<p>Senior Motion Planning and Controls Engineer</p> <p>Mission Statement:</p> <p>The Controls Team is responsible for the synthesis and execution of dynamic trajectories by the Motional Autonomous Vehicle. This team focuses on the generation of comfortable and safe trajectories for the AV to perform, the design of control systems that interface with vehicle platform actuators, and the communication interfaces that relay trajectory information to low-level control modules. The team pursues these goals through a process of rigorous algorithmic design, validation, analysis in simulation, and comprehensive closed-course and public road evaluation.</p> <p>As the team's responsibilities are growing to support more motion control capabilities and the scaling of Motional's deployment area, we are looking for a Senior Motion Planning and Controls Engineer to help build a robust motion planning and control pipeline. This person will work on enabling cutting-edge capabilities for Motional's AV, including algorithm design and documentation, software development, metrics definition, simulation implementation and evaluation, and in-vehicle testing. As part of this role, the team member will maintain cross-functional relationships across the organization to help understand and communicate the impacts of their work on overall AV performance.</p> <p>What you will work on:</p> <ul> <li>Design, implement, and test low-level controllers, state estimators, and state-machine logic that directly interface with platform sensors and actuators to produce performant, comfortable, and safe motion tracking. </li><li>Integrate upstream trajectory generation and downstream motion tracking controllers through principled trajectory interface design, including generator / controller state machine logic design and trajectory communication formulation. </li><li>Develop test/analysis tooling for isolated evaluation of motion tracking performance and incremental integration testing that incorporates upstream components (trajectory generation, planning, perception, etc.), select test parameters, and analyze test results. </li><li>Architect and implement dynamic simulation environments that accelerate the design and analysis of motion planning and control algorithms, including validation of simulation models against real-world data. </li><li>Define and implement performance, comfort, and safety metrics for motion planning and control, and perform quantitative analysis of fleet-wide vehicle data to validate design improvements and identify key areas of improvement. </li><li>Formulate, implement, analyze, and test optimization and machine learning-based frameworks for dynamic trajectory synthesis. </li><li>Build a system-wide understanding of Motional's autonomy stack components by supporting root-cause analysis of simulation, closed-course, and public road events from a motion planning and control perspective. </li><li>Travel for in-person vehicle testing at Motional's and our partner's deployment and test track locations, typically once every 4 to 6 months. </li></ul> <p>Desired Background:</p> <ul> <li>MS, PhD preferred, in one of Control Theory / Robotics / Computer Science / Applied Math or a related field </li><li>3+ years of experience developing controls / motion planning related algorithms and components in an industrial setting </li><li>Experienced with concepts from control theory, including linear/nonlinear systems, state estimation / Kalman filtering, model predictive control, data-driven system identification, time-series data processing, and data visualization </li><li>Familiarity with numerical optimization, quadratic/conic programming, convex optimization, nonlinear programming, and non-convex optimization </li><li>Familiarity with Python and C++/C </li><li>Familiarity with Linux-based operating systems </li></ul> <p>Bonus Points:</p> <ul> <li>Familiarity with vehicle dynamics and modeling, including longitudinal/lateral vehicle dynamics, tire modeling, EV drive-train / steer dynamics, etc. </li><li>General familiarity with machine learning, including supervised learning, reinforcement learning, training/test validation, etc. </li><li>Publications in Controls/Robotics or Autonomous Driving conferences/journals (CDC, ACC, TAC, CSL, Automatica, IROS, ICRA, CoRL, RAL, TRO, IV, ITSC, T-ITS). </li><li>Familiarity with SQL, Looker, MATLAB/SimuLink. </li><li>Familiarity with Gitlab, Bazel, VSCode / CLion. </li><li>Familiarity with AV industry simulation tooling. </li><li>Familiarity with CAN communication protocol, AUTOSAR, AURIX. </li><li>Familiarity with real-time kinematic (RTK) GPS localization </li></ul>