LUKE SHIMANUKI 61 Bishop Allen Dr, Apt 2 Cambridge, MA 02139 luke@shimanuki.cc 1-925-331-0577 https://luke.shimanuki.cc EXPERIENCE Senior Software Engineer (Motion Planning) (2022 - present) Aurora Innovation, Boston, Massachusetts Developed models for predicting and planning semantic driving behaviors such as merging and lane changing. SDE II --> Senior SDE (Planning & Controls) (2020 - 2022) Magna Electronics (formerly Optimus Ride), Boston, Massachusetts Designed and implemented probabilistic model for inferring trajectories and interactions between road users. Formulated requirements and algorithmic design for ADAS features following auto industry safety standards. Intern (Prediction) (Summer 2018) Cruise Automation (General Motors), San Francisco, California Improved model for robotic cars to predict trajectories of other road users, passing 3x as many scenario tests. SWE Intern (Perception) (Summer 2017) Optimus Ride, Boston, Massachusetts Created system for robotic cars to predict and avoid other vehicles to handle intersections. Intern (Machine Learning / Vision) (January 2017) RightHand Robotics, Somerville, Massachusetts Designed and implemented deep learning architectures for robotic vision and grasping. Developer (2015 - 2016) Tanius Technology (proprietary trading), Alamo, California Implemented machine learning models and data pipeline to predict market patterns. RESEARCH MIT CSAIL Learning and Intelligent Systems Group (2017 - 2020) Lower bounds for 2D motion planning under obstacle uncertainty -- WAFR 2018 & IJRR 2021 Fixed-parameter algorithm for motion planning under obstacle uncertainty -- WAFR 2022 Value functions for guiding task-and-motion planning using graph networks -- CoRL 2019 & IJRR 2021 Safe control avoiding moving obstacles with unobservable policies -- [unpublished] Leveraging hierarchies to efficiently solve robotic planning tasks / POMDPs -- [unpublished] Stanford Autonomous Systems Laboratory (Summer 2015) Efficiency of vehicle routing algorithms based on real-world ride requests -- ICRA 2016 Vehicle routing algorithm with 10% improvement over state-of-the-art in simulation -- Intel STS 2016 EDUCATION Massachusetts Institute of Technology (2016 - 2020) M.Eng Electrical Engineering & Computer Science (AI Concentration), GPA 5.0 (out of 5) S.B. Double Major in Computer Science and Brain & Cognitive Science, GPA 4.9 (out of 5), 5.0 in-major (CS) Coursework: Embedded Systems, Machine Learning (G), Comp. Intelligence (G), Robotics Science & Systems, Quantum Comp. (G), Operating Systems (G), Adv. Data Structures (G), Natural Language Processing, Theory of Comp. (G), Comp. Linguistics (G), Comp. Cognitive Science, Design & Analysis of Algorithms ACTIVITIES Site Manager (2020) Food for Free COVID-19 Relief Program Directed team of volunteers for packing and delivering groceries to ~300 households weekly. Program Director, Head Webmaster (2017 - 2020) MIT Educational Studies Program Directed educational programs reaching ~3000 MS/HS students with ~1000 classes taught by ~500 teachers and run by ~100 volunteers. Mentored future directors. Maintained website used by ~5000 students. Software Lead (2012 - 2016) AVBotz Led the software team (~12 members) for fully-autonomous submarine for manipulating objects, aiming and shooting torpedoes, and navigating around obstacles. International finalist (7th Place) at RoboSub 2015. Co-President, HPMS Branch Director (2013 - 2016) ACE Coding Managed ~16 volunteers to teach weekly programming lessons to ~100 middle school students annually. Organized ACE Code Day, an 8 hour event attracting ~300 students. Taught machine vision workshop. Middle School Tutor (2019 - 2020) Cambridge School Volunteers SKILLS Proficient in C, C++, Python, Javascript, Java, UNIX Shell Familiar with C#, LabView, Matlab, Simulink, Scala, x86 Assembly Libraries: ROS, OpenCV, Theano, PyTorch, ReactJS, TensorFlow AWARDS USA Computing Olympiad Platinum Division Intel Science Talent Search 2016 Semifinalist Eagle Scout MIT Battlecode 2018 Finalist (9th place) PROJECTS (C++) Low latency audio streaming to enable remote musicians to play in-sync (C) Web browser using Chromium's rendering engine with configurable vi-like key bindings (C) C compiler to convert C code to x86 assembly (Java) Neural network AI for a multiplayer platformer fighting game (Python) Musical autocomplete to assist chord and melody composition (Python) Gridded workspace manager for the i3 Window Manager