NVIDIA DRIVE® Chauffeur is built on NVIDIA DRIVE Orin™ and the NVIDIA DRIVE SDK. It features the perception, mapping, and planning layers—using diverse DNNs trained on high-quality, real-world driving data and synthetic data—to handle both highway and urban traffic scenarios. These perception outputs can be used for both autonomous driving and mapping, delivering a personal chauffeur for your daily drive.
DRIVE Chauffeur is built using NVIDIA DRIVE Perception, which is designed to detect and classify objects, drivable spaces, lanes, and road markings, as well as traffic lights and signs. It can estimate distances to each detected object and fuse inputs from multiple heterogeneous sensor modalities.
DRIVE Chauffeur uses DRIVE Map, which encapsulates mapping and localization components. It’s built on two map engines: ground-truth and fleet-sourced. The ground truth map engine provides the accuracy required for high levels of autonomy and improves the data pipeline. The scalability of fleet-sourced maps, powered by MapStream, removes geographic restrictions for AV feature development.
The NVIDIA DRIVE Planning module serves as the brain of DRIVE Chauffeur and plans and controls the vehicle’s motion. It relies on a unified architecture to support active safety, driving, and parking functions. Using information from perception, prediction, localization, and other modules, it generates an optimal trajectory through a series of model-based and data-driven analyses. It also ensures the effective execution of the trajectory by means of precise control systems for the vehicle.
DRIVE Chauffeur works directly with DRIVE Concierge to remove the stress and hassles of daily driving. DRIVE Concierge provides access to intelligent services that are always on, using NVIDIA DRIVE IX and NVIDIA Omniverse ACE for real-time AI avatars. It’s tightly integrated with DRIVE Chauffeur for 3D in-cabin visualization, valet parking, and intelligent summon capabilities.
Find out how you can start developing AI cockpits for intelligent vehicles.