University of Waterloo
Bridging the Sim2Real gap in autonomous vehicle testing
Developing data-driven methods for enabling reliable simulation-based testing of autonomous vehicle software and training learning-based autonomy.
Yash Vardhan Pant
University of Waterloo
Assistant Professor
Ongoing Research
- Adversarial reinforcement learning for augmenting AV simulators
- Specification-guided corner case detection for defining ODD
- Motion planning w/ complex objectives in uncertain environments
Selected Publications
- Formal Scenario-Based Testing of Autonomous Vehicles: From Simulation to the Real World, IEEE ITSC, 2020
- Addressing the IEEE AV test challenge with Scenic and VerifAI, IEEE AITest, 2021
- Counterexample-Guided Synthesis of Perception Models and Control, ACC, 2021
- Co-design of Control and Planning for Multi-rotor UAVs with Signal Temporal Logic Specifications, ACC, 2021