AI-Enabled Capabilities to Facilitate Next-Generation Rover Surface Operations

Contemporary Mars rovers such as Curiosity and Perseverance operate at average speeds on the order of 4.2 cm/s, with daily traverses typically below 100 m [1]. These constraints stem from conservative operational approaches necessitated by communication delays, irreplaceable hardware, and limited onboard processing capabilities. The traditional Sense-Model-Plan-Act (SMPA) paradigm requires frequent stops for terrain analysis, preventing continuous motion and severely limiting mission scope and scientific return. Missions requiring long-range access to diverse geological targets (sample-return campaigns) are particularly affected by these mobility constraints [2]. Recent advances in computer vision (CV) algorithms, compact ML models, and space-qualified computing platforms offer a practical path to maintaining safety while increasing autonomy and traverse speeds. In this work, we present a set of AI-enabled systems developed under ESA contracts RAPID, FASTNAV, ViBEKO and AIAXR, and CISRU. These systems were validated in Mars-and Lunar-analogue field trials and demonstrate substantial improvements in mobility and perception accuracy. The contributions presented in this work are: (1) a far-obstacle detection component which facilitates continuous motion at speeds in excess of 1.0 m/s; (2) a coordination framework enabling multi-robot human-robot workflows for resource extraction and handling; and (3) a suite of terrain classification models for operations.