The AI-powered medical assistant remains in the testing phase, but now the aerospace engineers aim to give it manipulator capabilities.
Google is collaborating with NASA to develop an autonomous robotic medical assistant designed to support astronauts on future deep-space missions. The initiative brings together Google’s public sector arm, NASA’s Human Research Program, Johnson Space Center’s robotics team, and the Jet Propulsion Laboratory to engineer a robot capable of assisting astronauts with medical tasks, cargo handling, and routine maintenance.
The robotics project builds upon the Crew Medical Officer Digital Assistant (CMO-DA), an AI-driven medical decision-support system that Google has been developing alongside NASA since last year. CMO-DA, powered by the open-source local AI tool RamaLama supported by Red Hat, is currently being evaluated using Earth-bound replicas of the hardware used aboard the International Space Station. Its primary function is to run AI models locally for the evaluation of medical issues—a necessity for future space missions where communication delays between Earth and astronauts in deep space would render real-time guidance nearly impossible.
“An astronaut on a future deep space mission to Mars could face severe operational challenges, including round-trip communication latencies of up to 44 minutes, making real-time medical guidance for crew nearly impossible,” Kelly explained in a recent blog post.
Google and NASA envision the robot as an auxiliary member of the crew medical team, providing hands-on assistance when human bedside care is insufficient. “To maximize its utility for a lean crew, the robotic system is designed as a versatile ‘payload’ handler capable of managing cargo, logistics, and equipment,” Kelly stated. When not needed for routine tasks like organizing tools or securing compartments, the robot can pivot to medical support.
For instance, if an astronaut experiences severe back pain potentially caused by kidney stones, the robot could fetch and prep an ultrasound machine, leaving the crew medical officer to interpret the scan and determine the appropriate treatment.
The ultimate goal is to build a robotic system capable of executing a variety of tasks via simple voice instructions, directly under the supervision and command of the astronaut. For example, the robot might be directed to assist with routine health monitoring—such as capturing basic vitals or performing simple ultrasounds—strictly under the guidance of a human crew medical officer. In essence, it is not a fully autonomous digital medical officer, but rather an additional set of hands for an overworked human doctor.
While the project has not yet progressed significantly, Google outlines several technologies under exploration, including JPL’s work adapting satellite situational-awareness tools originally used to track objects in orbit to help the robot navigate three-dimensional spaces. Currently, the project remains at the proof-of-concept stage, having conducted early laboratory demonstrations. The initial test involved the robot locating and moving a medical bag, achieving an 85 percent success rate in early lab tests. However, Google has yet to confirm whether a fully integrated, space-ready robot exists.
Regarding the project’s status, Google refers readers to NASA for specific details, but the space agency declined to provide specifics. NASA confirmed that it is working on various AI projects for its many missions and is assessing them with partners for future applications.