A Hybrid Graph Neural Network–Deep Reinforcement Learning Framework for Robust Multi-Modal Sensor Fusion and Real-Time Dynamic Obstacle Detection in Autonomous Environments

Abstract

The research presents an intelligent framework for autonomous systems that performs multimodal sensor fusion to improve the identification of obstacles operating in dynamic scenarios.The proposed solution allows robots to handle complex and messy situations.The system leverages graph neural networks to capture spatial and relational dependencies graphically and incorporates contextual understanding of environmental features in its operation.The system incorporates environmental interactive adaptive decisionmaking and deep reinforcement learning as part of the framework to ensure resiliency in variable environmental conditions.The safety and responsiveness of the obstacle avoidance system are within the specifications of the advanced learning frameworks developed for the detection systems in real-world applications in robotics and facilitate increased autonomy in robotic systems..