Apurva Badithela

Logo

PhD Student at Caltech

I am a final year PhD student in Control and Dynamical Systems at California Institute of Technology. I am advised by Professor Richard M. Murray. My research interests are in formal methods, robotics, verification and validation, and testing of autonomous cyber-physical systems.

My PhD research is on using formal methods for Test and Evaluation (T&E), and Verification and Validation (V&V) of autonomous systems. In particular, my dissertation research is focused on: 1) Reactive test synthesis from temporal logic specifications, and 2) Validating perception performance with respect to system-level temporal logic specifications.

Before Caltech, I earned my Bachelors degree in Aerospace Engineering and Mechanics at the University of Minnesota, Twin-Cities in 2018. As an undergraduate, I was fortunate to conduct research with Professor Peter Seiler, Professor Neera Jain and Professor Austin Nash, and Professor Ufuk Topcu and Dr. Ivan Papusha.

I also spent the summer of 2021 at Motional as an Autonomy Research intern in the Behavior Prediction and Planning Group under the supervision of Dr. Eric Wolff and Dr. Tung Phan-Minh. At Motional, I worked on Counter-example Guided Repair of Learning-based Planners using Optimization and Bayesian inference techniques.


CV, Google Scholar, LinkedIn, Github, Email: apurva@caltech.edu


Talks


Preprints

Pacti: Scaling Assume-Guarantee Reasoning for System Analysis and Design
Inigo Incer, Apurva Badithela, Josefine Graebener, Piergiuseppe Mallozzi, Ayush Pandey, Sheng-Jung Yu, Albert Beneveniste, Benoit Caillud, Richard M. Murray, Alberto Sangiovanni-Vincentelli, and Sanjit Seshia
Submitted to ACM Transactions on Cyber-Physical Systems (T-CPS)
[preprint, tool]


Publications

Evaluation Metrics of Object Detection for Quantitative System-Level Analysis of Autonomous Systems
Apurva Badithela, Tichakorn Wongpiromsarn, Richard M. Murray
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023
[paper]

Reasoning over Test Specifications using Assume-Guarantee Contracts
Apurva Badithela*, Josefine B. Graebener*, Inigo Incer*, and Richard M. Murray
Proceedings of the 15th NASA Formal Methods (NFM), 2023, pp 278-294.
[paper]

Synthesizing Reactive Test Environments for Autonomous Systems: Testing Reach-Avoid Specifications with Multi-Commodity Flows
Apurva Badithela*, Josefine B. Graebener*, Wyatt Ubellacker, Eric V. Mazumdar, Aaron D. Ames, Richard M. Murray
IEEE International Conference Robotics and Automation (ICRA), 2023
[paper, code]

Towards Better Test Coverage: Merging Unit Tests for Autonomous Systems
Josefine B. Graebener*, Apurva Badithela*, and Richard M. Murray
Proceedings of the 14th NASA Formal Methods (NFM), 2022, pp 133-155.
[paper, code]

Leveraging Classification Metrics for Quantitative System-level Analysis of Temporal Logic Specifications
Apurva Badithela, Tichakorn Wongpiromsarn, and Richard M. Murray
60th IEEE Conference on Decision and Control, 2021
[paper, code]

Analysis of the Heavy-ball Algorithm using Integral Quadratic Constraints
Apurva Badithela and Peter J. Seiler
American Control Conference, 2019
[paper]

Dynamic Modeling of a Sensible Thermal Energy Storage Tank with an Immersed Coil Heat Exchanger under Three Operation Modes
Austin Nash, Apurva Badithela, and Neera Jain
Journal of Applied Energy, 2017
[paper]

Workshop Papers

Minimally Constrained Testing for Autonomy with Temporal Logic Specifications
Apurva Badithela*, Josefine Graebener*, and Richard M. Murray
Workshop on Envisioning an Infrastructure for Multi-Robot and Collaborative Autonomy Testing and Evaluation
Robotics: Science and Systems (R:SS), 2022
[paper]

*: Equal authorship.