The startup develops driver assistance technology that utilizes an optical sensor suite and computer vision with deep learning for object motion prediction. This platform enhances self-driving car systems, improving vehicle responsiveness and creating a more intuitive driving experience.
Funding
$85.8M 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.
ICFounders
Product
Problem
Current Advanced Driver Assistance Systems (ADAS) often lack the flexibility and scalability required by Tier 1 suppliers and OEMs, leading to increased development costs and longer time to market. Existing solutions may also struggle with computational efficiency and accuracy in complex driving scenarios.
Solution
Phantom AI offers a modular, software-based autonomous vehicle stack that provides Tier 1 suppliers and OEMs with unparalleled customization and configuration options. The platform incorporates computer vision, sensor fusion, and control capabilities to deliver a comprehensive ADAS solution. Phantom AI's technology is designed for scalability and high precision, while maintaining better computational efficiency compared to existing solutions. The software supports a suite of Euro NCAP-compliant ADAS features, including vehicle, pedestrian, bicyclist, free-space, traffic sign, and traffic light detection.
Target Audience
The primary customers are Tier 1 automotive manufacturers and OEMs focused on delivering Level 2/3 ADAS solutions and, in the future, full autonomy.
Features
- PhantomVision™: Deep learning-based computer vision solution for comprehensive object detection and traffic direction recognition, supporting single or multiple cameras with a 360-degree view.
- PhantomFusion™: Platform-independent sensor fusion and object tracking system that integrates data from camera, radar, LiDAR, and ultrasonic sensors to create a thorough environmental model.
- PhantomDrive™: Vehicle control solution that predicts object motion to enable safe and natural vehicle movement, adaptable to various levels of automation and sensor configurations.
- Camera Gain Control: Optimized image capture for varying lighting conditions, including daytime, nighttime, tunnels, and direct sunlight.
- Optimal Data & Data Augmentation: Utilizes diverse datasets and novel augmentation techniques to enhance deep learning model performance in corner-case scenarios.
- Real-time processing of multiple cameras using state-of-the-art deep learning models and code optimization techniques.