This inventor holds 1 USPTO granted patent. Top assignee: Huawei Technologies Co., Ltd.. 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: Mohsen Rohani and Graph-Based Pedestrian Action Prediction
Introduction
Mohsen Rohani is an inventor based in Thornhill, Canada. His work includes a patented approach to predicting pedestrian actions in autonomous driving systems. The available information identifies 1 patent associated with him.
Latest Patents
Rohani’s patent, “Method and System for Graph Neural Network Based Pedestrian Action Prediction in Autonomous Driving Systems,” describes a method for analyzing traffic scenes around an autonomous vehicle. It models road users across observed frames as a spatiotemporal graph, groups them into categories, and provides the graph to a trained graph convolutional neural network. The system predicts whether a pedestrian will cross the road, supporting an improved understanding of the observed scene.
Career Highlights
Rohani is associated with Huawei Technologies Co., Ltd. His patented work focuses on applying graph neural networks to pedestrian-action prediction, a task relevant to autonomous vehicle perception and decision-making.
Collaborations
The provided information names Saber Malekmohammadi and Tiffany Yee Kay Yau as Rohani’s coworkers. Their inclusion indicates professional connections, but no specific roles or contributions to the patent are provided.
Conclusion
Mohsen Rohani’s patent applies spatiotemporal graph modeling and neural-network analysis to help autonomous driving systems anticipate pedestrian behavior.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile