Max Robotics — Global Service Robot Directory + US Certification

About

Ashish Tiwari is a researcher whose work sits at the intersection of robotics, machine learning, and formal verification, with a particular focus on making autonomous systems safer and more reliable. His most cited contribution, "Learning Task Specifications from Demonstrations" (2017, 42 citations), advances the field of learning from demonstrations by providing formal guarantees on learned sub-task specifications — a critical step forward for robotics applications where reliability is non-negotiable. His SOTER framework, developed across multiple publications (2018–2019), addresses the growing challenge of certifying autonomous robotic systems that rely on complex, third-party machine learning components, introducing runtime assurance as a practical programming paradigm. Tiwari has also pioneered the concept of "Trusted Machine Learning" for Markov Decision Processes, proposing principled methods to repair models, data, and reward functions to ensure safety in mission-critical settings. His more recent work extends into multi-agent coordination and IoT resource allocation, reflecting a broadening research agenda. Across his portfolio, Tiwari consistently bridges theoretical rigor with real-world applicability, making his work especially valuable for researchers building dependable intelligent systems.