ADAM: The Nvidia-Powered Bartender Robot at the NHL Arena

The hospitality industry is increasingly turning to robotics to address persistent labour shortages, with deployments now extending beyond kitchen automation into customer-facing roles. 

One such example took place at the T-Mobile Arena in Las Vegas, where hockey fans attending Golden Knights matches were served drinks by ADAM, a robot bartender that’s proving automation can handle more than just repetitive tasks.

What is ADAM’s purpose?

ADAM, which stands for Automated Dual Arm Mixologist, is a practical application of edge AI computing in hospitality environments. 

Developed by Las Vegas-based Richtech Robotics using Nvidia’s Isaac libraries, the system addresses workforce challenges while creating what the company describes as distinctive customer interactions at the NHL venue.

“The hospitality industry faces significant labor challenges and ADAM is our answer to meeting those needs while elevating the customer experience,” says Matt Casella, former President of Richtech Robotics as of 2nd December this year. 

“With Nvidia’s Isaac platform, we’ve developed a solution that’s scalable, consistent and frankly, creates memorable moments for fans.”

Before ADAM poured its first drink at the arena, it spent considerable time training in a virtual bar. 

Richtech used Nvidia Isaac Sim, an open-source robotic simulation framework built on Nvidia Omniverse, to create a digital replica of ADAM’s workstation. 

The simulated environment included cups, utensils and various lighting conditions that might affect vision systems, allowing the robot to learn how to handle real-world challenges before encountering them.

How was ADAM created?

This simulation approach generated synthetic data, artificially created training information that teaches AI systems to recognise objects under different conditions. 

The method proved particularly useful for teaching ADAM to identify items even when faced with glare or reflection that could confuse camera-based vision systems.

Isaac Lab, Nvidia’s open-source robot learning framework, then refined ADAM’s operational skills including pouring and shaking beverages.

The result is a robot that doesn’t simply follow programmed instructions but adapts to its environment with precision. 

ADAM operates on Nvidia Jetson AGX Orin, an edge AI computing platform delivering 275 trillion operations per second of processing power. 

Edge AI processes data locally on devices rather than sending information to cloud servers, which reduces latency and enables faster response times.

The Nvidia technology behind ADAM’s capabilities

Using Isaac ROS 2 libraries, ADAM captures camera feeds, detects objects and calibrates its workspace in real time. 

The robot’s perception system, built with TAO Toolkit and optimised with TensorRT, enables it to identify cups, measure liquid levels and adjust movements with latency below 40 milliseconds. 

That means ADAM can spot a misplaced cup, detect when foam reaches the rim and correct a pour without missing a beat.

Beyond hospitality, Richtech has developed Dex, a mobile humanoid robot designed for factory and warehouse applications. 

Unveiled at GTC DC, Nvidia’s technology conference, Dex combines an autonomous wheeled platform with dual-arm manipulation for tasks including machine operation, parts sorting and material handling. 

The system runs on Nvidia Jetson Thor, a robotics processor designed for real-time sensor processing in industrial environments and was trained using a blend of real-world and synthetic data generated from Isaac Sim.

“The response at T-Mobile Arena has been phenomenal – people love interacting with ADAM,” Matt says.