Papers
11
Total Citations
48
H-Index
4
About
Pushpak Jagtap is an emerging researcher whose work sits at the compelling intersection of control theory, formal methods, and autonomous systems. His research primarily focuses on safe controller synthesis, Control Barrier Functions (CBFs), reinforcement learning, and multi-agent systems — areas critical to ensuring that autonomous robots and vehicles behave safely and reliably in complex, real-world environments. Among his most notable contributions is pioneering work on Collision Cone Control Barrier Functions, a unified framework for collision avoidance in both ground and aerial unmanned vehicles, validated experimentally on UGVs and accumulating significant early attention with multiple papers garnering citations within their debut year. His spatiotemporal tubes approach offers elegant, closed-form control strategies for systems with unknown dynamics, addressing prescribed-time reach-avoid-stay specifications — a challenge of considerable practical importance in time-critical robotics applications. Jagtap has also advanced the frontier of formal controller synthesis against omega-regular specifications, enabling robots to satisfy complex, long-horizon behavioral requirements. His work on barrier function-inspired reward shaping for reinforcement learning bridges formal safety guarantees with data-driven methods, tackling scalability challenges that have long constrained real-world RL deployment. With over 45 cumulative citations across recent publications, Jagtap is rapidly establishing himself as a thoughtful and technically rigorous voice in safe autonomy research.
Research Focus
Key Achievements
Top Papers
- 1Barrier Functions Inspired Reward Shaping for Reinforcement Learning10 citations · 2024
- 2
- 3
- 4
- 5A Collision Cone Approach for Control Barrier Functions4 citations · 2024
- 6
- 7Autonomous Exploration Using Ground Robots with Safety Guarantees3 citations · 2023
- 8
- 9
- 10