Intern: Hybrid AI for Dexterous Humanoid Manipulation

Mitsubishi Electric Research Labs; Cambridge (MA); On-site; USD 67,000 - 89,000; Full time

Job summary

Mitsubishi Electric Research Laboratories (MERL) in Cambridge, MA, seeks a motivated PhD student for an internship to develop hybrid learning and control methods for dexterous humanoid manipulation in factory automation. The project combines Vision-Language-Action models with world-action models and classical planning and control.

You will implement algorithms on physical robots and in simulation, evaluate performance on tasks like container handling, assembly, and tool manipulation, and share

Qualifications

• Current enrollment in a Ph.D. program in robotics, computer science, mechanical engineering, electrical engineering, or a related field.
• Hands-on experience adapting or evaluating VLA models, such as GR00T, p0.5, or related models, including deployment on physical robots.
• Strong foundations in robot manipulation, motion planning, and feedback control.
• Proficiency in Python, ROS2, and a deep-learning framework such as PyTorch.
• Experience conducting robotic experiments using simulation environments such as Isaac Sim or MuJoCo.
• Demonstrated research ability through publications, substantial research projects, or research software.

Responsibilities

• Develop and test hybrid learning/control methods for humanoid manipulation.
• Evaluate algorithms on physical robotic platforms and in simulation.
• Collaborate with MERL researchers and contribute findings to conferences.

Skills

Python

ROS2

Deep learning (PyTorch)

Robot manipulation

Motion planning

Education

PhD student in robotics/CS/ME/EE

Tools

Isaac Sim

MuJoCo

Job description

Mitsubishi Electric Research Laboratories (MERL) in Cambridge, MA, seeks a motivated PhD student for an internship to develop hybrid learning and control methods for dexterous humanoid manipulation in factory automation. The project combines Vision-Language-Action models with world-action models and classical planning and control.

You will implement algorithms on physical robots and in simulation, evaluate performance on tasks like container handling, assembly, and tool manipulation, and share