Back To Projects

Adapting Martian Rover Technology for Terrestrial Disaster Response and Extreme Terrains

Humayl F.

This research examines how technological advances in Martian rovers, from autonomous navigation to adaptive suspension systems, can inform solutions for disaster response and operation in inaccessible regions on Earth. A 3D-printed rover prototype and global disaster data were used to evaluate the potential of ground-based rovers to complement aerial systems in challenging environments.


Rovers have transformed planetary exploration by enabling autonomous, intelligent operation on alien terrains. From the Soviet Lunokhod 1 to NASA’s Perseverance, rover technology has evolved to include advanced mobility systems, AI-driven navigation, autonomous decision-making, and onboard scientific instruments. This paper examines how these innovations, originally developed for Mars, can be adapted to solve real-world challenges on Earth, particularly in disaster-prone and inaccessible regions. We designed and 3D-printed a rover prototype, informed by Martian mobility principles, and analyzed its potential for navigating extreme terrain. Using global disaster datasets and a review of current aerial and terrestrial solutions, we evaluated rover applicability to scenarios such as floods, landslides, wildfires, and harsh geographical regions. Our results indicate that ground-based rovers, leveraging autonomous navigation and robust suspension systems, could complement drones and helicopters to improve disaster response and accessibility. Future work will explore multi-agent coordination, hybrid aerial-ground systems, and adaptive AI algorithms to enhance rover efficiency and resilience in complex Earth environments.

Explore More!

Humayl F.
Rami Abi-Akl

Related Projects

Detecting Racial and Ethnic Bias in Social Media Posts Using Machine Learning

This study investigates the use of machine learning to detect racial and ethnic bias in social media posts using TF-IDF text embeddings and multiple classification models. Results show that Random Forest achieved the highest overall accuracy of 93.45%, demonstrating the potential of machine learning to support automated bias detection despite challenges posed by imbalanced data and the complexity of language.
Mira C.
Mentored by Matan Gans
Predicting Unplanned Electric Vehicle Breakdowns using Machine Learning on Sensor and Diagnostic Data

This study explores the use of artificial intelligence (AI) for fault prediction in electric vehicles (EVs) to reduce unexpected breakdowns and improve reliability. Using sensor, driving, and diagnostic data from 2020–2024, the research found that tree-based models, particularly Decision Tree and Random Forest, achieved over 90% predictive accuracy, demonstrating AI’s potential to enable proactive maintenance and enhance user confidence in EV technology.
Richa K.
Mentored by Rami Abi-Akl
Human-Robot Task Handoff: A Probabilistic Modeling Approach Explored through Cooperative Drawing

This paper investigates the task of handoff detection, crucial for the success of robot-assisted surgery, focusing on the creation of a synthetic dataset that can be used for training and benchmarking models for this task.
Lucas C.
Mentored by Ross Greer