Internship - Physical AI for Dexterous, Contact-Rich Humanoid Manipulation

Mitsubishi Electric Research Laboratories, Inc.; Cambridge (MA); On-site; USD 67,000 - 89,000; Part time

Job summary

Mitsubishi Electric Research Laboratories (MERL) invites a Ph.D. student to join a project on hybrid learning and control for reliable humanoid manipulation in factory automation.

You will explore Vision-Language-Action models and World-Action Models, integrating them with motion planning, feedback control, and perception on physical robots. You will implement and evaluate algorithms on real platforms for tasks such as container stacking, kitting, tool manipulation, and assembly, with

Qualifications

• Current enrollment in a Ph.D. program in robotics, CS, ME, EE, or a related field.
• Hands-on experience adapting or evaluating VLA models on physical robots.
• Strong foundations in robot manipulation, motion planning, and feedback control.

Responsibilities

• Develop and evaluate novel algorithms on physical robotic platforms for industrial tasks.
• Combine Vision-Language-Action models with World-Action Models and classical motion planning, control, and perception.
• Compare approaches via task success, recovery performance, execution time, and constraint violations.

Skills

Robot manipulation

Motion planning

Feedback control

Education

PhD student in robotics / CS / ME / EE

Tools

Python

ROS2

PyTorch

Isaac Sim

MuJoCo

Job description

Mitsubishi Electric Research Laboratories (MERL) is seeking a highly motivated Ph.D. student to develop hybrid learning and control methods for reliable humanoid manipulation in factory automation. The research will combine Vision-Language-Action (VLA) models and World-Action Models (WAMs) with classical motion planning, feedback control, and perception. A central question is how robots should coordinate these components, recognize their limitations, and recover when execution deviates from the intended task.

The intern will develop and evaluate novel algorithms on physical robotic platforms, targeting industrial tasks such as container stacking and transport, kitting, tool manipulation, and assembly/disassembly. The project will combine algorithm development with simulation and real-world experiments, comparing approaches through task success, recovery performance, execution time, and constraint violations. The intern will work closely with MERL researchers on a focused research contribution, with the goal of submitting findings to leading robotics or machine-learning conferences such as CoRL, RSS, ICRA, IROS, NeurIPS, or ICML.

Required Specific Experience

• 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.

Preferred Experience

• Humanoid (Unitree G1, Agibot G2) or bimanual manipulation, including integration with whole-body control.
• World-action models or learned world models for prediction, planning, or control.
• Learning from demonstrations, teleoperation, or autonomous data collection.
• Uncertainty estimation, failure detection, policy intervention, or sim-to-real transfer.
• Contributions to open-source robotics or robot-learning repositories.

The pay range for this internship position will be 6-8K per month.