Sustainable and Attainable: Zoox Unveils Autonomous Robotaxi Powered by NVIDIA

When it comes to future mobility, you may not have to pave as many paradises for personal car parking lots.

This week, autonomous mobility company Zoox unveiled its much-anticipated purpose-built robotaxi. Designed for everyday urban mobility, the vehicle is powered by NVIDIA and is one of the first level 5 robotaxis featuring bi-directional capabilities, providing a concrete view into the next generation of intelligent transportation.

Zoox and NVIDIA first announced their partnership in 2017, with the innovative startup leveraging the high-performance, energy-efficient compute of NVIDIA to build a level 5 vehicle from the ground up. It was a significant milestone toward an autonomous future. Zoox is also an alumnus of NVIDIA Inception, our accelerator program for startups transforming industries with AI and data science.

Robotaxis are set to transform the way we move. Experts at UBS estimate these vehicles could create a $2 trillion market globally by 2030, while reducing the cost of daily travel for riders by more than 80 percent. With greater affordability, robotaxis are expected to decrease car ownership in urban areas — a recent survey of 6,500 U.S. drivers showed nearly half would be willing to give up car ownership if robotaxis became widespread.

With Zoox and the openness and scalability of NVIDIA AI technology, this vision of safer and more efficient mobility is no longer a faraway future, but a close reality.

Autonomy Forwards and Backwards

Unlike current passenger vehicles that focus on the driver, Zoox is designed for riders. The vehicle was built from the start to optimize features necessary for autonomous, electric mobility, such as sensor placement and large batteries.

Each vehicle features four-wheel steering, allowing it to pull into tight curb spaces without parallel parking. This capability makes it easy for Zoox to pick up and drop off riders, quickly getting to the curb and out of the flow of traffic to provide a better and safer experience.

The vehicle is bidirectional, so there is no fixed front or back end. It can pull forward into a driveway and forward out onto the road without reversing. In the case of an unexpected road closure, the vehicle can simply flip directions or use four-wheel steering to turn around. No reversing required.

Inside the vehicle, carriage seating facilitates clear visibility of the vehicle’s surroundings as well as socializing. Each seat has the same amount of space and delivers the same experience — there’s no bad seat in the house. Carriage seating also makes room for a wider aisle, allowing passengers to easily pass by each other without getting up or contorting into awkward positions.

All together, these design details give riders the freedom of seamless mobility, backed by safety innovations not featured in conventional cars.

One Solution

NVIDIA provides the only end-to-end platform for developing software-defined vehicles with a centralized architecture, spanning from the data center to the vehicle.

For robotaxis, achieving level 5 autonomy requires compute with enough headroom to continuously add new features and capabilities. NVIDIA enables this level of performance, starting with the infrastructure for training and validation and extending to in-vehicle compute.

These vehicles can be continuously updated over the air with deep neural networks that are developed and improved in the data center.

The open and modular nature of the NVIDIA platform enables robotaxi companies to create custom configurations to accommodate new designs, such as Zoox’s symmetrical layout, with cameras, radar and lidar that achieve a 270-degree field of view on all four corners of the vehicle.

With the ability to use as many processors as needed to analyze data from the dozens of onboard sensors, developers can ensure safety through diversity and redundancy of systems and algorithms.

By leveraging NVIDIA, Zoox is using the only proven, high-performance solution for robotaxis, putting the vision of on-demand autonomous mobility within reach.