# Autonomous Driving

GAIA-2 is an advanced video generation model developed by Wayve, designed to provide diverse and complex driving scenarios for autonomous driving systems to improve safety and reliability. The model addresses the limitations of relying on real-world data collection by generating synthetic data, capable of creating various driving situations, including both regular and edge cases. GAIA-2 supports the simulation of various geographical and environmental conditions, helping developers quickly test and verify autonomous driving algorithms without high costs.

NVIDIA Cosmos is an advanced foundational model platform aimed at accelerating the development of physical AI systems, such as autonomous vehicles and robotics. It provides a range of pre-trained generative models, advanced tokenizers, and accelerated data processing pipelines to make it easier for developers to build and optimize physical AI applications. With its open model licensing, Cosmos reduces development costs and enhances efficiency, making it suitable for businesses and research institutions of various sizes.

OpenEMMA is an open-source project that replicates Waymo's EMMA model, providing an end-to-end framework for motion planning of autonomous vehicles. This model utilizes pre-trained Vision-Language Models (VLMs) such as GPT-4 and LLaVA to integrate text and forward-facing camera inputs, achieving precise predictions of future path points and providing decision rationale. OpenEMMA aims to provide accessible tools for researchers and developers to advance research and applications in autonomous driving.

Smart AI Selection is a comprehensive platform focused on the field of artificial intelligence, aiming to gain insight into industry development prospects and showcase selected AI products and applications from around the world. The platform offers rich learning resources and case studies of industry integration, helping users understand AI trends and collaborate with AI technology to create a better future.

DiffusionDrive is a truncated diffusion model designed for real-time end-to-end autonomous driving. It accelerates computation speed by reducing diffusion denoising steps while maintaining high accuracy and variability. The model learns directly from human demonstrations, enabling real-time driving decisions without complex preprocessing or postprocessing steps. DiffusionDrive achieved a groundbreaking result of 88.1 PDMS on the NAVSIM benchmark and can operate at 45 FPS.

We, Robot is a page by Tesla showcasing its vision in the fields of autonomous driving technology and robotics. It emphasizes Tesla's commitment to creating a sustainable future, improving transportation efficiency, affordability, and safety. The page features Tesla's full self-driving technology (supervised) and the potential applications of future autonomous vehicles and robots, such as Robotaxi, Robovan, and Tesla Bot. These technologies aim to enhance everyday convenience through automation while reducing traffic accidents and lowering transportation costs.

Depth Pro is a research project for monocular depth estimation that can rapidly generate high-precision depth maps. This model utilizes multi-scale visual transformers for dense predictions and trains on both real and synthetic datasets to achieve high accuracy and detail capture. It generates a 2.25 million pixel depth map on standard GPUs in just 0.3 seconds, making it fast and precise, highly significant for fields such as machine vision and augmented reality.

OmniRe is a comprehensive method for efficiently reconstructing high-fidelity dynamic urban scenes from device logs. This technology achieves a complete reconstruction of different objects in the scene by constructing a dynamic neural scene graph based on Gaussian representations and building multiple local canonical spaces to simulate various dynamic actors, including vehicles, pedestrians, and cyclists. OmniRe enables comprehensive reconstruction of different objects present in a scene, allowing for real-time simulation of reconstructed scenes involving all participants. Extensive evaluations on the Waymo dataset show that OmniRe significantly outperforms previous state-of-the-art methods both quantitatively and qualitatively.

Boden is a provider of data solutions focusing on the artificial intelligence field, offering a complete suite of data processing services and AI algorithm solutions ranging from data collection, synchronization, and cleaning to smart data annotation and big data closed-loop platforms. Our primary application areas include autonomous driving, new retail, intelligent transportation, and smart governance, with a commitment to improving data processing efficiency and intelligence levels.

Silo AI, Europe's largest private artificial intelligence laboratory, collaborates with industry leaders to develop intelligent devices, autonomous vehicles, Industry 4.0 solutions, and smart cities. Its products and technologies are dedicated to bringing cutting-edge artificial intelligence to production, delivering tangible benefits to its clients.

DriveVLM is an autonomous driving system that leverages visual language models (VLMs) to augment scene understanding and planning capabilities. The system employs a unique combination of reasoning modules, encompassing scene description, scene analysis, and hierarchical planning, to enhance comprehension of complex and long-tail scenarios. Addressing the limitations of VLMs in spatial reasoning and computational demands, DriveVLM-Dual was developed as a hybrid system, integrating the strengths of DriveVLM with traditional autonomous driving pipelines. Experiments on the nuScenes and SUP-AD datasets demonstrate the effectiveness of DriveVLM and DriveVLM-Dual in handling complex and unpredictable driving conditions. Ultimately, DriveVLM-Dual has been deployed in production vehicles, validating its efficacy in real-world autonomous driving environments.

GenAD, the first large-scale autonomous driving video generation model jointly launched by Shanghai Artificial Intelligence Laboratory with Hong Kong University of Science and Technology, University of Tübingen in Germany, and the University of Hong Kong, predicts and simulates real-world scenarios to support research and application of autonomous driving technology. GenAD exhibits strong capabilities in understanding complex dynamic environments, adapting to open-world scenarios, and precise predictions. It can be controlled through language and driving trajectories, showcasing its potential for application in autonomous driving planning tasks, thus contributing to improved driving safety and efficiency.

Scale AI is a trusted provider of high-quality training data for companies worldwide. Its data powers AI applications in autonomous driving, augmented reality/virtual reality, robotics, and more.