SURF: Announcements of Opportunity
Below are Announcements of Opportunity posted by Caltech faculty and JPL technical staff for the SURF program. Additional AOs for the Amgen Scholars program can be found here.
Specific GROWTH projects being offerred for summer 2018 can be found here.
Each AO indicates whether or not it is open to non-Caltech students. If an AO is NOT open to non-Caltech students, please DO NOT contact the mentor.
Announcements of Opportunity are posted as they are received. Please check back regularly for new AO submissions! Remember: This is just one way that you can go about identifying a suitable project and/or mentor.
Announcements for external summer programs are listed here.
Students pursuing opportunities at JPL must be
U.S. citizens or U.S. permanent residents.
|Project:||Barefoot Rover Data Taking & Machine Learning (ML) Analysis|
|Disciplines:||Computer Science, Robotics, Data Science, Machine Learning|
|Mentor URL:||https://ml.jpl.nasa.gov/people/mandrake.shtml (opens in new window)|
|Background:||Close your eyes, take off your shoes, and walk around an unfamiliar room. Rapidly, you understand the general geometry and contents of the room. Surface textures, temperatures, stability, and sinkage richly inform you of the terrain types and objects in the room: shag carpet, wet kitchen tiles, lost car keys, legos. The Barefoot Rover project takes an existing pressure sensor-studded wheel as well as an installed inductance spectroscope, gathers copious pressure and inductance data as the wheel passes over many kinds of Earth and Mars-analog terrains, and builds algorithms to perform terrain classification, fit models of the surface itself such as sand grain size, and estimate the hydration level in the regolith.|
|Description:||This opportunity has three prongs: 1) The student will help in taking data using the actual MSL-scale sensor wheel upon many types, scales, and hydration levels as well as arrangements of embedded rocks. 2) ML-based exploratory analysis of the data will be conducted to assess sensitivity, content, and issues as well as advise labeling activities. 3) ML-based development will be used to create terrain classifications, soil composition analyzers, slip/skid/imbalance sensors, etc. Student must be comfortable taking science-grade data (reproducible, careful set up), Python programming, Linux environments, and some Machine Learning experience. It is also advisable that the student be physically capable of occasionally moving heavy objects (when changing out soil/regolith surrogates, 5 gallon buckets of sand)|
Required: Python+Numpy, Linux, basic statistics, some ML
Suggested: SKLearn, Random Forests, Clustering, physics/engineering/robotics lab experience
|Location / Safety:||Project building and/or room locations: . Student will need special safety training: Yes.|
This AO can be done under the following programs:
<< Prev Record 68 of 117 Next >> Back To List