Artificio develops self-driving technology using crowdsourced OOD data collected from taxi drivers for robust model training. The company leverages OpenSource Vision-Language-Action (VLA) models to fine-tune driving algorithms efficiently and at reduced costs. Their goal is to deploy autonomous vehicle capabilities globally across various cities.
Funding
$200K 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
Autonomous driving systems lack diverse, real-world training and testing data, particularly from challenging and unpredictable environments in emerging economies. This absence of out-of-distribution data hinders the development of robust self-driving technologies capable of navigating chaotic and informal driving conditions.
Solution
Artificio provides Robusto, a crowd-sourced benchmarking platform that offers open-source data collected from challenging environments in emerging economies. This platform enables logistics and transportation companies to evaluate and improve the performance of their autonomous driving systems in unpredictable, real-world conditions. By providing free access to these benchmarks, Artificio addresses the critical need for diverse training and testing data, allowing for the development of more reliable self-driving technologies. The platform focuses on data from regions where driving rules are less formal and routes are more chaotic, offering unique insights into system performance in demanding scenarios.
Target Audience
The primary users are logistics and transportation companies developing autonomous driving systems, as well as researchers in robotics, artificial intelligence, and computer vision.
Features
- Crowd-sourced data collection from drivers in emerging economies.
- Open-source benchmarks available for free use.
- Focus on out-of-distribution data prevalent in challenging driving environments.
- Platform allows users to identify gaps in their autonomous driving systems' performance.