ARL 7 – Research Assistant, Machine Learning, State Estimation, Sensor Modeling

Project Name
Machine Learning with State estimation and Sensor Modeling

Project Description
Applied research and development in machine learning, stochastic/Kalman filtering and control systems.

Job Description
The candidate will have experience implementing machine learning algorithms such as Gaussian mixture models, deep learning algorithms, and information theoretic methods; and have experience applying these algorithms to real-world datasets. The candidate will work with postdoc-level researchers to implement machine learning algorithms and analyze multimodal datasets, as well as develop sensor and process models from these datasets which are applicable to heterogeneous autonomous systems. BS/MS in computer science with experience in machine learning and implementation of machine learning algorithms, neural networks, stochastic/Kalman filtering, control systems, preferably with applied research experience. Laboratory experience in applied research and development is preferred. Experience with community-standard machine learning libraries such as Keras, Mallet, and Tensorflow is desired. Experience implementing and running control system algorithms such as extended Kalman filters in C++, Java, and Python is highly desirable.

Required Skills

  • Experience developing software in the Ubuntu Linux environment and mathematical software packages such as MATLAB
  • Experience with software build environments such as CMake, Ant, Maven
  • A solid foundation in machine learning and prototyping and implementing machine learning algorithms directly from theory
  • Experience applying machine learning algorithms to real-world datasets
  • Fluency in C++, Java, and Python
  • Experience with software and revision management tools such as Subversion and Git

Preferred Skills

  • Strong familiarity with the mathematics of fusion algorithms for either autonomous applications or state-estimation; and, the ability/willingness to learn the other.
  • Experience with implementation and use of stochastic filtering and control algorithms
  • Proficiency with community-standard machine learning libraries such as Tensorflow
  • Experience with generating mathematical sensor models involving complex systems
  • Experience with implementing and testing multi-sensor fusion and state estimation algorithms for robotics.
  • Practical understanding of experimental statistics including statistical experiment design, data analysis, validation and verification.
  • Experience with the Robot Operating System (ROS) and associated build environments

Apply now.

Go back to the summer research program list.