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

Research
princeton_dissertation

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.

expertinterventionlearning

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.

interventionlearning

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.

MOOCforums

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.

groundbased

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.

thesis

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.

2016infotec

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.

collisionrisk

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.

mackieradar

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.

Patents
radarpatent

Phased Array Radar Systems for Small Unmanned Aerial Vehicles
US Patent US10317518B2

Karl Warnick, Jonathan C. Spencer, 2018


This patent covers the use of one-board phased array radar systems as opposed to gimballed single beam radar systems for detecting small unmanned aerial vehicles and covers the majority of the work presented in my BYU masters thesis.

Teaching
teaching

EET201 - Electrical Circuits - Fall 2021 (Sole Instructor)

EET211 - Electronics I - Fall 2021 (Sole Instructor)

EET211 - Safety-Critical Robotics Systems - Fall 2020 (TA)

ELE381 - Networks: Friends, Money, Bytes - Fall 2017 (TA)

ECEn549 - VLSI Communication Circuits - Fall 2013 (TA)

ECEn380 - Signals and Systems - Winter 2013 (TA)

ECEn220 - Analog Circuits I - Fall 2012 (TA)

Service

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)


webpage formatting source