NVIDIA and Zoox pave the way for autonomous ride-hailing

During a fireside chat at Zoox’s headquarters in Foster City, California, the trio reflected on a decade of collaboration between the two companies, highlighting their shared achievements in autonomous vehicle (AV) innovation.

Pioneering the robotaxi concept

Zoox has distinguished itself in the AV industry by developing fully autonomous, bidirectional vehicles specifically designed for ride-hailing services. This approach contrasts with the industry norm of retrofitting existing cars with self-driving technology.

“The world has never seen a robotics company like this before,” said Huang. “Zoox started out solely as a sustainable robotics company that delivers robots into the world as a fleet.”

Since its inception in 2014, Zoox has focused on creating a new class of vehicles that integrate NVIDIA GPUs to power their autonomous capabilities. Today, Zoox’s robotaxis operate on public roads, embodying a decade of technological advancements.

Supercomputers on wheels

At the heart of Zoox robotaxis are multiple NVIDIA GPUs, transforming these vehicles into supercomputers on wheels. The sensor array, including cameras, lidar, radar, long-wave infrared sensors, and microphones, generates vast amounts of data. This data is processed in real time by the onboard computing system, which fuses the raw inputs to create a comprehensive understanding of the vehicle’s surroundings.

The processed data flows through a perception engine and prediction module, informing the planning and control systems that enable the vehicle to navigate complex urban environments safely. “We’ve been using NVIDIA hardware since the very start,” Levinson noted. “It’s a huge part of our simulator, and we rely on NVIDIA GPUs in the vehicle to process everything around us in real time.”

Virtual proving ground: simulation

A key component of Zoox’s development process is its extensive use of simulation, powered by NVIDIA GPUs and software tools. These simulations test autonomous systems in virtual environments before they are deployed in the real world. By using retrofitted Toyota Highlanders equipped with the same sensors and compute packages as the robotaxis, Zoox collects driving data that is then fed back into simulation environments.

This iterative process, including ‘adversarial simulations’ designed to push the limits of the AV systems, allows Zoox to rapidly improve its software. This approach enhances the safety and performance of its autonomous vehicles, addressing potential edge cases and ensuring robustness in diverse scenarios.

Innovative design for comfort and safety

Zoox’s robotaxi features a unique bidirectional design and carriage-style seating, which optimises the vehicle for autonomous operation and passenger comfort. By eliminating the traditional concepts of a car’s ‘front’ and ‘back’, Zoox provides equal comfort and safety for all occupants. Reflecting on Zoox’s journey, Huang said: “I came to visit you when you were zero years old, and the vision was compelling. The challenge was incredible. The technology, the talent – it is all world-class.”

Market potential and future projections

The robotaxi market is poised for significant growth. Guidehouse Insights projects over 5 million robotaxi deployments by 2030, with numbers expected to reach nearly 34 million by 2035. Zoox is one of only six companies permitted to test AVs without safety drivers in California, underscoring its leadership in the field.

Slider image depicts NVIDIA founder and CEO Jensen Huang standing with Zoox CEO Aicha Evans and Zoox cofounder and CTO Jesse Levinson in front of a Zoox robotaxi.