MERL is seeking a highly motivated and qualified intern to collaborate with the Control for Autonomy team in research on design and analysis of model predictive control algorithms for systems subject to environment uncertainty that can be reduced by perception. The research domain includes algorithms for stabilizing uncertain and stochastic model predictive control, uncertainty quantification and reduction via estimation, optimization algorithms for uncertain and stochastic predictive control. The ideal candidate is expected to be working towards a PhD with strong emphasis in some of: stochastic model predictive control, statistical estimation, uncertainty quantification, and sensing-driven control. Good programming skills in MATLAB, Python are required, knowledge of C/C++ or ROS are a plus. The expected start of of the internship is in the late Spring/Early Summer 2022, for a duration of 3-6 months.

MERL is looking for a self-motivated intern to work on problems at the intersection of computer vision and robotic manipulation for solving tasks such as vision-based robotic tool manipulation. The ideal candidate would be a PhD student with strong mathematical background in machine learning/reinforcement learning, modeling contact-physics for object manipulation, and experience in working with and training deep models on large scale computer vision datasets. Proficiency in PyTorch and (differentiable) robotic simulators is expected. Knowledge of meta-learning, hierarchical RL, self-supervised learning, and scene graph based visual reasoning would be useful. The intern will conduct original research with MERL researchers towards scientific publications.

MERL is looking for a highly motivated individual to develop planning and control algorithms for multi-agent systems for resource monitoring. The ideal candidate has experience in multi-agent motion planning and data-driven sequential decision-making. The ideal candidate will have published in one or more of these topics: planning over discrete spaces, task scheduling and assignment, vehicle routing and scheduling problems, multi-arm bandits, reinforcement learning, and planning and control of aerial and ground robots. The candidate should have a working knowledge of ROS and Python/C++ since the internship will include validation in various simulation/hardware testbeds at MERL. The minimum duration of the internship is 3 months; the start time is Summer/Fall 2023.