20240029012. NODAL GRAPH AND REINFORCEMENT-LEARNING MODEL BASED SYSTEMS AND METHODS FOR MANAGING MOVING AGENTS simplified abstract (TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.)

NODAL GRAPH AND REINFORCEMENT-LEARNING MODEL BASED SYSTEMS AND METHODS FOR MANAGING MOVING AGENTS

Organization Name

TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.

Inventor(s)

Rohit Gupta of Santa Clara CA (US)

Akila Ganlath of Mountain View CA (US)

Nejib Ammar of San Jose CA (US)

Prashant Tiwari of Santa Clara CA (US)

NODAL GRAPH AND REINFORCEMENT-LEARNING MODEL BASED SYSTEMS AND METHODS FOR MANAGING MOVING AGENTS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240029012 titled 'NODAL GRAPH AND REINFORCEMENT-LEARNING MODEL BASED SYSTEMS AND METHODS FOR MANAGING MOVING AGENTS

Simplified Explanation

The patent application describes a method for managing moving agents, such as vehicles or robots, within a specific area. The method involves the following steps:

• Identifying goods agents, moving agents, and a plurality of requests within a predetermined area.
• Generating a nodal graph that includes the moving agents, requests, and goods as vertices, and the edges define the relationships between two vertices.
• Obtaining actions for the moving agents by inputting the nodal graph into a reinforcement-learning based graphical neural network model stored in the moving agents.
• The reinforcement-learning based graphical neural network outputs the action for the moving agent in response to receiving the nodal graph.
• Instructing the moving agents to operate based on the actions to satisfy at least one of the plurality of requests.

Potential applications of this technology:

• Logistics and supply chain management: The method can be used to efficiently manage the movement of goods agents, such as delivery trucks or drones, to fulfill customer requests or optimize delivery routes.
• Traffic management: The method can help optimize the movement of moving agents, such as autonomous vehicles, to reduce congestion and improve traffic flow.
• Warehouse management: The method can be applied to coordinate the movement of robots or automated guided vehicles (AGVs) within a warehouse to optimize order fulfillment and inventory management.

Problems solved by this technology:

• Coordination and optimization: The method provides a systematic approach to manage the movement of multiple agents in a given area, ensuring efficient allocation of resources and minimizing conflicts or inefficiencies.
• Decision-making: By utilizing a reinforcement-learning based graphical neural network model, the method enables the moving agents to make intelligent decisions based on the current state of the system and the desired outcomes.
• Adaptability: The method can adapt to changing conditions or requests by continuously updating the nodal graph and obtaining new actions from the neural network model.

Benefits of this technology:

• Improved efficiency: By optimizing the movement of moving agents, the method can reduce travel time, increase productivity, and enhance overall operational efficiency.
• Cost savings: The method can help minimize fuel consumption, reduce maintenance costs, and optimize resource allocation, leading to potential cost savings for businesses.
• Enhanced customer satisfaction: By ensuring timely and accurate fulfillment of requests, the method can improve customer satisfaction and loyalty.

Original Abstract Submitted

a method for managing moving agents is provided. the method comprises identifying goods agents, moving agents, and a plurality of requests within a predetermined area, generating a nodal graph including the moving agents, requests, and goods as vertices and edges defining relations between two vertices, obtaining actions for the moving agents by inputting the nodal graph to a reinforcement-learning based graphical neural network model stored in the moving agents, the reinforcement-learning based graphical neural network outputs the action for the moving agent in response to receiving the nodal graph, and instructing the moving agents to operate based on the actions to satisfy at least one of the plurality of requests.