Selected Experience
Google DeepMind, Research Director
Mountain View, California, 2023 - presentGoogle DeepMind / Google Brain Research, Senior Staff Research Scientist
Mountain View, California, 2021 - 2023Google Brain Research, Staff Research Scientist
Mountain View, California, 2020 - 2021Robotics at Google / Google Brain, Staff Research Scientist
Mountain View, California, 2019 - 2020Robotics at Google / Google Brain, Senior Research Scientist
Mountain View, California, 2017 - 2019Waymo / Google X, Senior Research Robotics Engineer
California, 2015 - 2017Sandia National Laboratories, Senior Computer Science R&D Engineer
Albuquerque, New Mexico, 2006 - 2015Selected Honors and Awards
IEEE Micro Top Picks 2023 Honorable Mention
2023Google Excellence in Leadership Award
2021Best of IEEE Computer Architecture Letters
2020IEEE Early Career Award in Robotics and Automation
2020RL4RealLife at ICML Best Paper Award
2019Distinguished Alumna
School of Engineering, University of New Mexico, 2018ICRA Best Paper in Service Robotics
2018Tom L. Popejoy Award
University of Mexico, 2015The best doctoral dissertation in Engineering, Mathematics, and Science in the period 2011-2014 Outstanding Graduate Student in Computer Science Award
University of New Mexico School of Engineering, 2014Sandia National Laboratories Doctoral Studies Program Fellow
2012 - 2014Young Scientist Fellow, Belgrade, Serbia
Education
Ph.D. in Computer Science (with distinction), University of New Mexico, Albuquerque, NM
Dissertation Title: “Reinforcement Learning and Planning for Preference Balancing Tasks," Advisor: Lydia TapiaMaster of Computer Science , University of Illinois, Urbana-Champaign, IL
Bachelor of Science in Mathematics, University of Belgrade, Belgrade, Serbia
Concentration in Computer Science. Selected Academic Service
IEEE RAS AdCom member, 2021 - present
Advisory Board Member, University of New Mexico, Department of Computer Science, 2019 - present
Co-Chair for Algorithms for Planning and Control of Robot Motion, IEEE Robotics Automation Society (RAS) Technical Committee, 2019 - 2022
Associate Vice President, IEEE Robotics Automation Society (RAS) Members Activities Board, 2018 - 2021
Panelist for CISE Research Initiation Initiative (CRII) on Machine Learning, National Service Foundation (NSF), 2018
Young Professionals Co-Chair, IEEE RAS
Program committee
AutoML 2023
Conference on Robot Learning 2021
Journal and Conference Service
Editor for Robot Learning, IEEE Robotic and Automation Letters (RA-L), 2023 - present
Action Editor, TLMR, 2022 - present
Awards Committee: ICLR 2023, L4DM 2022, CoRL 2020
Program Chair: AutoML 2023, CoRL 2021
Senior Area Chair, ICLR 2023
Associate Editor, IEEE Robotic and Automation Letters (RA-L), 2018 - 2021
Area Chair
NeurIPS, CoRL 2000
International Conference on Machine Learning (ICML), 2018 - 2021
International Conference on Learning Representations (ICLR), 2017 - 2022
IEEE International Conference on Robotics and Automation (ICRA), 2018
Workshop organizer
Co-organizer, Robot Learning in the Cloud: Remote Operations and Benchmarking, RSS 2022
Co-organizer - Machine Learning in Planning and Control of Robot Motion 4 Workshop, ICRA 2020
Co-organizer - Algorithms And Architectures For Learning In-The-Loop Systems In Autonomous Flight, ICRA 2019
Co-organizer - Becoming a Robot Guru Workshop 3, WAFR 2018
Lead organizer - Machine Learning in Planning and Control of Robot Motion 3 Workshop, ICRA 2018
Co-organizer - Becoming a Robot Guru Workshop 2, RSS 2016
Lead organizer - Machine Learning in Planning and Control of Robot Motion 2 Workshop, IROS 2016
Co-organizer - Becoming a Robot Guru, a workshop on broadening participation in robotics, ICRA 2015
Co-organizer - Machine Learning in Planning and Control of Robot Motion Workshop, IROS 2014
Journal reviewer
International Journal of Computer Vision
IEEE Robotics and Automation Letters (RA-L)
International Journal of Robotics Research (IJRR)
Robotica journal
Journal of Robust and Nonlinear Control
Conference Reviewer
ICRA, IROS, ICLR, CDC, MRS, ISRR, WAFR, NeuroIPS, CoRL
Invited Talks
2023 - Space Studies Board and Aeronautics and Space Engineering Board Joint Meeting Spring 2023, National Academy of Sciences
2023 - AI for Good moderator
2022 - Keynote @ CoRL 2022
2022 -- Keynote @ IROS 2022
2022 - AutoRL Tutorial at Fall AutoML School
2022 - AutoRL Tutorial @ AutoML
2022 - Scaling Robot Learning @ RSS
2022 - Pioneers Workshop @ RSS
2022 - Keynote at Advanced Robotics and its Social Impacts (ARSO) 2022
2022 - Motion Planning with Implicit Neural Representations of Geometry @ ICRA 2022
2022 - Easter European ML Workshop
2022 - Re-Work Deep RL
2022 - GATech Invited lecture on autonomy
2022 - Stanford Robotic Seminar
2021 - NeurIPS Industry Panel @ Physical Reasoning and Inductive Biases for the Real World - slides
2021 - NeurIPS, Safe and Robust Control of Uncertain Systems workshop - slides
2021 - NeurIPS Debate on Sim2Real Gap
2021 - NeurIPS Safety Workshop
2021 - ETH
2021 - AI Wonderland
2021 - IROS, Perception, Learning, and Controls
2021 - IROS, CLAMP, Self-supervision in Motion Planning & panel - recorded talk
2021 - IROS, SPAR, Learning to Learn for RL & panel
2021 - IROS, RL-Conform, Panel on RL & Control & HCI
2021 - IROS, IPLC, Autonomous navigation
2021 - AI Frontiers Meetup
2021 - Discussant, SFI Workshop on Evolutionary Computation
2021 - RSS, Workshop on Social Robot Navigation
2021 - RSS, Workshop on Integrating Learning and Planning
2021 - CVPR, Embodied AI workshop
2021 - ICRA, Perception and Action in Dynamic Environments
2021 - ICLR, A Roadmap to Neverending RL, panelist
2021 - University of Utah, seminar
2020 - Multidrone Cinematography Symposium, CMU
2020 - Perception, Learning, and Controls workshop @ IROS 2020, video (100+ attendees)
2020 - Summer Symposium on AI Research (3500+ attendees)
2020 - Future of Robotics Debate @ ICRA (1000+ unique attendees)
2020 - BAIR Commons Summit
2020 - Toward autonomous agents through evolution, reinforcement, and self-supervision, UCCS
2019 - Deep Learning for Motion Planning, Demo at CoRL
2019 - Deep Learning for Motion Planning, GATech
2019 - Deep Learning for Motion Planning, UIUC
2019 - Deep Learning for Motion Planning, UC Berkeley DREAM Seminar (Video)
2019 - Deep Learning for Robot Navigation, Google ML Summit Kirkland (Video, Pannel)
2019 - Robotics at Google: Navigation in Dynamic Environments, Demo at ICML
2019 - Task and Motion Planning - Learn locally, apply globally, BAIR / Google Meeting
2019 - Deep Learning for Motion Planning in the Dynamic World, Stanford - Google Navigation Workshop
2019 - Deep Learning Motion and Task Planning, University of Southern California
2019 - Overview of Deep Learning Motion and Task Planning, Industry forum at ICRA
2019 - Robot navigation with automated reinforcement learning, AI for Mankind
2018 - Automating Robot Learning Experiments, Automating Robot Experiments: Manipulation and Learning, IROS
2018 - Robot Navigation: From Abilities to Capabilities, Machine Learning in Robot Motion Planning Workshop, IROS
2018 - AI for Transportation Summit
2018 - PEARL: Continuous Action Model-based Reinforcement Learning, Columbia University
2017 - Society of Women Engineers WE17 Plenary on AI and Hi - 15,000 attendees
2017 - CogEdge workshop w/ MICRO 50 (declined)
2017 - PEARL: Continuous Action Model-based Reinforcement Learning, Electronic Materials Symposium (EMS)
2016 - Women Techmakers Summit, Chicago
2018, 2016 - University of New Mexico
2016 - University of Belgrade
2016 - Science, Technology, Engineering, Art, and Math Committee, PAUSD
Patents
2023 - US Patent application "Guided Evolution With Binary Predictors For ML Program Search"
2022 - US Patent application 20220391687, “Reinforcement Learning Algorithm Search”
2022 - US Patent, 11436441, “Systems and methods for training a machine learned model for agent navigation”
2021 - US Patent application 20210334320, “Automatic Navigation of Interactive Web Documents”
2020 - US Patent 10837811, “Systems, methods and computer program products for self-tuning sensor data processing”
2019 - US Patent 10311658, “Unexpected Impulse Change Collision Detector”.
2019 - US Patent, 10254759, “Interactive Autonomous Vehicle Agent”.
2017 - US Patent, 9,828,107, “Redundant Component and Intelligent Computerized Control System for Multi-rotor VTOL Aircraft”.
Media (last updated in 2021)
2021 - Techxplore - Air Learning: A gym environment to train deep reinforcement algorithms for aerial robot navigation
2021 - BlogPost: Evolving Reinforcement Learning Algorithms
2021 - BlogPost: Model-Based RL for Decentralized Multi-agent Navigation
2021 - BlogPost: PAIRED: A New Multi-agent Approach for Adversarial Environment Generation
2021 - Medium: DQNReg with Stable Baselines
2021 - Analytics India Magazine: What Are Evolving Reinforcement Learning Algorithms
2021 - Science Magazine: Who needs a teacher? Artificial intelligence designs lesson plans for itself
2021 - Featured in Google Research: Looking Back at 2020, and Forward to 2021
2020 - Techxplore: A framework for indoor robot navigation among humans
2020 - VentureBeat: Google’s AI helps robots navigate around humans in offices
2020 - Featured in Google Research: Looking Back at 2019, and Forward to 2020 and Beyond
2019 - Interview with GA Tech
2019 - How To Automate Reward Design For Reinforcement Learning Systems
2019 - Medium: QWeb: Solving Web Navigation Problems using DQN by Sherwin Chen
2019 - Bitcraze blog: Learning to Seek: autonomous source seeking using deep reinforcement learning onboard a Crazyflie
2019 - Medium: What if Quantization was Applied for Reinforcement Learning? by Christopher Dossman
2019 - New York Times, Inside Google’s Rebooted Robotics Program,
2019 - Google AI Blog, Follow-up press: [1], [2], [3], [4], [5]
2019 - Two papers mentioned in Looking Back at Google’s Research Efforts in 2018
2018 - ZdNet, “Forget Go, Google helps AI learn to book flights on the Web”
2018 - PC Magazine, “This Google Research Scientist Helps Robots Make Good Decisions”
2018 - ZdNet, “Google suggests all software could use a little robot AI”
2017 - New York Times, “Meet the People Who Train the Robots (to Do Their Own Jobs)”
2017 - Selected to represent Google in the Immigration video
2015 - Alum News, Newsletter The Computing Research Association’s Committee on the Status of Women in Computing Research (CRA-W) Newsletter, Summer/Fall 2015
2015 - Sandia Daily News, "Sandia robotics scientist wins prestigious UNM dissertation award,"
2015 - “Reinforcement learning and planning for preference balancing tasks,” AI Matters 1, 3, 8-12.
2014 - “Multicopter’s Smart Technology Provides Safer, More Efficient Delivery System,” The Innovation Door to The University of New Mexico, Vol. XXVII, pp 2,5.