Chef Robotics Advances Bi-Manual Physical AI System for Prep Table Food Assembly Powered by a Food Foundation Model

SAN FRANCISCO--(BUSINESS WIRE)--May 18, 2026--

Chef Robotics, a leader in physical AI for the food industry, today announced the development of a bi-manual physical AI system for prep table food assembly. While today’s Chef robots handle high-volume meal assembly on food manufacturing conveyor lines, this new bi-manual physical AI system will focus on lower-volume, higher-complexity prep-table-based assembly for industries such as ghost kitchens, fast-casual restaurants, airline catering, schools, hospitals, military, prisons, stadiums, corporate dining, and hotels.

This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20260518262468/en/

With the advent of physical AI and imitation learning, Chef’s AI team is developing a new physical AI system designed to handle meal assembly tasks on prep tables, such as back-of-house burger or burrito assembly. These tasks are lower-volume but higher-complexity than food manufacturing on conveyor lines because a single worker (or robot) must assemble the entire meal, rather than breaking the process down into separate workstations for each ingredient.

To perform higher-complexity tasks, the new system will use two robotic arms, enabling bi-manual control. It will be able to perform coordinated, dexterous manipulation comparable to that of human arms and hands. The system’s end effectors will be flexible enough to pick up different food ingredients and utensils.

Powered by Chef’s Food Foundation Model (FFM)

The new physical AI system will be powered by Chef’s Food Foundation Model (FFM), which learns faster and adapts to a wider range of use cases than traditional robotic systems.

Off-the-shelf vision-language-action models (VLAs) and physical AI models aren’t sufficient for food manipulation. Most VLAs and physical AI models are trained on rigid-body manipulation, but food manipulation involves highly variable, deformable materials (e.g., wet, sticky, irregular items). This requires Chef’s AI models to generalize across a broad range of physical states and interactions.

Instead of requiring separate models for tasks such as picking and placing food, detecting trays, compartments, and inserts, and handling scoopable or discrete ingredients, the FFM supports all of these capabilities through a single “foundational” AI model. It can also be extended to new tasks more efficiently and with improved performance.

Rather than being programmed, the FFM learns from demonstration (imitation learning) to perform specific tasks like assembling a burger or building a burrito bowl. It also generalizes across different robotic hardware platforms by learning task representations that transfer across hardware embodiments (e.g., systems with different kinematics, end effectors, and configurations). In that sense, Chef is building the physical AI layer for food.

The FFM is expected to unlock additional capabilities over time. For example, it may support zero-shot or few-shot ingredient onboarding, adapting to new ingredients with minimal training. The model will also self-improve and autonomously increase yield and consistency over time.

Other benefits

Chef’s new physical AI system will be:

“We started Chef by focusing on high-throughput food manufacturing, but a large part of the industry still relies on manual prep table assembly,” said Rajat Bhageria, Founder and CEO of Chef Robotics. “These environments are more complex and less structured, which makes them harder to automate. With this new physical AI system and our Food Foundation Model, we will extend physical AI to handle those real-world conditions and unlock a much broader set of applications in the food industry.”

About Chef Robotics

Chef is the first company to have commercialized a scalable AI-driven food robotics solution. With over 100 million servings made in production, Chef leverages ChefOS, an AI platform for food manipulation, to offer a Robotics-as-a-Service solution that helps industry-leading food companies increase production volume and meet demand. Headquartered in San Francisco, CA, Chef aims to empower humans to do what humans do best by accelerating the advent of intelligent machines. Visit https://chefrobotics.ai to learn more.

Chef's bi-manual physical AI system for prep table food assembly

The U.S. would join a very short list of nations that carry out capital punishment in public if it goes forward with plans to live-stream a military execution this year.

Only two countries carried out the death penalty in public last year, according to Amnesty International's tracking of 2,700 executions in 17 countries.

Iran executed 11 people publicly and Afghanistan killed six, the human rights organization said.

The Pentagon announced Thursday that it would live stream the Dec. 3 execution by firing squad of Fort Hood shooter Nidal Malik Hasan at Fort Hood, Texas, the first military execution in more than 65 years.

Hasan was convicted of killing 13 people and injuring 32 others in a shooting at the Texas military base in 2009.

The U.S. has not publicly executed anyone since the 1930s as capital punishment has moved from the town square to places out of public view, typically in prison death chambers.

Over time, execution methods also have changed from hangings and an occasional firing squad to the electric chair, gas chamber and lethal injection.

U.S. President Donald Trump, who has previously been critical of public executions in Iran, approved Hasan's firing squad death, a Pentagon spokesman said Monday.

If Hasan's execution goes ahead publicly as planned, the U.S. would be in rare company with one country it is currently at war with — Iran — and another enemy it fought for years in Afghanistan — the Taliban.

In the last four years, the only public killings documented by Amnesty were in Iran and Afghanistan.

But Amnesty only reports on judicial executions and does not have numbers for China, North Korea and Vietnam, where executions are believed to be carried out. It has noted that it has received reports of public executions in North Korea that it couldn't verify.

In 2021, at least nine people were publicly executed in Yemen, Amnesty said.

Saudi Arabia also conducted public executions in the past, but not in recent years.

Iran led the report with the most executions — 2,159 — though few took place in public settings, which usually are reserved for political prisoners. They are typically carried out in public squares, where the convicted are hanged from cranes mounted on trucks.

In July, two men convicted of killing four police officers during nationwide anti-government protests in January were hanged at dawn in Alikhani Square, in the central city of Isfahan, state media reported.

Human rights organizations have condemned the resumption of public executions in Afghanistan after the Taliban-led government seized power in 2021 in the wake of the chaotic withdrawal of U.S. and NATO forces.

In the late 1990s during their previous rule, the Taliban regularly carried out public executions, floggings and stonings.

In December, tens of thousands of people gathered in a stadium in the eastern city of Khost to see a man convicted of killing 13 members of a family, including several children, be shot to death. It was the 11th execution carried out since the Taliban's return to power.

The victims’ kin were offered the choice of forgiving the man and sparing his life or having him shot, the Supreme Court said.

They chose the death penalty and one of their relatives pulled the trigger.

FILE - A crowd leaves a stadium after attending the public execution, carried out by Taliban authorities, of a man sentenced by the Supreme Court for killing 13 members of a family, including children, earlier this year, in the eastern city of Khost, Afghanistan, Dec. 2, 2025. (AP Photo/Saifullah Zahir, File)

FILE - A Taliban policeman, center, and two other men walk past a poster stating that cameras, phones, and weapons are banned inside a stadium where a public execution was taking place in the city of Khost, eastern Afghanistan, Dec. 2, 2025. (AP Photo/Saifullah Zahir, File)