Simulation of Intelligent Energy Management and Autonomous Recovery for Lunar Rovers

Author

Ms. Kokila G, Abrose Begam A, Chennammal K, Durga Sri K, Bavithran R

Abstract

 Lunar rovers must survive extreme temperature swings and manage limited battery energy, because solar power disappears during the roughly fourteen-day lunar night. This paper presents a software-based academic simulation of intelligent energy management and autonomous recovery for lunar rovers. The system generates synthetic telemetry (battery level, electronics bay temperature, solar power and lunar phase) for lunar day, night and dawn, cleans the data, and uses a Decision Tree classifier to predict thermal risk as Low, Moderate, High or Critical.

A rule-based energy manager then decides the state of the camera, navigation and heater subsystems and selects an energy-saving mode, while an autonomous recovery engine checks five wake-up conditions and reports a readiness score. All modules are presented through an interactive Streamlit dashboard. The Decision Tree reached 99% accuracy on a 100-sample synthetic test set; because the risk label is derived from temperature thresholds, this reflects the synthetic labelling rule and not real-mission performance. The work is a simulation only and does not communicate with or control any real spacecraft, including Chandrayaan-3 or Pragyan.

Keywords

lunar rover, energy management, autonomous recovery, thermal risk, Decision Tree, Streamlit.

Full Text:

Download Paper PDF

References

[1] Breiman, L., Friedman, J.H., Olshen, R.A. & Stone, C.J. Classification and Regression Trees. Wadsworth International Group, 1984.
[2] Francis, R. et al. AEGIS Autonomous Targeting for ChemCam on Mars Science Laboratory: Deployment and Results of Initial Science Team Use. Science Robotics, 2(7), eaan4582, 2017.
[3] Gilmore, D.G. (ed.). Spacecraft Thermal Control Handbook, Volume I: Fundamental Technologies, 2nd ed. The Aerospace Press, 2002.
[4] Heiken, G.H., Vaniman, D.T. & French, B.M. (eds.). Lunar Sourcebook: A User's Guide to the Moon. Cambridge University Press, 1991.
[5] Hundman, K., Constantinou, V., Laporte, C., Colwell, I. & Soderstrom, T. Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding. Proc. 24th ACM SIGKDD, 387-395, 2018.
[6] Larson, W.J. & Wertz, J.R. (eds.). Space Mission Analysis and Design, 3rd ed. Microcosm Press / Kluwer Academic Publishers, 1999.
[7] Pedregosa, F. et al. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12, 2825-2830, 2011.
[8] Quinlan, J.R. Induction of Decision Trees. Machine Learning, 1(1), 81-106, 1986.
[9] Streamlit documentation. https://docs.streamlit.io

Share your valuable work from Social Media Buttons