Improving resilience of sensors in planetary exploration using data-driven models

Improving the resilience of sensor systems in space exploration is a key objective since the environmental conditions to which they are exposed are very harsh. For example, it is known that the presence of flying debris and Dust Devils on the Martian surface can partially damage sensors present in rovers/landers. The objective of this work is to show how data-driven methods can improve sensor resilience, particularly in the case of complex sensors, with multiple intermediate variables, feeding an inverse algorithm (IA) based on calibration data. The method considers three phases: an initial phase in which the sensor is calibrated in the laboratory and an IA is designed; a second phase, in which the sensor is placed at its intended location and sensor data is used to train data-driven model; and a third phase, once the model has been trained and partial damage is detected, in which the data-driven algorithm is reducing errors. The proposed method is tested with the intermediate data of the wind sensor of the TWINS instrument (NASA InSight mission), consisting of two booms placed on the deck of the lander, and three boards per boom. Wind speed and angle are recovered from the intermediate variables provided by the sensor and predicted by the proposed method. A comparative analysis of various data-driven methods including machine learning and deep learning (DL) methods is carried out for the proposed research. It is shown that even a simple method such as k-nearest neighbor is capable of successfully recovering missing data of a board compared to complex DL models. Depending on the selected missing board, errors are reduced by a factor between 2.43 and 4.78, for horizontal velocity; and by a factor between 1.74 and 4.71, for angle, compared with the situation of using only the two remaining boards.

Automated summary

This study aims to demonstrate how data-driven methods can improve the resilience of sensors, particularly for complex sensors with multiple intermediate variables, by using calibration data to train an inverse algorithm (IA). The method consists of three phases: initial calibration and IA design, placing the sensor at the intended location and training a data-driven model using sensor data, and reducing errors using the data-driven algorithm when partial damage is detected. The proposed method is tested with the intermediate data of the wind sensor of the TWINS instrument (NASA InSight mission), and it is shown that even simple methods like k-nearest neighbor can successfully recover missing data compared to complex deep learning models.