Robotics Intern, Dynamics and Simulation

Toyota Research Institute

Toyota Research Institute

Kendall Square, Cambridge, MA, USA
Posted on Friday, November 3, 2023
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 Robotics, Human-Centered AI, Human Interactive Driving, and Energy & Materials.
This is a Summer 2024 paid 12-week internship opportunity. Please note that this internship will be a hybrid in-office role.
The Department
The mission of TRI Robotics is to invent and prove new robotic capabilities required to enable home robots to solve the challenges faced by an aging society. As part of that mission, we are developing a sophisticated suite of open source robotics software called Drake (https://drake.mit.edu), for use in our internal robotics projects and the wider community of advanced robotics researchers.
The Team
Within TRI Robotics, the Dynamics and Simulation team develops Drake tools to model and simulate mobile robot dynamics, object manipulation, and perception. We emphasize physical accuracy and robust, performant software permitting controller synthesis, learning, analysis, regression testing, and design in simulation that transfers meaningfully to the real world. Features include:
- Physics-based, high-fidelity, high-performance software tools for simulation of robots and vehicles interacting with their environments.
- Multibody dynamics, rigid and soft body computational mechanics.
- A unique hybrid dynamic system abstraction and infrastructure (like Simulink blocks, but differentiable and symbolically analyzable).
- Solvers for dynamic systems (numerical integration of DAEs, time stepping, event handling).
- Computational geometry, rendering, and contact response (emphasizing manipulation).
- Validation of simulation accuracy and verification of software and numerical methods.
This is open source, modern C++ software, developed using rigorous best practices including extensive unit and validation tests, detailed documentation, and collaborative pre-merge peer review. We encourage publication of novel work in peer-reviewed literature and collaboration with the wider robotics community.
Our team consists of computer scientists and engineers trained at leading academic institutions and innovative companies, with research and practical experience in robotics, computer graphics, computational mechanics, multibody dynamics, numerical methods, and software engineering. We have considerable expertise in all these fields and a lot of software to write, so there is much interesting work to do and plenty of opportunity to extend your knowledge in any of the above areas.
The Internship
We are looking for an intern to work on a research project that will help us advance the capabilities of our simulation tools. During this internship you will collaborate with other software engineers and research scientists to develop physically-accurate, reliable, and fast models and algorithms that are relevant to the simulation and robotics community. Every day, you will work towards solving difficult modeling, mathematical, and implementation problems with a focus on accuracy of simulation results, and reliability and performance of software. Your challenge will be to distill physical and mathematical phenomena into the clearest possible software model, and make it work! The final goal is to publish in a scientific journal and to implement new capabilities in our open source software, Drake.

Qualifications

  • Bachelor's degree in Computer Science or equivalent; advanced degree, physics and engineering background a plus.
  • Experience developing numerical methods and scientific software including physics-based simulation.
  • Solid grasp in at least some of linear algebra, differential equations, partial differential equations, nonlinear equations, geometry, and related numerical methods.
  • Excellent software development skills, preferably in C++ and/or Python.
  • Strong understanding of scientific software accuracy and performance issues and tradeoffs.
  • Bonus – deep knowledge and expertise in one or more of the following: hybrid systems, multibody dynamics, numerical integration, discrete and differential computational geometry, contact mechanics, differential-algebraic equations, high performance computing, GPU programming.
Please add a link to Google Scholar and include a full list of publications when submitting your CV to this position.
The pay range for this position at commencement of employment is expected to be between $45 and $65/hour for California-based roles; however, base pay offered may vary depending on multiple individualized factors, including market location, job-related knowledge, skills, and experience. Note that TRI offers a generous benefits package including vacation and sick time. Details of participation in these benefit plans will be provided if an employee receives an offer of employment.
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.