Robotics Intern, World Action Models for Robot Policy
About the Role
At Toyota Research Institute (TRI), we're on a mission to improve the quality of human life by developing new tools and capabilities to amplify the human experience. We're building general-purpose robots that can perform a wide variety of dexterous, multi-step tasks in everyday environments. Our Vision-Language-Action Models (VLAs) are foundation models that generate robot actions from sensor data and natural-language requests, trained on a large curriculum of robot demonstrations combined with internet-scale text, image, and video data and procedurally generated simulation data. A growing focus is world action models that learn to predict both how the world will change and which actions the robot should take, supporting planning over long horizons, recovery from errors, and anticipation of human behavior.
The challenge is to enable robots that help with household chores and cooking, support older adults living independently, and work side by side with people in messy, unstructured settings where useful tasks take minutes rather than seconds. Robots must chain many skills together, notice and recover from mistakes, and adapt to the people around them. We believe world action models grounded in large-scale physical interaction data are key to robot policy learning.
This is a paid 12-week internship opportunity with a hybrid, in-office work arrangement. The intern will adapt pre-trained world foundation models—through mid-training, fine-tuning, or post-training techniques—into world action models that serve as robot policies deployed on humanoid platforms or other mobile manipulators in human-centered environments. Project focus areas can be customized based on research interests. The intern will work closely with researchers and engineers to turn ideas into working prototypes, run experiments in simulation and on real robots, and publish results at peer-reviewed venues.
Areas of Focus
- World action models for long-horizon tasks
- Human-robot interaction and collaboration
- Humanoid whole-body manipulation
- Cross-embodiment transfer and learning from human video
- Sim-to-real and synthetic data
- Post-training and continual learning
Responsibilities
- Conduct original research on world action models for robot policy, from problem definition through experiments and analysis
- Mid-train, fine-tune, or post-train world action models, and evaluate them in simulation and on humanoids or mobile manipulators
- Design evaluations that measure long-horizon task success and the quality of interaction with people
- Collaborate with researchers and engineers across teams, the Robotics division, and university partners
- Share results through internal presentations, peer-reviewed publications, and open-source releases where appropriate