Gianluca Piquet

Papers

Total Citations

H-Index

About

Gianluca Piquet is a rising researcher at the intersection of formal methods and autonomous robotics, with a primary focus on learning interpretable temporal logic specifications from system behaviors. His most cited work, "Learning Linear Temporal Properties for Autonomous Robotic Systems" (2023, 6 citations), tackles the critical problem of passive learning of linear temporal logic (LTL) formulae—finding the shortest, most explanatory formula that distinguishes two sets of execution traces. This contribution is foundational for making robotic decision-making more transparent and verifiable, enabling engineers to automatically extract human-interpretable rules from observed behaviors. Piquet’s approach, which implements an optimized exhaustive search algorithm, addresses a key bottleneck in formal verification: bridging the gap between complex system dynamics and human-understandable specifications. While still early in his career, his work has already attracted attention from the robotics and formal methods communities, positioning him as a promising voice in explainable autonomy. His research holds significant implications for safety-critical systems, where understanding why an autonomous agent acts as it does is as important as the action itself.