Coco Robotics Launches Next-Gen Autonomous Robots for Urban Deliveries

Trained on millions of city miles, Coco 2 robots expand urban logistics for cities – scaling autonomous delivery through sidewalks, bike lanes and roads where permitted.

Coco Robotics, the world’s leading urban robotics platform, launched Coco 2, its next-generation autonomous delivery robots. This is a major milestone in the company’s evolution into a physical AI leader as Coco 2 represents the shift from human-guided robotics to full autonomy.

Coco’s new robots adapt more quickly to new cities, navigate complex urban environments with greater precision, and continuously improve through millions of real-world data points. Extending even further into urban logistics, Coco 2 is designed as a general-purpose urban robotics platform, enabling city-wide movement of goods for all types of businesses from restaurants and grocers to pharmacies and local retailers, expanding far beyond traditional sidewalk food deliveries.

Coco 2’s capabilities are powered by the industry’s largest dataset of sidewalk robot operations, built from millions of miles navigating complex urban environments – including flooded streets in Miami, heavy snow and freezing temperatures in Chicago, and dense traffic in Los Angeles – conditions that can disrupt urban logistics. This operational data continuously strengthens the fleet’s AI, enabling safe and efficient deployment in new cities.

“Every mile our robots have driven has made the whole fleet smarter,” said Zach Rash, CEO and Co-Founder of Coco Robotics. “Human-in-the-loop learnings have helped us improve with every edge case, creating a feedback loop between deployment, data collection, and model advancements. This ongoing process has steadily enhanced our fleet’s intelligence, enabling Coco to operate in new cities with real-time adaptability.”

Also Read: AiThority Interview With Arun Subramaniyan, Founder & CEO, Articul8 AI

From Sidewalks to Citywide Autonomy

While Coco began with sidewalk-first delivery, Coco 2 expands into bike lanes and roads where permitted, reducing delivery times by up to 50 percent compared to the prior generation. With up to three times longer uptime and improved resilience to weather and wear, Coco 2 also increases daily order capacity while lowering cost per mile.

Coco 2 builds upon Coco’s Urban Robotic Platform to lower the cost per mile and increase the range and reliability of delivery – making instant delivery affordable at scale for any business, on any delivery platform, and across a wide range of basket sizes.

Today, Coco powers autonomous delivery through Uber Eats, DoorDash, and Wolt, and serves more than 3,000 merchants and restaurants – from local favorites to national brands – demonstrating growing demand. Building on that momentum, Coco is on track to scale its fleet to thousands of robots globally by the end of the year.

Under the Hood: The Intelligence Behind Coco 2

By leveraging NVIDIA Omniverse libraries, open robotics simulation and learning frameworks Isaac Sim and Isaac Lab along with NVIDIA Cosmos world foundation models – Coco creates physically accurate simulations and synthetic data, or computer-generated scenarios that mimic real streets, pedestrians, vehicles, and obstacles. This allows Coco’s AI to safely practice navigating complex city streets and edge cases before ever leaving the warehouse.

Coco 2 robots run on NVIDIA Jetson Orin NX, a robotic computing platform that processes data much faster and more efficiently directly on the robot, without relying on cloud connections. This combination of NVIDIA accelerated computing and software creates a fully integrated driving system that lets Coco 2 see and understand its surroundings, anticipate movement, plan routes, and execute maneuvers smoothly and safely.

“The era of physical AI has arrived, and scaling it requires a seamless loop between massive real-world data and high-performance edge computing,” said Amit Goel, head of strategic partnerships at NVIDIA. “By leveraging NVIDIA’s full robotics stack, Coco is accelerating the deployment of autonomous systems that can safely navigate the complexities of our cities at scale.”

As a result, Coco can now expand quickly into new cities, bringing modern, autonomous urban delivery to more neighborhoods and businesses.