Ottometric provides an AI-driven software platform that automates the validation and training of Advanced Driver Assistance Systems (ADAS) and Autonomous Vehicles (AVs) by analyzing vast amounts of sensor data to ensure system performance and safety. This solution reduces development costs and accelerates time to market by efficiently identifying critical scenarios for manual review, addressing the challenges of data management and real-world validation in the automotive industry.
Funding
$5.7M 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
Validating Advanced Driver Assistance Systems (ADAS) and Autonomous Vehicles (AVs) requires extensive road testing, generating massive volumes of sensor data that must be analyzed to ensure system safety and performance. Traditional validation methods involve manual annotation and analysis of this data, which is costly, time-consuming, and prone to errors. Identifying critical scenarios and edge cases within these vast datasets presents a significant challenge, potentially leading to project delays and increased liability.
Solution
Ottometric offers an AI-powered software platform that automates the validation and training of ADAS and AV systems by streamlining the analysis of sensor data. The platform employs proprietary AI and mathematical models to validate the correct operation of ADAS/AV systems and identify critical scenarios that require manual review. By automatically computing a synthetic ground truth through the fusion of LiDAR, camera, and other sensor data, Ottometric enables automated calculation of KPIs for both sensor and system performance. This approach reduces the need for manual annotation, accelerates data analysis, and improves the identification of long-tail issues, ultimately reducing development costs and accelerating time to market.
Target Audience
Ottometric's primary customers include OEMs, Tier 1 and Tier 2 automotive suppliers, and emerging autonomous vehicle designers involved in the development and validation of ADAS and AV systems.
Features
- Automated data screening to provide feedback on data quality, conformance and uniqueness.
- AI-driven data curation to create diverse training datasets, reducing data volume by up to 100x.
- Synthetic ground truth generation by fusing LiDAR, camera, and other sensor data.
- Automated calculation of sensor KPIs, detecting true/false positives and negatives.
- Automated calculation of system KPIs for ADAS functions like Lane Departure Warning (LDW) and Automatic Emergency Braking (AEB).
- Data classification and meta-tagging for environmental conditions to facilitate easy searching.
- Scenario Prioritization Ranking (SPR) technology to "fingerprint" failure conditions and identify similar drive segments.
- Ottoviz data visualizer for detailed examination of failures.