Technical Description
The invention is a brain-inspired computational model using a Hierarchical Reinforcement Learning (HRL) framework for autonomous spatial navigation. By configuring the prefrontal cortex at a higher organizational level with the Basal Ganglia (BG) and Hippocampus (HC) at the lower level, the model maps neural interactions to provide real-time, seamless path planning across shifting environments.
Problems Addressed
- Exponential Runtime Growth and Poor Scaling
- Inability of Oversimplified Conventional ANNs
- Failure of Prior Brain-Inspired Models
- Structural Limitations in Managing Context Shifts
Tech Features
- Hierarchical Reinforcement Learning Engine
- Two-Level Hierarchical Navigation Module
- Bi-Directional Neuro-Anatomical Mapping
- Striatal-Hippocampal Spatial
- Dopaminergic Value Circuitry
Target Audience
- Autonomous Vehicle & Self-Driving Engineers
- Commercial Drone & UAV Designers
- Robotics & Underwater Navigation Developers
Tech ID: P02-2131 TRL 3 Patent Status: Granted Available For Exclusive and Non-exclusive License
