AI assistant may help astronauts solve emergencies in space
Future long-duration missions to Mars will inevitably present astronauts with periods of communication blackout, rendering real-time support from mission control impossible. In anticipation of this challenge, researchers at Texas A&M University are developing Daphne-AT, a virtual assistant designed to empower astronauts to independently address spacecraft anomalies, as per Phys.org.
Led by Aerospace Engineering Associate Professor Dr. Daniel Selva, the team's work, detailed in The Journal of Aerospace Information Systems, outlines Daphne-AT's sophisticated approach to onboard problem resolution. "Daphne-AT uses a mix of logic and data-driven decision-making to help astronauts make informed decisions when a problem arises on a spacecraft," Selva explained. "The VA uses spacecraft data in real time to detect anomalies, hypothesize what is causing the issue, and give astronauts information on how to solve the problem." The system continuously analyzes real-time spacecraft data, including critical environment and life support parameters like oxygen and carbon dioxide levels. Upon detecting deviations from normal operating ranges, Daphne-AT immediately alerts the crew and provides actionable guidance to resolve the issue.
The virtual assistant leverages diverse data streams to diagnose problems and presents astronauts with established operational procedures, facilitating swift and calm responses to unexpected events. Initially, laboratory testing of Daphne-AT utilized a virtual reality simulation mimicking NASA's Human Exploration Research Analog (HERA) facility. Graduate students with varying levels of aerospace knowledge participated, demonstrating that Daphne-AT significantly reduced the time taken to resolve anomalies and lowered the participants' overall mental workload. Situational awareness remained largely consistent with and without the assistance.
However, subsequent testing conducted at the actual HERA facility with experienced NASA engineers, pilots, and other professionals yielded different results. During these trials, eight crews of four participants each resided in HERA for 45 days. In this real-world environment, Daphne-AT did not significantly impact the time taken to resolve anomalies. Selva attributed this disparity partly to the participants' extensive training and experience, noting that "part of the difference is likely due to the differences in training and experience levels of participants," and "there are only so many anomalies we can present to participants, and the trained professionals had more time with the VA and more opportunities to resolve different anomalies."
Beyond space exploration, the developers envision Daphne-AT and similar virtual assistants having broad applications. Selva suggested potential benefits for professions like firefighters and emergency responders, where rapid, informed decision-making in high-stakes situations is critical. The prospect of AI-powered assistance becoming a standard tool for astronomers and other demanding professions appears increasingly likely, bringing a new era of autonomous problem-solving closer to reality. The research team includes co-author Dr. Bonnie J. Dunbar (aerospace engineering professor and NASA astronaut), Dr. Ana Diaz-Artiles (aerospace engineering associate professor), and Dr. Raymond Wong (associate professor of statistics).
The development of advanced AI tools like Dahne-AT aligns with NASA's extensive and long-standing use of artificial intelligence. AI has been crucial for decades, supporting missions, analyzing vast datasets, and developing autonomous systems for spacecraft and aircraft, according to NASA. Many of these tools use machine learning to train computers for classification, predictions, and identifying patterns in large datasets. This allows NASA to automate time-intensive processes, like project reviews, which streamlines decision-making, saves resources, and maximizes workforce potential. Innovations like Daphne-AT highlight AI's continuing evolution as a vital asset for NASA's current and future endeavors.
