NVIDIA DRIVE Map
NVIDIA DRIVE® Map is a multi-modal mapping platform designed to enable the highest levels of autonomy while improving safety. It combines the accuracy of ground truth mapping with the freshness and scale of AI-based fleet-sourced mapping. With four localization layers—camera, lidar, radar, and GNSS—DRIVE Map provides the redundancy and versatility required by the most advanced AI drivers. DRIVE Map is designed for the highest level of accuracy, the ground truth map engine creates DRIVE Maps using rich sensors—cameras, radars, lidars, and differential GNSS/IMU—with NVIDIA DRIVE Hyperion data collection vehicles. It achieves better than 5 cm accuracy for higher levels of autonomy (L3/L4) in selected environments, such as highways and urban environments. DRIVE Map is designed for near real-time operation and global scalability. Based on both ground truth and fleet-sourced data, it represents the collective memory of millions of vehicles.
Learn more
Parallel Domain Replica Sim
Parallel Domain Replica Sim enables the creation of high-fidelity, fully annotated, simulation-ready environments from users’ own captured data (photos, videos, scans). With PD Replica, you can generate near-pixel-perfect reconstructions of real-world scenes, transforming them into virtual environments that preserve visual detail and realism. PD Sim provides a Python API through which perception, machine learning, and autonomy teams can configure and run large-scale test scenarios and simulate sensor inputs (camera, lidar, radar, etc.) in either open- or closed-loop mode. These simulated sensor feeds come with full annotations, so developers can test their perception systems under a wide variety of conditions, lighting, weather, object configurations, and edge cases, without needing to collect real-world data for every scenario.
Learn more
Apollo Autonomous Vehicle Platform
Various sensors, such as LiDAR, cameras and radar collect environmental data surrounding the vehicle. Using sensor fusion technology perception algorithms can determine in real time the type, location, velocity and orientation of objects on the road. This autonomous perception system is backed by both Baidu’s big data and deep learning technologies, as well as a vast collection of real world labeled driving data. The large-scale deep-learning platform and GPU clusters. Simulation provides the ability to virtually drive millions of kilometers daily using an array of real world traffic and autonomous driving data. Through the simulation service, partners gain access to a large number of autonomous driving scenes to quickly test, validate, and optimize models with comprehensive coverage in a way that is safe and efficient.
Learn more
WaveFarer
WaveFarer is a high-fidelity radar simulator that accounts for multipath and scattering from structures and vehicles in the immediate environment of a radar system as well as key atmospheric and scattering effects for frequencies up to and beyond 100 GHz. Applications include simulation of automotive drive scenarios, indoor sensors, and far-field radar cross section (RCS). WaveFarer’s features enable fast and accurate analysis of scenarios with radars in close proximity to structures, targets, and other features in a simulated environment. WaveFarer is designed to support all applications relevant to the simulation and analysis of a radar system. For automotive radar, this includes evaluating radar sensor placement and target returns within a simulated drive scenario environment. For surveillance radar applications, this includes analysis of target radar cross section (RCS) and the impact of materials on results.
Learn more