Uncategorized
THE EXPLOSION OF THE ADAS AND AV VALIDATION PROBLEM
Advanced Driver Assistance Systems (ADAS) and Autonomous Vehicles (AVs) require exhaustive validation prior to production release to ensure the safety of each new vehicle. Validation teams are required to drive millions of actual road-miles while recording the data from on-board cameras and sensors to determine if the systems behave as designed under real-world conditions. This process generates a massive amount of data (petabytes) which must be annotated and analyzed to understand system performance and identify areas for improvement. With increasing levels of driver assistance in each model-year, this problem is becoming untenable and a major source of project delays, cost overruns and potential warranty and legal liability.
THE OTTOMETRIC SOLUTION
The Ottometric platform automatically reviews thousands of hours of raw endurance test and training data, distilling it based on the KPIs for each particular system. Employing proprietary AI and mathematical models, Ottometric’s technology analyzes sensor and system data to validate correct operation of ADAS/AV systems. It also generates a prioritized list of scenarios that warrant manual review, thereby guiding engineers to the “needles in the haystack”. This speeds up required certifications and greatly improves identification of long-tail issues, which can otherwise be missed.
Below are common use cases in ADAS + AV system validation and training that can be automated by the Ottometric solution. Click on any use case to get further information:
Ottometric Product Brief
Get the Ottometric Product Brief to learn more about how Ottometric accelerates ADAS Validation and AV Training, further helping OEMs, their Tier 1 + Tier 2 suppliers and emerging autonomous vehicle designers deliver safe systems.
Ottometric White Paper
AI training is essential for ADAS and AV, ensuring systems handle diverse road scenarios, including edge cases. The labor-intensive labeling process requires detailed object identification and precise location mapping. To reduce costs and training times, this paper explores traditional data reduction methods and highlights Ottometric’s Scenario Prioritization Ranking (SPR), which achieves high-quality results with only 1% of the full training dataset.
PARTNERS
Ottometric strategic partners enhance the Ottometric solution by streamlining the data collection and
processing pipeline, and providing secure storage and access to test data and validation results.
Ottometric leverages AWS cloud services to securely process data collected from test vehicles used for
ADAS development and validation. We screen all data sent to AWS for quality and completeness to help reduce storage costs and ensure the data can be properly processed. The Ottometric platform takes advantage of automated scale up and scale down of EC2 compute instances as needed, ensuring rapid turnaround, and helping ADAS development and validation programs complete on time.
Ottometric works with the IBM Partner Plus program, specifically with storage systems that are used during data collection for ADAS and AV development and validation. IBM provides an optimized pipeline for Cloud, Hybrid and on-premise that can ensure data is available to the Ottometric platform in the Cloud.
As a partner with the BlackBerry IVY Connected Vehicle Data Platform, Ottometric works with automotive Tier-1s and OEMs to collect data from production vehicles to be processed by the Ottometric platform.
ABOUT US
FInd out more about the Ottometric Team, Investors and Advisors.
CAREERS
Ottometric continues to grow our team, if you are interested in our careers on offer,
please visit our Careers Page.
For general, product, sales and media inquires,
reach out to the Ottometric team at info@ottometric.com
