Abstract:
Automation in warehouse material handling increases efficiency, reduces costs, and improves safety. The traditional method of manual handling is slow, labor-intensive, and error-prone. In this thesis, we discuss an Autonomous Mobile Transport Robot (AMR) designed for work in dynamic warehouse environments, running on real-time mapping, path planning with AI, and obstacle avoidance. That which makes the Activity Map Robot autonomous is its ability to use SLAM for navigation, which is possible with LiDAR, ultrasonic sensors, cameras. Having a shock-absorbing chassis, it boasts adaptive load balancing and real-time speed control, which further promotes stability and safety. The reinforcement learning technique is employed, as well as neural networks capable of movement in unstructured environments, PID controllers, and efcient battery management systems, in the optimization of movement for the AMR, contrary to the typical static robots. The AMR’s modular architecture guarantees flexible payload handling and grit for attachments like robotic arms, conveyor modules, or forklifts. IoT and cloud-based fleet management facilitate remote monitoring, predictive maintenance, and operational analytics. Reducing dependence on human labor and automating repetitive tasks enhances AMR productivity while minimizing workplace accidents. Synthesis of AI-driven enhancements over ”An Autonomous Robotic System for Load Transportation” needs comes in this research. Simulations and real-time trials validate the effectiveness of the implementation, in doing so, makes amendments regarding accuracy, stability, and reliability. The work is intended for warehouse automation, thereby producing an industrial logistics solution that is scalable and cost-effective.
