Toyota Research Institute
Robotics Intern - Large Behavior Models, Human-Robot Interaction (HRI)
Toyota Research Institute, Cambridge, Massachusetts, us, 02140
At Toyota Research Institute (TRI), we're on a mission to improve the quality of human life. We're developing new tools and capabilities to amplify the human experience. To lead this transformative shift in mobility, we've built a world-class team in Energy & Materials, Human-Centered AI, Human Interactive Driving, and Robotics.
This is a summer 2025 paid 12-week internship opportunity. Please note that this internship will be an in-office role.
The Team
The team aims to create compelling, seamless, and effective interactions between humans and robots using Large Behavior Models (LBMs) that adhere to a human-centered design. Our team bridges complementary research and engineering expertise in physical human-robot interaction, user-centered design, extended reality interfaces, teleoperation, humanoid systems, software development, planning and controls, and robot learning. We're working on bringing human input into the development and evaluation of LBMs, specifically focusing on tasks and interactions relevant to older adults' needs and wants, where the overarching goal is to support aging in place through robotics. We're also implementing data-driven robot policies that can account for a person's preferences and feedback, especially in the context of policy errors/failures.
The Internship
We are looking for an intern researcher to join our team in the Cambridge, MA office! In collaboration with the wider LBM division, you will focus on categorizing and detecting policy failures in real-world tasks based on their impact on the human-robot interaction. You will develop reactive, multimodal classifiers to discriminate different levels of robot policy failures that can occur. You will help rapidly test these classifiers and develop mitigation strategies (e.g., safeguards in robot behavior, feedback mechanisms to provide information to users, etc.) for critical robot failures, which will be evaluated through experiments on real hardware that interacts with real people. The resulting monitors and mitigation strategies for failures will lead to the production of maintainable code and documentation. Lastly, you will have the opportunity to present your study findings to your colleagues and the larger TRI organization. We welcome you to join a positive, friendly, and enthusiastic team of researchers, where your research will contribute to helping people gain independence, access, and mobility.
Qualifications
Pursuing MS or PhD degree in Human-Robot Interaction, Human-Computer Interaction, Human Factors, Robotics, Computer Science, or a related field or equivalent practical experience.2+ years experience as an academic Human-Robot Interaction researcher.Expertise/Experience in machine learning around user behavioral modeling, such as human behavior monitoring and intention inference.Strong software engineering skills (C++ / Python preferred) and experience analyzing/debugging autonomous robotic systems.Experience with deploying and/or field-servicing prototype technologies.Experience conducting user studies involving real robot hardware.Experience with writing peer-reviewed conference papers or journal articles as lead author.Desire to contribute back to the robotics community with publications and open source code.Familiarity with robotic simulators including Drake, Mujoco, Bullet, etc. and/or original ROS or ROS 2.Passion for seeing robotics help humans and have a real-world, large-scale impact.Bonus Qualifications
Experience with behavior cloning and related imitation learning methods.Experience with interactive machine learning techniques that adapt robot policies given human feedback/corrections.Knowledge of optimization and sampling based planners for physical, reactive planning and control, trajectory optimization, or coordinated whole-body control.System integration experience around complex, open-ended, and multi-functional projects.Experience with qualitative and quantitative user research, including developing user study materials, IRB applications, facilitation and interviewing, management of Personally Identifiable Information (PII), and statistical analysis.
Please reference this Candidate Privacy Notice to inform you of the categories of personal information that we collect from individuals who inquire about and/or apply to work for Toyota Research Institute, Inc. or its subsidiaries, including Toyota A.I. Ventures GP, L.P., and the purposes for which we use such personal information.
TRI is fueled by a diverse and inclusive community of people with unique backgrounds, education and life experiences. We are dedicated to fostering an innovative and collaborative environment by living the values that are an essential part of our culture. We believe diversity makes us stronger and are proud to provide Equal Employment Opportunity for all, without regard to an applicant's race, color, creed, gender, gender identity or expression, sexual orientation, national origin, age, physical or mental disability, medical condition, religion, marital status, genetic information, veteran status, or any other status protected under federal, state or local laws.
Pursuant to the San Francisco Fair Chance Ordinance, we will consider qualified applicants with arrest and conviction records for employment.
This is a summer 2025 paid 12-week internship opportunity. Please note that this internship will be an in-office role.
The Team
The team aims to create compelling, seamless, and effective interactions between humans and robots using Large Behavior Models (LBMs) that adhere to a human-centered design. Our team bridges complementary research and engineering expertise in physical human-robot interaction, user-centered design, extended reality interfaces, teleoperation, humanoid systems, software development, planning and controls, and robot learning. We're working on bringing human input into the development and evaluation of LBMs, specifically focusing on tasks and interactions relevant to older adults' needs and wants, where the overarching goal is to support aging in place through robotics. We're also implementing data-driven robot policies that can account for a person's preferences and feedback, especially in the context of policy errors/failures.
The Internship
We are looking for an intern researcher to join our team in the Cambridge, MA office! In collaboration with the wider LBM division, you will focus on categorizing and detecting policy failures in real-world tasks based on their impact on the human-robot interaction. You will develop reactive, multimodal classifiers to discriminate different levels of robot policy failures that can occur. You will help rapidly test these classifiers and develop mitigation strategies (e.g., safeguards in robot behavior, feedback mechanisms to provide information to users, etc.) for critical robot failures, which will be evaluated through experiments on real hardware that interacts with real people. The resulting monitors and mitigation strategies for failures will lead to the production of maintainable code and documentation. Lastly, you will have the opportunity to present your study findings to your colleagues and the larger TRI organization. We welcome you to join a positive, friendly, and enthusiastic team of researchers, where your research will contribute to helping people gain independence, access, and mobility.
Qualifications
Pursuing MS or PhD degree in Human-Robot Interaction, Human-Computer Interaction, Human Factors, Robotics, Computer Science, or a related field or equivalent practical experience.2+ years experience as an academic Human-Robot Interaction researcher.Expertise/Experience in machine learning around user behavioral modeling, such as human behavior monitoring and intention inference.Strong software engineering skills (C++ / Python preferred) and experience analyzing/debugging autonomous robotic systems.Experience with deploying and/or field-servicing prototype technologies.Experience conducting user studies involving real robot hardware.Experience with writing peer-reviewed conference papers or journal articles as lead author.Desire to contribute back to the robotics community with publications and open source code.Familiarity with robotic simulators including Drake, Mujoco, Bullet, etc. and/or original ROS or ROS 2.Passion for seeing robotics help humans and have a real-world, large-scale impact.Bonus Qualifications
Experience with behavior cloning and related imitation learning methods.Experience with interactive machine learning techniques that adapt robot policies given human feedback/corrections.Knowledge of optimization and sampling based planners for physical, reactive planning and control, trajectory optimization, or coordinated whole-body control.System integration experience around complex, open-ended, and multi-functional projects.Experience with qualitative and quantitative user research, including developing user study materials, IRB applications, facilitation and interviewing, management of Personally Identifiable Information (PII), and statistical analysis.
Please reference this Candidate Privacy Notice to inform you of the categories of personal information that we collect from individuals who inquire about and/or apply to work for Toyota Research Institute, Inc. or its subsidiaries, including Toyota A.I. Ventures GP, L.P., and the purposes for which we use such personal information.
TRI is fueled by a diverse and inclusive community of people with unique backgrounds, education and life experiences. We are dedicated to fostering an innovative and collaborative environment by living the values that are an essential part of our culture. We believe diversity makes us stronger and are proud to provide Equal Employment Opportunity for all, without regard to an applicant's race, color, creed, gender, gender identity or expression, sexual orientation, national origin, age, physical or mental disability, medical condition, religion, marital status, genetic information, veteran status, or any other status protected under federal, state or local laws.
Pursuant to the San Francisco Fair Chance Ordinance, we will consider qualified applicants with arrest and conviction records for employment.