The startup develops a platform that provides simulation technologies for autonomous systems, focusing on scenario factories and sensor data repositories. Their tools facilitate the design, data annotation, and testing of deep learning models, enhancing scene perception across various sensor inputs in the automotive industry.
Funding
$360K raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Developing and validating autonomous systems, particularly for the automotive industry, requires extensive testing across a wide range of scenarios and sensor configurations. Generating realistic and diverse datasets for training and testing perception and decision-making algorithms is a significant challenge. Existing methods often lack the scalability and accuracy needed to ensure the safety and reliability of autonomous vehicles.
Solution
SimDaaS Autonomy provides a simulation platform that enables end-to-end autonomous system design, development, and validation through synthetic data generation. The platform offers a scenario factory for generating customized scenarios, a scenario library with diverse conditions including edge cases, and a sensor data repository with data in standard formats for training deep learning models. SimDaaS facilitates the integration of perception and decision engines with the simulation system, allowing users to evaluate performance across various scenarios and sensor combinations. The technology leverages both learning-based and physics-based methods to create accurate and scalable synthetic data.
Target Audience
The primary target audience includes automotive OEMs, ADAS developers, autonomous vehicle manufacturers, and researchers focused on developing and validating autonomous systems.
Features
- SaaS platform for training and testing perception and decision engines
- Scenario Factory for generating custom scenarios with user-defined inputs and recommendations
- Scenario Library offering a variety of scenarios for different terrains, weather conditions, and edge cases, including specific scenarios for Indian conditions
- Sensor Data Repository providing LiDAR, camera, and other sensor data in standard formats
- Automated data annotation pipeline for generating precisely annotated data with support for custom labels
- Traffic Manager module to simulate realistic traffic conditions with dynamic adaptability, smart collision avoidance, and advanced lane change capabilities
- Support for OpenDrive format road networks and configurable left-hand drive (LHD) or right-hand drive (RHD) systems
- Ability to simulate different weather conditions and times of day