This inventor holds 1 USPTO granted patent and 1 published patent application. Top assignee: Mitsubishi Electric Research Laboratories, Inc.. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2026
Title: Farshud Sorourifar and Generative AI-Based Stochastic Control
Introduction
Farshud Sorourifar is an inventor associated with Columbus, Ohio, and Mitsubishi Electric Research Laboratories, Inc. His patent work explores how generative AI can help predictive controllers manage uncertainty in mechanical systems.
Latest Patents
Sorourifar is named on 1 patent, titled “Stochastic Control Subject to Generative AI-Based Disturbance.” The invention describes a predictive controller that uses a deep generative decoder model to estimate a probability distribution for disturbances based on partial observations. It samples from that distribution, decodes the sample into predicted disturbance values over a time horizon, and uses the probabilities of those predictions to determine control commands for the mechanical system.
Career Highlights
The patent reflects work at the intersection of stochastic control, predictive control, and deep generative modeling. By incorporating uncertainty into its predictions, the described approach aims to help a mechanical system adjust its operation in response to disturbances.
Collaborations
Ye Wang is identified as a coworker associated with Sorourifar’s work. The patent also connects Sorourifar’s inventive activity with Mitsubishi Electric Research Laboratories, Inc.
Conclusion
Farshud Sorourifar’s patent presents a generative AI-based approach to predictive control that accounts for uncertain disturbances when determining how a mechanical system should operate.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile