Recogni Founder and CPO RK Anand on Breakthroughs in Computing Platforms for ADAS and Autonomous Driving

Auto2x spoke to RK Anand about Recogni’s computing platform that combines Peta-Op class performance and low power consumption to enable ADAS Level 2+ and Autonomy

LONDON, UK, Sept. 29, 2022 /EINPresswire.com/ — “Advances in Recogni’s computing platform could solve perception processing issues that are holding back the transition from ADAS to level autonomous driving.” 3-4,” says Auto2x, a consultancy specializing in research into self-driving technologies.

Recogni enables ADAS Level 2+ and Autonomy by leveraging its high-performance, low-power Peta-Op class visual inference system. The company was founded in 2017 and is backed by Toyota Ventures, BMW i Ventures, Faurecia, Bosch and Continental, among other investors.

Auto2x spoke with RK Anand to understand how the company is solving technology challenges in vehicle detection processing to support progress to higher levels of autonomy.

“We are a Silicon + Systems + AI company,” says RK Anand, Founder and Product Manager at Recogni. “Our vision for Recogni was to solve fundamental computational problems in vehicles for AI. Our goal was to build a computer that was an order of magnitude better than anyone else in the world.”

“Recogni has the world’s most powerful AI inference device for vision processing, the first Peta-Op (one quadrillion operations per second) class device. Our chip is at least 8X, maybe 10X, better than any other in the industry. It also has lower power consumption than leading devices in the industry. We haven’t just built the chip and software, but we have a working system that runs at better op/s at a very low 25 watts. The combination of computational performance and low power consumption allows us to achieve detection capabilities that come close to real human perception,” continues RK Anand.

Autonomous driving computing platforms that combine high-performance processing of vehicle perception data and low power consumption are one of the building blocks for the transition to higher levels of autonomy. Today, many players face challenges related to real-time processing of the large amount of data required to enable SAE Levels 3 and 4. Higher levels of autonomy require improved perception redundancy, new centralized architecture and driver-facing cameras, among others.

New software and hardware requirements will drive the demand for next-generation ADAS sensors, chips and supercomputers, artificial intelligence, HD boards, and more. They will also stimulate collaboration between OEMs and Tiers 1 and 2 for the development of AD platforms. Auto2x estimates that ADAS and automated driving revenues will nearly double between 2021 and 2025 to €35 billion due to increased sensor content. Recogni taps into the Level 2+ and Level 3 autonomous driving market with its unique solution.

Contents

1. About Recognition
• Capabilities as a “Silicon+Systems” business, across the US and Germany
• Product, adaptation to the market and customer acquisition: the main priorities today

2. Recogni product differentiation
• The Recogni advantage: high-power, low-power computing platforms
• How to unlock full autonomy: Sense (Perception) | Plan (IT) | Law
• IT was a major challenge in upgrading ADAS camera resolution and frame rate for security and longer battery life
• Industry must move from low-performance sensors that merely comply with regulations to perceptual accuracy that saves lives

3. Product positioning and adaptation to the market
• Optimized design for low power consumption provides cost savings and scalability
• OEMs falling behind on battery life could benefit from Recogni’s chips

4. Growth trajectory
• Leverage technology advantage to increase customer acquisition
• Milestones: Deployment in 2023 with trucking customers and 2024 with passenger car OEMs
• Product roadmap: next generation integration, chips and systems

5. How to overcome the challenge ahead
• Alignment with customer delivery schedules is crucial
• Strengthening the team by complementing IT experts with experienced automotive teams

To learn more about Recogni, visit recogni.com

To listen to the full interview, join Auto2xperts.

Auto2x Automotive advice and research

Auto2x is a London-based automotive consultancy specializing in advanced transport technologies for sustainable and circular mobility.

Auto2x, Automotive Intelligence & Consulting
Auto2x Ltd.
+44 7825 686532
write to us here
Visit us on social media:
LinkedIn