14Edge AI for Connected & Automated Vehicles: Opportunities & Challenges
Alok Ranjan*, Ashutosh Bandyopadhyay and Guru Prasad A. S.
Centre of Excellence for Edge & Connectivity, Bosch Global Software Technologies, Bangalore, India
Abstract
The intersection of machine learning and embedded systems has ushered in a new era of possibilities, and at the heart of this paradigm shift lies Edge Intelligence also known as Edge AI. Edge AI has been leveraged recently across different industry verticals including industrial IoT, healthcare, smart homes, automation, and in connected products. The major motivations are to address the limitations of the current centralized artificial intelligence (AI) based solution approach such as real-time processing, lower latency requirements, network bandwidth, data privacy and cost. With the recent advancements in computing domain, vehicles are becoming increasingly connected, with software-defined features designed primarily for safety and comfort. Connected and automated vehicle (CAVs) are the key to the future intelligent transportation systems (ITS). CAVs are further complemented by the advancements in edge computing, hardware compute, big data, and AI focusing on user comfort and most critically safety. This chapter covers the background of the Edge AI in CAVs, emerging architecture, advancements, and optimization in deep learning design approach for CAV. In addition, we also present the different edge devices and tool chains for Edge AI innovation, ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access