Operating Systems
Supported operating
systems include
Microsoft Windows
and Linux Ubuntu
aiSim | The Automotive Simulator for ADAS & Autonomous Driving
aiSim provides an ideal testing environment to investigate and validate AD systems' performance in high-mileage tests and adverse driving scenarios, focusing on virtual, high-fidelity sensor data. How? Check out some of the main features of aiSim:
Physics-based sensor & environment simulation
Simulate challenging weather conditions, including snowstorms, heavy rain, fog, and sunshine, and complex sensor setups supported by distributed rendering over multiple GPUs, all based on the laws of physics, and enabling run-time changes in the environmental conditions.
Neural reconstruction-based digital twin 3D environments
Leverage digital twin 3D environments of real-world locations across all relevant Operational Design Domains (ODDs), including highways, urban areas, and parking zones of place from all over the world.
Automotive grade
aiSim is the world’s first ISO 26262, ASIL-D-certified automotive simulator for verification and validation. The certification is enabled by the deterministic and physics-based sensor & environment simulation and it covers all its capabilities, including the simulation of all major sensor modalities.
Flexible architecture & easy integration
aiSim has been architected in a modular way with C++ / Python APIs to ensure the easy integration with any System under test (SuT) and CI/CD pipeline. In addition, aiSim’s open SDK allows developers to create custom integrations into their testing toolchains.
Extensive 3D asset library & mature content pipeline
aiSim 5 provides a comprehensive set of 3D assets and all related tools needed to set up diverse, high-fidelity environments, including vehicles, vulnerable road users, maps, assets, and scenarios.
aiFab, scenario randomization for smart edge case detection
Create great volumes of diverse synthetic data with the variability needed to replicate real-world conditions for training and testing your AD software with aiFab’s domain randomization capabilities.
AI-based Rendering
aiSim AIR engine
The cornerstone of aiSim is aiSim AIR, bringing AI-based rendering for multi-sensor simulation. Offering high-quality virtual sensor data streams while optimizing resource usage, aiSim™ AIR introduces features such as high parallelism, reduced memory footprint, balanced workloads, and asynchronous data transfer – while keeping all the benefits of the previous aiSim generations.
Multi-sensor simulation powerhouse
Experience the evolution in simulation with aiSim™ AIR, the beating heart of aiSim. Delivering unparalleled performance, it optimizes resources, ensures ISO26262 compliance, and seamlessly transitions between real-time HiL to SiL – all with cutting-edge AI-based rendering techniques for a truly immersive experience.
Synthetic data generation on another level
Discover a new era in simulation with aiSim, now enriched by aiFab. Redefining smart scenario creation, aiFab seamlessly integrates into the aiSim workflow, offering features like scenario variation, detailed statistics, and an intuitive user interface. Using large language model-based techniques, aiFab simplifies environment and scenario creation, making smart scenarios more accessible than ever before.
Click here to see aiFab's features
Easy to use and easy to adapt
With aiSim comes a new level of accessibility and adaptability. Boasting open APIs for sensors, scenario & map management, and vehicle dynamics, along with a comprehensive SDK featuring example codes across multiple platforms, aiSim 5 seamlessly integrates with industry-standard toolchains, ensuring unprecedented interoperability. Experience user-friendly interaction through an intuitive Graphical User Interface (GUI) and web deployment.
Deterministic environment and weather simulation
ADAS & AD functions heavily rely on sensors to perceive the environment. For this, it is essential to simulate the environment perception of the involved sensors correctly. aiSim's state-of-the-art technology that appropriately simulates the physical environment and weather effects. It can consistently provide a single source of truth for all the simulated types, which is crucial for multi-sensor, neural network-based perception systems.
aiSim's proprietary, real-time rendering engine addresses all the requirements for a physically correct environment and weather simulation with complete determinism and repeatability. In aiSim, a broad range of weather conditions, including snowstorms, heavy rain, fog, and sunshine, can be simulated by leveraging state-of-the-art ray-tracing and rasterization technologies. In addition, multiple road parameters, including road painting deterioration and road degradation, can be easily configured to create even more diverse and challenging environments for perception stacks.
Interested in details?
Explore more of aiSim's capabilities
