MERL is seeking a highly motivated intern to research multi-agent motion planning by combining optimization-based methods with machine learning. The ideal candidate is enrolled in a PhD program in Electrical, Mechanical, Aerospace Engineering, Robotics, Computer Science or related program, with prior experience in multi-agent motion planning, machine learning (especially supervised, reinforcement, and safe ML), and convex and non-convex optimization. A successful internship will result in innovative methods for multiagent planning, in the development of well-documented (Python/MATLAB) code for validating the proposed methods, and in the submission of relevant results for publication in peer-reviewed conference proceedings and journals. The expected duration of the internship is 3 months with a flexible start date in the Spring/Summer 2021. This internship is preferred to be onsite at MERL, but may be done remotely where you live if the COVID pandemic makes it necessary.

MERL is looking for a highly motivated and qualified intern to work on computer vision for robotic manipulation. The ideal candidate would be a current Ph.D. student with a strong background in computer vision, deep learning, and/or robotics. There are several available topics for consideration including learning for object manipulation, grasp detection and regrasping, pose estimation, and intent recognition for human-robot interaction. The internship requires development of novel algorithms which can be implemented and evaluated on a robotic test-bed. Experience in working with a physics engine simulator like Mujoco, pyBullet, or Gazebo is required. Proficiency in Python programming is necessary and experience with ROS is a plus. Successful candidate will collaborate with MERL researchers and publication of the relevant results is expected. Start date is flexible and expected duration of the internship is 3-4 months. Interested candidates are encouraged to apply with their recent CV and list of publications in related topics. This internship is preferred to be onsite at MERL, but may be done remotely where you live if the COVID pandemic makes it necessary.

MERL is seeking a highly motivated and qualified intern to collaborate with the Control for Autonomy team in the development of algorithms for coordinating control and perception in autonomous systems. The overall objective is to determine the sensing strategy together with the motion/control strategy to effectively achieve a control goal while managing the risk due to the environment uncertainty. The ideal candidate is expected to be working towards a PhD with strong emphasis in control or planning algorithms, and to have interest and background in as many as possible among: predictive control, stochastic tubes, scenario-based stochastic optimization, uncertainty and risk representation, machine learning and motion planning algorithms. Good programming skills in MATLAB and/or Python, are required. The expected duration of the internship is in the Spring of 2021, for a duration of 3-6 months. This internship is preferred to be onsite at MERL, but may be done remotely where you live if the COVID pandemic makes it necessary.