This position is posted from an outside job board or employer website for the convenience of Yale students. Please note this position was not posted directly at Yale by the employer, and therefore the employer has not reviewed or agreed to any of Yale’s recruiting policies. The University does not endorse or recommend employers, and a posting does not constitute an endorsement or recommendation. The University makes no representations or guarantees about job listings or the accuracy of the information provided by the employer. The University is not responsible for safety, wages, working conditions, or any other aspect of off-campus employment. It is the responsibility of students to perform due diligence in researching employers when applying for or accepting opportunities.
The Motional global headquarters are located at 100 Northern Avenue in Boston, MA. Nestled in the busting Seaport district with sweeping views of Boston Harbor and downtown Boston, the offices are located close to major transit lines and a quick walk to various restaurants and popular attractions.
AUTONOMOUS VEHICLE RESEARCH INTERN: RULEBOOKS (PF)
The Rulebooks team formalizes the desired behavioral specifications of our vehicles as many, potentially conflicting, rules with different priorities. In this role, you will support the team’s effort on building a computationally efficient framework for generating rule-guided optimal trajectories in various driving scenarios. You will leverage recent advancements in motion control and path planning techniques to find control strategies that are dynamically and computationally feasible and are optimal with respect to the hierarchy of priorities of rules. (See https://arxiv.org/abs/2107.07460 , https://arxiv.org/pdf/2009.11954.pdf , https://arxiv.org/pdf/2105.01204 )
You will also study the effect of various sources of uncertainty (e.g. in perception, localization, object classification) in evaluation of rules and generation of optimal control strategies under uncertainty.
WHAT YOU’LL BE DOING
- Develop robust algorithms to produce rule-based optimal trajectories more efficiently and integrate the algorithms with our in-house tools at Motional
- Structure performance metrics for evaluation of rules under uncertainty
- Design a framework for comparison of trajectories using hierarchy of prioritized rules under uncertainty
WHAT WE’RE LOOKING FOR
- Graduate student in control engineering, Robotics, Intelligent Transportation Systems, or related fields
- Strong experience with path planning and control techniques (RRT, CBF, etc.)
- Experience in Python, including standard scientific computing and optimization libraries
- Knowledge of statistics and probabilities
BONUS POINTS (NOT REQUIRED)
- Publication record in robotics and control
- Experience in formal logics (STL, LTL) and autonomous systems
- Experience in Git
WHY YOU SHOULD JOIN US
- This is a great opportunity to experience first hand what it takes to bring a commercial grade robot taxi service to life while working in a welcoming environment full of enthusiastic professionals.