Jaime F. Fisac

I am currently spending a year as a Research Scientist at Waymo (formerly known as Google’s Self-Driving Car project) and will be starting as an Assistant Professor at Princeton in Summer 2020.

I am interested in developing analytical and computational tools to safely deploy robotic and artificial intelligence (AI) systems in the physical world and the human space. My goal is to ensure that autonomous systems such as self-driving cars, delivery drones, or home robots can operate and learn in the open while satisfying safety constraints at all times. These systems will often need to reason about people's beliefs and intentions, acknowledging and leveraging human-machine interaction to guarantee safety.

Specifically, my research focuses on the following areas:

  • Safety assurance for learning robotic systems
  • Safe and scalable multi-agent decision-making
  • Safe human-centered robotic and AI systems

Bio in a nutshell
I completed my PhD at Berkeley in Fall 2019 advised by Profs. Shankar Sastry, Claire Tomlin, and Anca Dragan. Before that, I got my B.S./M.S. Electrical Engineering degree at the Universidad Politécnica de Madrid in Spain and a Masters in Aeronautics at Cranfield University in the UK. I also spent one year working in UAV system design at Aerialtronics. I was then awarded the La Caixa Foundation fellowship to pursue a graduate degree in the United States. At the midpoint of my PhD, I spent 6 months doing R&D work at Apple.



Here are the main research projects comprising my PhD research.
Click on the images to learn more.

Safe Learning for Robotics

Safe Learning for Robotics

Safety in Multi-Agent Systems

Safety in Multi-Agent Systems

Human-Centered Robotics

Human-Centered Robotics


Journal Articles

A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems
J. F. Fisac*, A. K. Akametalu*, J. H. Gillula, S. Kaynama, M. N. Zeilinger, and C. J. Tomlin
IEEE Transactions on Automatic Control, 2019. In press.

Robust Sequential Path Planning Under Disturbances and Adversarial Intruder
M. Chen, Q. Hu, C. Mackin, J. F. Fisac, and C. J. Tomlin
IEEE Transactions on Control Systems Technology, 2018.

Reachability-Based Safety and Goal Satisfaction of Unmanned Aerial Vehicle Platoons on Air Highways
M. Chen, Q. Hu, J. F. Fisac, A. K. Akametalu, C. Mackin, and C. J. Tomlin
AIAA Journal of Guidance, Control, and Dynamics, 2017.

Conference Articles

Probabilistically Safe Robot Planning with Confidence-Based Human Predictions
J. F. Fisac*, A. Bajcsy*, S. L. Herbert, D. Fridovich-Keil, S. Wang, C. J. Tomlin, and A. D. Dragan
Robotics: Science and Systems (RSS), 2018.

Planning, Fast and Slow: A Framework for Adaptive Real-Time Safe Trajectory Planning
D. Fridovich-Keil*, S. L. Herbert*, J. F. Fisac*, S. Deglurkar, and C. J. Tomlin
International Conference on Robotics and Automation (ICRA), 2018.

An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning
D. Malik*, M. Palaniappan*, J. F. Fisac, D. Hadfield-Menell, S. Russell, A. D. Dragan
International Conference on Machine Learning (ICML), 2018. Selected for long talk.

Pragmatic-Pedagogic Value Alignment
J. F. Fisac, M. A. Gates, J. B. Hamrick, C. Liu, D. Hadfield-Menell, M. Palaniappan, D. Malik, S. S. Sastry, T. L. Griffiths, A. D. Dragan
International Symposium on Robotics Research (ISRR). Blue-Sky Award.

FaSTrack: a Modular Framework for Fast and Guaranteed Safe Motion Planning
S. L. Herbert*, M. Chen*, S. Han, S. Bansal, J. F. Fisac, and C. J. Tomlin
Conference on Decision and Control (CDC), 2017.

Safe Sequential Path Planning of Multi-Vehicle Systems Under Disturbances and Imperfect Information
S. Bansal*, M. Chen*, J. F. Fisac, and C. J. Tomlin
American Control Conference (ACC), 2017.

Generating Plans that Predict Themselves
J. F. Fisac*, C. Liu*, J. B. Hamrick*, S. S. Sastry, J. K. Hedrick, T. L. Griffiths, and A. D. Dragan
Conference on Decision and Control (CDC), 2016.

Goal Inference Improves Objective and Perceived Performance in Human-Robot Collaboration
C. Liu*, J. B. Hamrick*, J. F. Fisac*, A. D. Dragan, J. K. Hedrick, S. S. Sastry, and T. L. Griffiths
International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), 2016.

The Pursuit-Evasion-Defense Differential Game in Dynamic Constrained Environments
J. F. Fisac and S. S. Sastry
Conference on Decision and Control (CDC), 2015.

Safe Platooning of Unmanned Aerial Vehicles via Reachability
M. Chen, Q. Hu, C. Mackin, J. F. Fisac, and C. J. Tomlin
Conference on Decision and Control (CDC), 2015.

Safe Sequential Path Planning of Multi-Vehicle Systems via Double-Obstacle Hamilton-Jacobi-Isaacs Variational Inequality
M. Chen, J. F. Fisac, S. S. Sastry, and C. J. Tomlin
European Control Conference (ECC), 2015.

Reach-Avoid Problems with Time-Varying Dynamics, Targets and Constraints
J. F. Fisac, M. Chen, C. J. Tomlin, and S. S. Sastry International Conference on Hybrid Systems: Computation and Control (HSCC), 2015.

Reachability-Based Safe Learning with Gaussian Processes
A. K. Akametalu, J. F. Fisac, J. H. Gillula, S. Kaynama, M. N. Zeilinger, and C. J. Tomlin
Conference on Decision and Control (CDC), 2014.

General-Audience Articles

Automating Us – the entanglement of people and machines
D. Aranki, R. Dobbe, J. F. Fisac, and C. Wu
Berkeley Science Review, 2015
A look into the ethical and social implications of automation technologies.



UC Berkeley EE 106A/206A - Introduction to Robotics - Fall 2015 - 67 students
Students learn the fundamentals of robotic motion and manipulation: the theoretical part of the course covers robot kinematics, perception, localization, planning, and control; the lab component introduces students to the Robot Operating System (ROS) framework. Final projects ranged from a heat-seeking mobile robot to a robot arm that could track and catch other robots.
UC Berkeley CS 188 - Introduction to Artificial Intelligence - Spring 2018 - 680 students
Students learn the basic building blocks of decision-making in intelligent systems: the course covers search algorithms, Markov decision processes (MDPs), dynamic programming, reinforcement learning, and Bayesian networks.

Research Mentorship

Ted Xiao
UC Berkeley EECS undergraduate, 2015. Stayed on for a M.S. and went on to work at Google Brain.

Elis Stefansson
Visiting Master's student, 2016. Now a PhD student at KTH, Sweden.

Steven Wang
UC Berkeley EECS undergraduate, 2017–18. Now a Research Engineer at the Center for Human-Compatible Artificial Intelligence.

Eli Bronstein
UC Berkeley EECS undergraduate, 2017–18. Now a Research Engineer at Symbio Robotics.

Neil Lugovoy
UC Berkeley Physics and Computer Science undergraduate, 2018–19. Continuing onto EECS Master's Program at Berkeley.

Organized Workshops and Seminars

Robust Autonomy: Safe Robot Learning and Control in Uncertain Environments - RSS workshop, 2019
This workshop, held during the 2019 conference on Robotics: Science and Systems, provided a forum for researchers and practitioners in the areas of robotic perception and control to discuss challenges and promising strategies for the deployment of autonomous systems in uncertain real-world environments, with a focus on theoretical and algorithmic frameworks for safety.

DREAM/CPAR Seminar - 2017–2019
This seminar series has been well established over the past few years, and is a joint effort between the Design of Robotics and Embedded systems, Analysis, and Modeling Seminar and the CITRIS People and Robots Initiative.

Perspectives on Analysis and Design of Human-Centered Robotics - IROS workshop, 2016
This workshop, held at the 2018 International Conference on Intelligent Robots and Systems, brought together researchers from industry and academia to discuss key tools and challenges for introducing autonomous robots into the human domain. Participants spanned the areas of human modeling, human-robot interaction, and robot design and control.


BAIR AI4ALL Camp - 2017
I was part of the small team of students and faculty who ran the first BAIR AI4ALL camp, a summer program for 9th and 10th grade students from underrepresented communities in the Bay Area. We taught students about artificial intelligence, guided them as they experimented with their first computer programs, and talked to them about how automation can be used to help people.