAE J3016 Level 3 or higher. To cope with the product liability law, manufacturers develop autonomous driving systems in compliance with international standards for safety such as ISO 26262 and ISO 21448. Concerning the safety of the intended functionality (SOTIF) requirement in ISO 26262, the driving policy recommends providing an explicit rational basis for maneuver decisions. In this case, mathematical models such…
University of Maryland（马里兰大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
Multi-camera vehicle tracking is one of the most complicated tasks in Computer Vision as it involves distinct tasks including Vehicle Detection, Tracking, and Re-identification. Despite the challenges, multi-camera vehicle tracking has immense potential in transportation applications including speed, volume, origin-destination (O-D), and routing data generation. Several recent works have addressed the multi-camera tracking problem. However, most of the effort has gone towards improving accuracy on high-quality benchmark datasets while disregarding lower camera resolutions, compression artifact…
NVIDIA Corporation（英伟达公司）；New York University（纽约大学）；Google Research（谷歌研究院）
As part of a complete software stack for autonomous driving, NVIDIA has created a neural-network-based system, known as PilotNet, which outputs steering angles given images of the road ahead. PilotNet is trained using road images paired with the steering angles generated by a human driving a data-collection car. It derives the necessary domain knowledge by observing human drivers. This eliminates the need for human engineers to anticipate what is important in an image and foresee all the necessary rules for safe driving. Road tests demonstrated that PilotNet can successfully perform lane keepi…
The Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）；General Motors Global R&D（通用汽车全球研发中心）
A safe and robust on-road navigation system is a crucial component of achieving fully automated vehicles. NVIDIA recently proposed an End-to-End algorithm that can directly learn steering commands from raw pixels of a front camera by using one convolutional neural network. In this paper, we leverage auxiliary information aside from raw images and design a novel network structure, called Auxiliary Task Network (ATN), to help boost the driving performance while maintaining the advantage of minimal training data and an End-to-End training method. In this network, we introduce human prior knowledg…
Evidence-Based Landing Site Selection and Vison-Based Landing for UAVs in Unstructured Environments
Aerospace Research Centre, National Research Council Canada（加拿大国家研究委员会航空航天研究中心）；Department of Mechanical and Industrial Engineering, Toronto Metropolitan University（多伦多 Metropolitan 大学机械与工业工程系）
Autonomous machines (e.g., vehicles, mobile robots, drones) require sophisticated 3D mapping to perceive the dynamic environment. However, maintaining a real-time 3D map is expensive both in terms of compute and memory requirements, especially for resource-constrained edge machines. Probabilistic OctoMap is a reliable and memory-efficient 3D dense map model to represent the full environment, with dynamic voxel node pruning and expansion capacity. This paper presents the first efficient accelerator solution, i.e. OMU, to enable real-time probabilistic 3D mapping at the edge. To improve the perf…
In autonomous vehicles (AVs), early warning systems rely on collision prediction to ensure occupant safety. However, state-of-the-art methods using deep convolutional networks either fail at modeling collisions or are too expensive/slow, making them less suitable for deployment on AV edge hardware. To address these limitations, we propose sg2vec, a spatio-temporal scene-graph embedding methodology that uses Graph Neural Network (GNN) and Long Short-Term Memory (LSTM) layers to predict future collisions via visual scene perception. We demonstrate that sg2vec predicts collisions 8.11% more accur…
Real-time semantic image segmentation on platforms subject to size, weight and power (SWaP) constraints is a key area of interest for air surveillance and inspection. In this work, we propose MAVNet: a small, light-weight, deep neural network for real-time semantic segmentation on micro Aerial Vehicles (MAVs). MAVNet, inspired by ERFNet, features 400 times fewer parameters and achieves comparable performance with some reference models in empirical experiments. Our model achieves a trade-off between speed and accuracy, achieving up to 48 FPS on an NVIDIA 1080Ti and 9 FPS on the NVIDIA Jetson Xa…
École de Technologie Supérieure（高等工程技术学院）；King Saud University（沙特国王大学）；Waseda University（早稻田大学）
Driven by the ever-increasing requirements of autonomous vehicles, such as traffic monitoring and driving assistant, deep learning-based object detection (DL-OD) has been increasingly attractive in intelligent transportation systems. However, it is difficult for the existing DL-OD schemes to realize the responsible, cost-saving, and energy-efficient autonomous vehicle systems due to low their inherent defects of low timeliness and high energy consumption. In this paper, we propose an object detection (OD) system based on edge-cloud cooperation and reconstructive convolutional neural networks, …
WareFly-VLA: A Vision-Language-Action Framework for UAV Navigation and Human Tracking in Smart Warehouses
Center for AI Research, VinUniversity（VinUniversity人工智能研究中心）；College of Engineering and Computer Science, VinUniversity（VinUniversity工程与计算机科学学院）；VinRobotics（VinRobotics公司）
Although autonomous vehicles (AVs) are expected to revolutionize transportation, robust perception across a wide range of driving contexts remains a significant challenge. Techniques to fuse sensor data from camera, radar, and lidar sensors have been proposed to improve AV perception. However, existing methods are insufficiently robust in difficult driving contexts (e.g., bad weather, low light, sensor obstruction) due to rigidity in their fusion implementations. These methods fall into two broad categories: (i) early fusion, which fails when sensor data is noisy or obscured, and (ii) late fus…
Among several road hazards that are present in any paved way in the world, potholes are one of the most annoying and also involving higher maintenance costs. There exists an increasing interest on the automated detection of these hazards enabled by technological and research progress. Our research work tackled the challenge of pothole detection from images of real world road scenes. The main novelty resides on the application of the latest progress in AI to learn the visual appearance of potholes. We built a large dataset of images with pothole annotations. They contained road scenes from diff…
Moving object detection and segmentation is an essential task in the Autonomous Driving pipeline. Detecting and isolating static and moving components of a vehicle's surroundings are particularly crucial in path planning and localization tasks. This paper proposes a novel real-time architecture for motion segmentation of Light Detection and Ranging (LiDAR) data. We use three successive scans of LiDAR data in 2D Bird's Eye View (BEV) representation to perform pixel-wise classification as static or moving. Furthermore, we propose a novel data augmentation technique to reduce the significant clas…
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation (IOSB)（弗劳恩霍夫光学、系统技术与图像 exploitation 研究所）；Fraunhofer Center for Machine Learning（弗劳恩霍夫机器学习中心）；Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）；Institute of Photogrammetry and Remote Sensing, Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院摄影测量与遥感研究所）；Vision and Fusion Laboratory, Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院视觉与融合实验室）
With the emergence of low-cost robotic systems, such as unmanned aerial vehicle, the importance of embedded high-performance image processing has increased. For a long time, FPGAs were the only processing hardware that were capable of high-performance computing, while at the same time preserving a low power consumption, essential for embedded systems. However, the recently increasing availability of embedded GPU-based systems, such as the NVIDIA Jetson series, comprised of an ARM CPU and a NVIDIA Tegra GPU, allows for massively parallel embedded computing on graphics hardware. With this in min…
Binghamton University, The State University of New York（纽约州立大学宾汉姆顿分校）；Harbin Institute of Technology（哈尔滨工业大学）；The State University of New York at Buffalo（纽约州立大学布法罗分校）
Real-time accurate detection of three-dimensional (3D) objects is a fundamental necessity for self-driving vehicles. Most existing computer vision approaches are based on convolutional neural networks (CNNs). Although the CNN-based approaches can achieve high detection accuracy, their high energy consumption is a severe drawback. To resolve this problem, novel energy efficient approaches should be explored. Spiking neural network (SNN) is a promising candidate because it has orders-of-magnitude lower energy consumption than CNN. Unfortunately, the studying of SNN has been limited in small netw…
TSLA: A Task-Specific Learning Adaptation for Semantic Segmentation on Autonomous Vehicles Platform
Department of Electrical and Computer Engineering, Northeastern University（电气与计算机工程系，东北大学）；Robotics Institute, Carnegie Mellon University（机器人研究所，卡内基梅隆大学）；School of Computing at the University of Georgia（佐治亚大学计算机学院）；Knight Foundation School of Computing & Information Sciences at Florida International University（佛罗里达国际大学Knight基金会计算机与信息科学学院）
Beihang University（北京航空航天大学）；JD.COM Inc（京东集团）；Tongji University（同济大学）；Democritus University of Thrace（德谟克利特大学）
Estimating a scene's depth to achieve collision avoidance against moving pedestrians is a crucial and fundamental problem in the robotic field. This paper proposes a novel, low complexity network architecture for fast and accurate human depth estimation and segmentation in indoor environments, aiming to applications for resource-constrained platforms (including battery-powered aerial, micro-aerial, and ground vehicles) with a monocular camera being the primary perception module. Following the encoder-decoder structure, the proposed framework consists of two branches, one for depth prediction a…
In an autonomous driving system, it is essential to recognize vehicles, pedestrians and cyclists from images. Besides the high accuracy of the prediction, the requirement of real-time running brings new challenges for convolutional network models. In this report, we introduce a real-time method to detect the 2D objects from images. We aggregate several popular one-stage object detectors and train the models of variety input strategies independently, to yield better performance for accurate multi-scale detection of each category, especially for small objects. For model acceleration, we leverage…
The Era of End-to-End Autonomy: Transitioning from Rule-Based Driving to Large Driving Models
The Australian Centre for Robotics, School of Aeronautical, Mechanical and Mechatronic Engineering, The University of Sydney（澳大利亚机器人中心，航空航天、机械及机电工程学院，悉尼大学）
