Home Teaching Service

Andrea Bajcsy
abajcsy [at] berkeley [dot] edu

I am a final-year Ph.D. candidate at University of California, Berkeley working with Anca Dragan and Claire Tomlin. I am broadly interested in the intersection of robotics, control theory, machine learning, and human-robot interaction.

Much of my research focuses on combining data-driven human models and control theoretic-tools to develop robust human motion predictors and safe motion planners for robots operating in close physical proximity to people. A large component of my work involves designing robots which reason about the validity of their models online in light of new data.

At Berkeley, I get to collaborate with some amazing people in the InterACT Lab and the Hybrid Systems Lab. I have been graciously supported by the NSF Graduate Research Fellowship.

email   |   cv   |   google scholar   |   github

profile photo

  • [Aug 2020]

    New paper on arXiv! In this work we advocate for the use of Hamilton Jacobi (HJ) reachability as a unifying mathematical framework for comparing existing safety concepts used throughout industry and academia, and propose ways to expand its modeling premises in a data-driven fashion.
  • [April 2021]

    I'm excited to join NVIDIA for an internship in the Autonomous Driving Research group led by Marco Pavone.
  • [Mar 2021]

    Our paper on analyzing human models that adapt online was accepted to ICRA 2021!
  • [Feb 2021]

    I gave a talk at University of Pennsylvania on analyzing human models that adapt online.
  • [Dec 2020]

    I gave a talk on safe robots which learn from (and about) humans at the University of Chicago Laboratory School for the middle and high-school robotics club.
  • [Dec 2020]

    I gave a talk at ETH Zurich on introspective human motion prediction for safe robot autonomy.


For the most up-to-date list of publications, please see google scholar.
* indicates equal contribution and co-authorship.


Towards the Unification and Data-Driven Synthesis of Autonomous Vehicle Safety Concepts
A. Bajcsy*, K. Leung*, E. Schmerling, M. Pavone

Physical Interaction as Communication: Learning Robot Objectives Online from Human Corrections
D.P. Losey, A. Bajcsy, M.K. O'Malley, A.D. Dragan


Analyzing Human Models that Adapt Online
A. Bajcsy, A. Siththaranjan, C.J. Tomlin, A.D. Dragan
International Conference on Robotics and Automation (ICRA), 2021
paper   |   code

Efficient Dynamics Estimation with Adaptive Model Sets
E. Ratner, A. Bajcsy, C.J. Tomlin, A.D. Dragan
IEEE Robotics and Automation Letters (RA-L), 2021


A Robust Control Framework for Human Motion Prediction
A. Bajcsy, S. Bansal, E. Ratner, C.J. Tomlin A.D. Dragan
IEEE Robotics and Automation Letters (RA-L), 2020

Quantifying hypothesis space misspecificationin learning from human-robot demonstrations and physical corrections
A. Bobu, A. Bajcsy, J.F. Fisac, S. Deglurkar, A.D. Dragan
IEEE Transactions on Robotics (T-RO), 2020

(Honorable Mention for the 2020 IEEE T-RO Best Paper Award)

paper   |   code

A Hamilton-Jacobi Reachability-Based Framework for Predicting and Analyzing Human Motion for Safe Planning
S. Bansal*, A. Bajcsy*, E. Ratner*, A.D. Dragan, C.J. Tomlin
International Conference on Robotics and Automation (ICRA), 2020
paper   |   video


Confidence-aware motion prediction for real-time collision avoidance
D. Fridovich-Keil*, A. Bajcsy*, J.F. Fisac, S.L. Herbert, S. Wang, A.D. Dragan, C.J. Tomlin
International Journal of Robotics Research (IJRR), 2019

An Efficient Reachability-Based Framework for Provably Safe Autonomous Navigation in Unknown Environments
A. Bajcsy*, S. Bansal*, E. Bronstein, V. Tolani, C.J. Tomlin
Conference on Decision and Control (CDC), 2019
paper   |   video   |   project website

A Scalable Framework For Real-Time Multi-Robot, Multi-Human Collision Avoidance
A. Bajcsy*, S.L. Herbert*, D. Fridovich-Keil, J.F. Fisac, S. Deglurkar, A.D. Dragan, C.J. Tomlin
International Conference on Robotics and Automation (ICRA), 2019
paper   |   video   |   code


Learning under Misspecified Objective Spaces
A. Bobu, A. Bajcsy, J.F. Fisac, A.D. Dragan
Conference on Robot Learning (CORL), 2018

(invited to special issue)

paper   |   video   |   code

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, A.D. Dragan
Robotics: Science and Systems (RSS), 2018

(invited to special issue)

paper   |   video   |   code

Learning from Physical Human Corrections, One Feature at a Time
A. Bajcsy , D.P. Losey, M.K. O'Malley, A.D. Dragan
International Confernece on Human-Robot Interaction (HRI), 2018
paper   |   video


Learning Robot Objectives from Physical Human Robot Interaction
A. Bajcsy* , D.P. Losey*, M.K. O'Malley, A.D. Dragan
Conference on Robot Learning (CoRL), 2017

(oral, acceptance rate 10%)

paper   |   talk   |   blog   |   video

A User-Centered Design and Analysis of an Electrostatic Haptic Touchscreen System for Students with Visual Impairments
A. Bateman, O. Zhao, A. Bajcsy, M. Jennings, B. Toth, A. Cohen, E. Horton, A. Khattar, R. Kuo, F. Lee, M.K. Lim, L. Migasiuk, R. Renganathan, A. Zhang, M.A. Oliveira
International Journal of Human-Computer Studies, 2017


A review of principles in design and usability testing of tactile technology for individuals with visual impairments
E.L. Horton, R. Renganathan, B.N. Toth, A.J. Cohen, A.V. Bajcsy, A. Bateman, M.C. Jennings, A. Khattar, R.S. Kuo, F.A. Lee, M.K. Lim, L.W, Migasiuk, A. Zhang, O.K. Zhao, M.A. Oliveira
Assistive Technology, 2016


Systematic measurement of marginal mark types on voting ballots
A. Bajcsy, Y.S. Li-Baboud, M. Brady
NIST IR 8069, 2015


Depicting Web images for the blind and visually impaired
A. Bajcsy, Y.S. Li-Baboud, M. Brady
SPIE Newsroom, 2013

website adapted from here