NVIDIA and Zoox have achieved a significant milestone in autonomous vehicle (AV) innovation by marking a decade of collaboration. This partnership has been instrumental in propelling advancements in ride-hailing technology. According to the NVIDIA Blog, NVIDIA CEO Jensen Huang recently engaged in a discussion with Zoox CEO Aicha Evans and Zoox co-founder and CTO Jesse Levinson to showcase their latest achievements.

Decade of Innovation

During a fireside chat at Zoox’s headquarters in Foster City, California, the trio reflected on the companies’ ten-year partnership. Zoox has been a pioneer in developing robotaxis specifically for ride-hailing, utilizing NVIDIA’s technology to create groundbreaking innovations. “The world has never seen a robotics company like this before,” remarked Huang. “Zoox started out solely as a sustainable robotics company that delivers robots into the world as a fleet.”

Since its establishment in 2014, Zoox has dedicated efforts to creating fully autonomous, bidirectional vehicles tailored for ride-hailing services. This distinctive approach sets Zoox apart from competitors who retrofit existing cars with self-driving technology. Presently, Zoox operates its robotaxi, powered by NVIDIA GPUs, on public roads.

Computing at the Core

Zoox robotaxis can be likened to supercomputers on wheels, built on multiple NVIDIA GPUs that process vast amounts of data in real-time. Equipped with a comprehensive sensor array, including cameras, lidar, radar, long-wave infrared sensors, and microphones, the vehicles process raw sensor data swiftly to gain a coherent understanding of their surroundings.

From a perception engine to prediction module and planning and control systems, the data undergoes various stages of processing, enabling the vehicle to navigate intricate urban environments safely. NVIDIA GPUs deliver the substantial computing power necessary for autonomous capabilities and continual learning from new experiences.

Simulation as a Virtual Proving Ground

An essential component of Zoox’s AV development process is its extensive use of simulation. Employing NVIDIA GPUs and software tools, the company conducts a wide array of simulations to test its autonomous systems in virtual environments before real-world deployment. These simulations range from synthetic scenarios to real-world situation replays using data collected from test vehicles.

Zoox also engages in “adversarial simulations,” crafted scenarios designed to challenge the limits of autonomous systems and unveil potential edge cases. This comprehensive approach enables Zoox to iterate rapidly and enhance its autonomous driving software, thereby improving AV safety and performance.

A Neat Way to Seat

Zoox’s robotaxi features a unique bidirectional design and carriage-style seating, optimized for autonomous operation and passenger comfort. This innovative design eliminates traditional concepts of a car’s “front” and “back,” ensuring equal comfort and safety for all occupants. With NVIDIA GPUs and tools, Zoox aims to redefine urban mobility, leading the way towards safe, efficient, and sustainable autonomous transportation.

From Testing Miles to Market Projections

As the AV industry gains momentum, projections indicate explosive growth in the robotaxi market. Guidehouse Insights forecasts over 5 million robotaxi deployments by 2030, with numbers projected to reach nearly 34 million by 2035. The regulatory landscape mirrors this progress, with 38 companies currently holding valid permits to test AVs with safety drivers in California. Zoox stands as one of the six companies permitted to test AVs without safety drivers in the state.

As the industry continues to evolve, Zoox has developed a next-generation robotaxi that combines cutting-edge onboard computing with extensive simulation and development efforts.

In the accompanying image, NVIDIA founder and CEO Jensen Huang is pictured alongside Zoox CEO Aicha Evans and Zoox co-founder and CTO Jesse Levinson in front of a Zoox robotaxi.

Image source: Shutterstock