Mapless Autonomous Driving is developing a navigation system that utilizes real-time sensor data and machine learning algorithms to enable vehicles to operate without traditional maps. This technology addresses the limitations of GPS-dependent systems by providing reliable navigation in areas with poor satellite coverage or rapidly changing environments.
Funding
$3.5M 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
Existing autonomous vehicle systems often rely on high-definition (HD) maps, which are expensive to create and maintain, require continuous updates, and are limited to specific geographic areas. These systems also face challenges in areas with poor network coverage or rapidly changing environments, hindering their ability to navigate safely and efficiently.
Solution
Imagry provides an AI-based autonomous driving software solution that enables vehicles to navigate without HD maps, using real-time vision-based perception and imitation-learning AI. The software creates dynamic maps on-the-fly, mimicking human driving by reacting to the vehicle's immediate surroundings. This mapless approach eliminates the need for costly HD map creation and maintenance, reduces communication costs, and enhances location independence. Imagry's system is hardware agnostic, allowing OEMs and Tier-1 suppliers to integrate it with their preferred components for SAE L3/L4 autonomy in passenger cars and buses.
Target Audience
The primary target audience includes automotive OEMs, Tier-1 suppliers, and public transportation operators seeking cost-effective, scalable, and safe autonomous driving solutions for passenger vehicles and buses.
Features
- Real-time vision-based perception using multiple cameras to capture a 360° view of the environment
- Deep convolutional neural networks (DCNN) for object detection and classification, creating a dynamic map of the surroundings
- Motion planning stack trained by supervised learning techniques to mimic human driving behavior
- Distributed neural network architecture for efficient learning and adaptation to new driving scenarios
- Continuous data collection from a fleet of autonomous test vehicles operating in diverse environments
- Hardware-agnostic design, allowing integration with various cameras, computing platforms, and sensors
- Over-the-air (OTA) updates for continuous improvement and expansion of the annotated use case database
- Safe Driver OverWatch™ feature for enhanced safety, particularly for young, elderly, or distracted drivers