Research Intern, Continual Adaptation for Robotics

About the Role

At Toyota Research Institute (TRI), we’re developing new tools and capabilities to amplify the human experience. We are seeking a Research Intern to advance continual adaptation for robot policies. This is a paid 12-week internship opportunity and is a hybrid, in-office role.

The Research

The goal is to enable robots to improve from experience, personalize their behavior, preserve learned capabilities, and build on prior learning to acquire new behaviors more efficiently. The work will combine algorithm development with experiments in simulation and on real robots, emphasizing reliable adaptation with limited robot experience and human effort. Projects may explore:

• Continual learning: Preserving existing capabilities and using prior experience to learn new behaviors efficiently.
• Efficient learning and adaptation: Enabling robots to improve with limited experience by identifying adaptation needs and effectively using prior knowledge, new interactions, and guidance.
• Personalization from human guidance: Using demonstrations, corrections, or preference feedback to change robot task performance while maintaining success.

Key Responsibilities

• Work with a mentor to formulate a research question, develop an approach, and implement it.
• Design and run controlled experiments in simulation and on real robots.
• Analyze failure modes and maintain reproducible code and experimental records.
• Collaborate with researchers and engineers, present findings, and contribute to technical reports and potential publications.

Requirements & Tech Stack

• Strong programming skills in Python.
• Experience with a deep learning framework such as PyTorch or JAX.
• Ability to design experiments, reason critically about results, work independently with mentorship, and communicate clearly.

Qualifications

• Currently pursuing a Ph.D. in robotics, machine learning, computer science, or a related field.
• Research experience in reinforcement learning, imitation learning, continual learning, or closely related machine learning methods.

Bonus Qualifications

• Experience with generative robot policies, diffusion or flow models, vision-language-action, or world-action models.
• Experience with online reinforcement learning, interactive learning, personalization, preference learning, or continual learning.
• Experience with post-training, parameter-efficient adaptation, modular models, or agentic approaches using pretrained models.
• Experience with robotics simulation, real-world robot learning, or robot data collection and evaluation systems.
• Relevant research contributions demonstrated through publications, open-source projects, or substantial research projects.