Zenseact develops advanced safety software for autonomous vehicles, specifically designed for Volvo Cars, to enhance road safety through real-time data analysis and machine learning algorithms. The technology addresses the critical issue of traffic accidents by improving vehicle decision-making and response times in complex driving environments.
Funding
Funding not disclosed
Founders
Product
Problem
Traffic accidents, often caused by human error, result in millions of injuries and fatalities annually. Existing advanced driver-assistance systems (ADAS) have limitations in complex driving scenarios and may not provide sufficient responsiveness to prevent collisions effectively.
Solution
Zenseact develops advanced safety software for autonomous vehicles, designed to significantly reduce traffic accidents and enhance road safety. The software suite provides advanced driver assistance and self-driving capabilities by managing all aspects of automated driving, from sensor input to vehicle maneuvering. By combining rule-based programming with deep learning, Zenseact's technology enables vehicles to make safer decisions and respond more quickly in challenging driving environments. The system integrates real-time data analysis and machine learning algorithms to continuously improve its performance and adapt to various road conditions, weather, and traffic patterns. Zenseact works closely with Volvo Cars to deliver a reliable and driver-friendly solution, aiming to move faster towards a crash-free society.
Target Audience
The primary target audience includes automotive manufacturers seeking to enhance vehicle safety and introduce advanced driver-assistance systems, particularly Volvo Cars, as well as researchers and developers in the autonomous driving sector.
Features
- Comprehensive ADAS functionality including automatic emergency braking, adaptive cruise control, lane-keeping assistance, curve speed management, emergency steering support, and lane change assistance
- AI-powered perception stack for accurate and reliable environmental awareness
- Data-driven development approach leveraging real-world traffic data and AI to refine software performance
- Integration of computer vision, sensor fusion, tracking, planning, and actuation for full autonomous driving capabilities
- Utilizes deep learning models trained on NVIDIA DGX systems for efficient AI training and faster innovation
- Capability to generate synthetic datasets for training AI models, expanding the range of scenarios for improved learning
- Over-the-air (OTA) software updates for continuous improvement and feature enhancement