Exploring Ultra-Wideband (UWB) Sensors for Martian Terrain Localization

Navigating in deep space terrains such as in lunar caves and Martian lava tubes is a challenging problem for conventional sensors such as cameras due to dust storms and other environmental disturbances in these extraterrestrial environments. Ultrawideband Sensors (UWBs) are a great alternative since they can provide passive ranging capabilities with up to cm-level accuracy in challenging terrains. NASA and other space agencies are actively prototyping various configurations of using UWB sensors to perform distributed rover localization for future autonomous navigation missions. 

In addition to exploring the sensing capabilities of these sensors, it is important to quantify the uncertainty in the positioning estimate using formal methods. Conformal Prediction (CP) is one such tool that provides distribution-free probabilistic uncertainty estimates from any positioning algorithm. The Machine Learning & Autonomy for Diverse Domains (MADD) Lab is actively prototyping various hardware configurations for real-time deployment of UWB sensors in Martian terrains and also developing novel algorithms to provide uncertainty measures in deep terrain. 

Some example tasks might include reading articles and prototyping with conformal prediction and UWB localization codes, designing experiments with Python and running them on robotic platforms in the lab, working with microcontrollers such as the Jetson Nano and Raspberry Pi, documenting experiments and contributing to open-source data collection and sharing efforts. The student will also gain experience working with a senior research mentor, presenting their work to a broad engineering audience, working and improving their Python/C ++ programming skills. 

Please submit the following as a single PDF to my email:

• Why do you want to be a part of the MADD lab and in particular, what are your interests in this project.
• Relevant experience (courses, projects, labs) and your technical contributions.
• Weekly availability (hrs/week) and any conflicts.
• Technical writing sample (s) from a prior class project.
• Unofficial transcript.

Interviews will be held after the initial review of applications.