Search
aiSim 5
The Most Scalable, High-Fidelity Sensor and Environment Simulation System for ADAS/AD Development
Contact Us

aiSim The simulation software provides a platform for the development, validation and testing of automated driving development with extreme simulation. With a highly accurate virtual environment, development teams can accelerate the R&D process and conduct extreme tests with safety in mind. Three core technologies: AI-based Digital Twin scene construction, highly optimized Sensor Simulation, and a self-developed rendering engine with accurate and reproducible rendering.

 

Functions

Authoritative certification to accelerate the process of global compliance

aiSim is the world's first software to receive the ISO 26262 ASIL-D A certified simulation platform with a complete built-in Euro NCAP We provide a high-confidence, closed-loop test environment that ensures virtual validation results meet international safety standards and shorten the time to market. We provide a high-confidence, closed-loop testing environment to ensure that virtual verification results meet international safety standards, helping you to minimize compliance risks and shorten the time-to-market.

Multi-sensor simulation engine

aiSim™ AIR is the core of the aiSim 5 simulation tool, enabling AI-based rendering of multi-sensor simulations. aiSim delivers high-quality virtual sensor data streams while optimizing resource usage to ensure ISO 26262 compliance with high parallelism, reduced memory footprint, balanced workloads, and asynchronous data transfers.

Large-scale generation of synthetic data

With the aiFab module, aiSim 5 takes synthetic data generation to the next level. aiFab redefines smart scene creation with features such as scene changes, detailed data statistics, and an intuitive user interface. At the same time, aiSim 5 simplifies environment and scene creation using technology based on large-scale language models, making smart scenes more accessible.

Significant improvement in accessibility and adaptability

aiSim 5 provides open APIs for sensor simulation, scene and map management, and vehicle dynamics, and is equipped with a comprehensive SDK for seamless integration into industry-standard toolchains for better interoperability. At the same time, it supports local GUI deployment and web-based cloud deployment to ensure a good user experience.

AI algorithm generates scene editing

With the addition of external rendering APIs and advanced capabilities of the simulation engine, aiSim 5 can now easily simulate mixed traffic scenes in realistic environments generated by AI algorithms like NeRF or 3D Gaussian Splatting.

Self-developed engine provides accurate environment simulation.

ADAS/AD development relies on sensor-aware environments. aiSim's self-developed real-time rendering engine can accurately simulate the relevant sensor-aware environments, create physical environments and weather effects with full certainty and repeatability, and always provide real and reliable sources of information for the simulated scenarios, thus providing a solid foundation for neural network-based multi-sensor sensing systems.

Configuration Recommendations

optimal configuration

Comprehensive Weather and Traffic Simulation Using the Widest Range of Sensor Models in Computationally Intensive Simulations

Computer Configuration

- CPU:7th Generation Inter Core i7 processors (or higher)

- Memory:32 GB

- Hard disk space:200 GB

- Showcard:NVIDIA GeForce RTX 3080Ti (or higher)

- Light tracking:For light-tracking sensor simulations (cameras, laser radar, radar)

Requires a GPU with optical tracking, such as the NVIDIA GeForce RTX 2080Ti.

  • Titan RTX
  • GeForce RTX 3000 Series
  • GeForce RTX 4000 Series
  • GeForce RTX 3000 Series
  • Quadro RTX 3000
  • Quadro RTX 4000
  • - NVIDIA RTX A5000

Supported Platforms

- Windows 10 64 bit

- Ubuntu 18.04 and 20.04

performances

- Recommend the best configuration of aiSim to realize its full potential.

Software Configuration

  • Latest GPU drivers supporting Khronos Vulkan
  • For NVIDIA cards used on Windows 10, it is recommended to install the GeForce Game Ready driver.
  • For Ubuntu systems, it is recommended to get the latest Nvidia drivers through the Graphics Drivers PPA.
  • 7-Zip
  • Python 3
  • Git Bash for Windows
  • VK_EXT_SCALAR_BLOCK_LAYOUT
  • VK_KHR_SHADER_FLOAT_CONTROLS
  • VK_EXT_DESCRIPTOR_INDEXING
  • vk_khr_spirv_1_4
  • VK_KHR_ACCELERATION_STRUCTURE
  • vk_khr_ray_tracing_pipeline
  • VK_KHR_MAINTENANCE3
  • vk_khr_pipeline_library
  • VK_KHR_DEFERRED_HOST_OPERATIONS
  • vk_khr_buffer_device_address
  • CMake 3.26 or later
  • Python 3
  • Visual Studio 2019 16.10 and 16.11 → Microsoft Visual C++ Compiler 14.29
  • Visual Studio 2022 17.2 → Microsoft Visual C++ Compiler 14.32
  • Ubuntu 20.04 → GCC 9.4.0 and Clang 10.0 (with libstdc++)
  • Ubuntu 22.04 → GCC 11.4.0 and Clang 14.0 (with libstdc++)
  • CMake 3.26 or later

Base Configuration

CPU only simulation.
and the use of object-level sensors.

  • CPU:7th Generation Inter Core i7 processors (or higher)
  • Memory:8 GB
  • Hard Disk:200 GB

The aiSim Normal configuration is an example of deploying aiSim on a lower performance device. It may affect performance when simulating complex environments such as city scenes or scenes with many light sources at night; therefore, optimal performance cannot be guaranteed.

(The NVIDIA GTX 1050Ti does not support optical tracking sensor emulation.)

Upgraded Configurations

Combined with camera sensors, using object-level simulation.
No need for more complex light tracking.

  • CPU:7th Generation Inter Core i7 processors (or higher)
  • Memory:32 GB
  • Showcard:NVIDIA GeForce GTX 1080Ti (or higher)
  • Hard disk space:200 GB

Frequently Asked Questions

Technical support and paid services to drive your project to the limit.

aiSim is the world's first product to receive ISO 26262 ASIL-D It is a certified high-fidelity simulation platform for autonomous driving. It provides a highly-confirmable simulation environment to ensure that the results of ADAS and automated driving software in virtual testing are highly consistent with the real world, fully meeting the most stringent functional safety validation standards of global automotive OEMs and Tier 1 suppliers.

aiSim pioneered the integration of 3D Gaussian Splatting (3DGS) aiSim's 3DGS solution can quickly transform the real sensor data collected into a high fidelity 3D virtual environment. Compared with traditional manual 3D modeling, aiSim's 3DGS solution can significantly shorten the construction cycle of the simulation scenario while preserving the detailed texture of the real road surface, which greatly enhances the visual fidelity of the simulation test.

Yes, aiSim uses a modular and open architecture that seamlessly integrates into the SIL (Software-in-the-Loop) up to HIL (Hardware-in-the-Loop) In the development process. It supports Sensor Injection for all major sensors, helping R&D teams to complete complex closed-loop testing at the hardware prototype stage, effectively reducing the risk of physical testing.

aiSim provides physical properties based onLens, LiDAR, Radar and UltrasoundThe high fidelity simulation of aiSim. Through advanced ray-tracing and wave propagation algorithms, aiSim is able to simulate the raw data output from the sensors under different weather conditions (rain, snow, fog) and lighting environments, which ensures the robustness of the sensing algorithms under extreme edge cases.

Absolutely. aiSim has a rich library of built-in predefined scenes, covering Euro NCAP protocols, C-NCAP, and a variety of safety test scenarios required by global regulations. Through automated batch testing capabilities, aiSim helps OEMs quickly assess whether their active safety features comply with the latest regulatory standards, thereby accelerating the vehicle's time-to-market.

Professional technical support from HONGKEI to help you succeed in your project.

HongKe offers AISIM Simulator - an advanced ADAS/AD simulation solution that supports multi-sensor simulation, environmental scene reproduction, real road conditions simulation and compliance level verification, which helps R&D teams to efficiently test system performance in controlled environments, improving development speed and overall verification quality.

 

Contact Hongke to help you solve your problems.

Let's have a chat