Competency-Aware Collaborative Robotic Surface Exploration: A Study at the Mars Desert Research Station

Future concepts for space exploration envision astronauts relying on autonomous robots to accomplish a variety of tasks, including planetary surface exploration, science, and mining operations. An astronaut’s understanding of the robots’ competencies will be crucial to informed, risk-aware decision-making during both mission planning and mission execution. A key challenge is to develop methods to calibrate future astronauts (or more generally, users of autonomous robots in safety-critical operations) to the capabilities and limitations of these machines. In the spring of 2024, we partnered with the Mars Society’s Mars Desert Research Station (MDRS) Crew #297 to conduct a two-week exploratory field deployment and limited user study evaluating an autonomous ground robot with a competency-awareness capability—autonomy algorithms capable of quantifying and communicating estimates of the robot’s ability to meet mission objectives. During the analog Mars expedition, the crew utilized a robot to explore areas and gather data during extravehicular activities (EVAs). They overcame several technical challenges and were able to safely and efficiently leverage the robot for their mission needs. The competency information reported by the robot served as a valuable component of the crew’s planning and decision-making process, with 50% of the crew indicating that they directly relied on the assessments while planning tasks for the robot. We believe that integrating competency assessment capabilities into robotic autonomy can enable future astronauts to better manage risk and make more informed decisions while tasking and supervising autonomous robots.