Max Robotics — Global Service Robot Directory + US Certification

About

Gilad Francis is a robotics researcher specializing in motion planning, autonomous exploration, and probabilistic methods for robot navigation. His work sits at the intersection of Bayesian inference, sampling-based planning, and occupancy mapping, addressing fundamental challenges in enabling robots to move safely and efficiently through complex environments. Francis's most significant contribution is his development of Bayesian local sampling strategies for motion planning, detailed in his most-cited work "Bayesian Local Sampling-Based Planning" (2020, 43 citations), which tackles a critical inefficiency in traditional global random sampling schemes by introducing smarter, locally-informed sampling distributions. This work meaningfully advances the field by improving planning efficiency in constrained and narrow-passage environments. Complementing this, his research on occupancy map building through Bayesian exploration (24 citations) introduced a holistic framework combining constrained Bayesian optimization with autonomous exploration, enabling robots to build maps while satisfying real-world motion and safety constraints. His earlier stochastic functional gradient approaches (17 citations) further bridged trajectory optimization and sampling-based planning within continuous occupancy maps. Across his body of work, Francis has accumulated over 90 citations, reflecting growing recognition of his contributions. His research is particularly relevant to students and practitioners working on autonomous mobile robotics, where safe, efficient navigation remains an open and consequential challenge.