Jonathan Spencer
I work as a software engineer at Waymo on the Planner team, applying ML techniques to help the car reason about challenging multi-agent interactions in the next few seconds. I have a deep love for all human beings and I'm very interested in systems that model or interact with humans and make this world a better place for them.
My research background is in applying ML to robotics, using imitation learning and other methods to make the training of robotic systems less taxing on the humans involved. I earned a Ph.D. from Princeton University as part of the Edge Lab, co-advised by Mung Chiang and Peter Ramadge. Prior to Princeton I did my bachelors and masters degrees in electrical engineering at Brigham Young University working with Karl Warnick and the MAGICC Lab on radar signal processing and design for drone collision avoidance. During my Ph.D. I also spent time training small robot cars with Sidd Srinivasa and the UW MuSHR team, and training large autonomous cars with the Motion Planning team at Aurora.
I love running, cycling, triathlons, learning new languages, playing my cello, baking cookies, and puzzles.
Resume  / 
CV  / 
Google Scholar  / 
LinkedIn
|
|
|
Learning from Humans: Beyond Classical Imitation Learning
Jonathan C. Spencer
Princeton University Ph.D. Thesis , 2022
video
An overview of classical methods for learning from demonstration, including imitation learning and inverse reinforcement learning, followed with novel algorithms that improve on key deficiences in classical approaches. This includes lightly expanded versions of "Expert Intervention Learning" and "Feedback in Imitation Learning" papers below.
|
|
Expert Intervention Learning: An online framework for robot learning from explicit and implicit human feedback
Jonathan Spencer, Sanjiban Choudhury, Matthew Barnes, Matthew Schmittle, Mung Chiang, Peter Ramadge, Sidd Srinivasa
Autonomous Robots (AURO) , 2021
An expanded look at learning from interventions. This cost-based approach to imitation learning allows us to learn from a wide variety of feedback, including explicit actions and implicit signaling based on timing of takeover. We achieve 10x speedup over naive imitation learning.
|
|
Feedback in Imitation Learning: The Three Regimes of Covariate Shift
Jonathan Spencer,
Sanjiban Choudhury,
Arun Venkatraman,
Brian Ziebart,
J. Andrew Bagnell
ArXiv, 2021
arxiv
We show how imitation learning can be divided into three regimes of interest, depending on the amount of covariate shift induced by environment feedback effects. In the easy regime, naive behavioral cloning (BC) works out of the box. In the hard regime, we must query expert everywhere (i.e. DAgger). We introduce a set of techniques that require fewer samples than BC in the medium-difficulty "Goldilocks" regime.
|
|
Learning from Interventions: Human-robot interaction as both explicit and implicit feedback
Jonathan Spencer, Sanjiban Choudhury, Matthew Barnes, Matthew Schmittle, Mung Chiang, Peter Ramadge, Sidd Srinivasa
Robotics: Science and Systems (RSS) , 2020
video
We introduce a new technique for imitation learning based on a supervisor that intervenes in the robot control. Based on both the timing of when the expert takes over and the content of what the expert does while in control, we achieve a massive speed-up over traditional imitation learning techniques.
|
|
Personalized Thread Recommendation for MOOC Discussion Forums
Andrew Lan, Jonathan C. Spencer, Ziqi Chen, Chris Brinton, Mung Chiang
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD) , 2018
arxiv /
bibtex
We introduce a point-process based technique for making timely and topical thread recommendations in MOOC discussion forums that significantly outperforms baselines.
|
|
Ground-Based Sense-and-Avoid System for Small Unmanned Aircraft.
Laith Sahawneh, Jared Wikle, Kaleo Roberts, Jonathan C. Spencer, Tim McLain, Karl Warnick, Randy Beard
Journal of Aerospace Information Systems (JAIS) Vol. 15 Iss. 8 Pg. 501-517 , 2018
This work demonstrates a complete end-to-end collision avoidance system where the ego drone communicates in real time with a ground-based radar sensor that detects intruders and computes safe avoidance trajectories. This work was the cumulative effort of many years of work by many, many people.
|
|
A Compact Phased Array Radar for UAS Sense and Avoid
Jonathan C. Spencer
Brigham Young University Master's Thesis , 2015
This thesis details the full-stack system design and signal processing of a four channel phased array FMCW radar system. The bulk of the supporting RF circuitry for LO, FMCW modulator, demodulation, and baseband filtering was done by myself, as well as the algorithms for processing and filtering the angular signal on the integrated DSP board.
|
|
Minimum Required Sensing Range for UAS Sense and Avoid Systems
Laith Sahawneh, Jonathan C. Spencer, Randy Beard, Karl Warnick
AIAA Infotech @ Aerospace , 2016
Based on realistic sensor models, maximum flight velocities of several different aircraft and a minimum safe distance of 500 ft, we determine that the minimum sensing distance for a UAV to be able to successfully detect, compute and execute a maneuver is 1.8km.
|
|
Airborne Radar-Based Collision Detection and Risk Estimation for Small Unmanned Aircraft Systems
Laith Sahawneh, James Mackie, Jonathan C. Spencer, Randy Beard, Karl Warnick
Journal of Aerospace Information Systems (JAIS) Vol. 12 Iss. 12 Pg. 756-766 , 2015
This work estimates probability of collision risk for a pair of aircraft at the same altitude using state estimates from a radar sensor and a reachable sets framework.
|
|
Compact FMCW Radar for a UAS Sense and Avoid System
James Mackie, Jonathan C. Spencer, Karl Warnick
IEEE Antennas and Propagation Society International Symposium (APSURSI) , 2014
This radar demonstrates the effectiveness of an ultra-low cost radar system (>$100) using a 24 GHz radar-on-a-chip system.
|
|
I've served as a reviewer for the following venues
Neural Information Processing Symposium (NeurIPS)
Conference on Robot Learning (CoRL)
Artificial Intelligence for Human-Robot Interaction (AI-HRI)
Conference on Information Signals and Systems (CISS)
|
|