Optimizing Mobileye’s REM™ with AWS Graviton: A focus on ML inference and Triton integration

This post is written by Chaim Rand, Principal Engineer, Pini Reisman, Software Senior Principal Engineer, and Eliyah Weinberg, Performance and Technology Innovation Engineer, at Mobileye. The Mobileye team would like to thank Sunita Nadampalli and Guy Almog from AWS for their contributions to this solution and this post.

Mobileye is driving the global evolution toward smarter, safer mobility by combining pioneering AI, extensive real-world experience, a practical vision for the advanced driving systems of today, and the autonomous mobility of tomorrow. Road Experience Management™ (REM™) is a crucial component of Mobileye’s autonomous driving ecosystem. REM™ is responsible for creating and maintaining highly accurate, crowdsourced high-definition (HD) maps of road networks worldwide. These maps are essential for:

• Precise vehicle localization
• Real-time navigation
• Identifying changes in road conditions
• Enhancing overall autonomous driving capabilities

Mobileye Road Experience Management (REM)™ (Source: https://www.mobileye.com/technology/rem/)

Map generation is a continuous process ...