AutoNav, the autonomous navigation capability for Mars rovers, will play an essential role in achieving the goals of the Mars 2020 Rover and potential future Sample Retrieval and Launch (SRL) missions. While the line-of-site “blind drivable” distance was limited to ~60 m/sol on average for Curiosity, future rovers are expected to achieve 150-200 m/sol on average in order to visit geographically dispersed regions of interest (ROIs), and to complete sample collection. Furthermore, since MAVEN and ESA’s TGO are not in a Sun-synchronous orbit, after the end of life of MRO, the bandwidth available for rovers will become irregular, meaning that multi-sol driving would be required more frequently. With all of these considerations, it is likely that Mars 2020 and the notional SRL mission would have to constantly drive ~100m/sol beyond the line of sight using AutoNav without compromising safety.
The objective of the task is to develop on-board capabilities that would enable rovers to traverse difficult terrains autonomously, efficiently, and safely. The proposed capability consists of two technologies: vision-based terrain classifier and risk-aware path planner. Combining the two technology would enable human-like reasoning on risk, such as avoiding >30 deg sandy slope or pointy rocks on a hard terrain, hence allowing rovers to safely traverse difficult terrains where the current Autonav cannot. We will deploy the algorithms on test rovers (Athena and ATRV Jr.) and perform experiments in the Mars Yard.