Max Robotics — Global Service Robot Directory + US Certification

About

Aniruddh G. Puranic is a robotics and artificial intelligence researcher whose work sits at the intersection of robot learning, formal methods, and safe autonomous systems. His research focuses primarily on Learning from Demonstrations (LfD), a paradigm that enables robots to acquire complex control policies through reinforcement learning without requiring manually engineered reward functions. A central thread running through his work is the application of Signal Temporal Logic (STL) as a principled framework for extracting safe, robust, and interpretable robot behaviors from demonstrated data. Puranic's most influential contribution, "Learning From Demonstrations Using Signal Temporal Logic in Stochastic and Continuous Domains" (2021), has accumulated 26 citations and addresses longstanding challenges in developing robotic systems that can reason formally about safety constraints. His subsequent work on performance graphs further advances the field by improving how demonstrated behaviors are understood and evaluated, reducing the risk of robots inferring incorrect or unsafe reward functions. Across his publications, Puranic consistently tackles the critical problem of imperfect demonstrations and safety assurance in autonomous systems. His growing citation record reflects increasing community recognition of formal logic-based approaches as a promising direction for trustworthy robot learning.