Mobile Robot Collection Routing for Loaned Device Returns
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In device lending systems, inventory shortages occur due to prolonged stay times of lending devices after use, as return transportation is determined by staff at the lending destination, leading to inefficiencies and potential device deterioration.
Innovation Solution
A transport system utilizing a learned model that predicts the end time of device use, determining an efficient collection route for a mobile robot to minimize stay time by inputting collection record and route data, optimizing routes based on past data to reduce time, distance, and power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If return transportation is determined by staff at the lending destination, then flexibility in handling emergency situations is improved, but stay time of devices is prolonged
Solution Approach 1:
The system performs preliminary actions by predicting the end time of device use and determining collection routes in advance. The management device calculates optimal collection routes and assigns mobile robots before devices are actually returned, eliminating waiting time while maintaining the ability to handle emergencies through predictive scheduling
Solution Approach 2:
The system uses feedback from collection record data and collection route data to continuously improve route determination. By analyzing past collection patterns and device return behaviors, the system refines its predictions and route optimization, balancing emergency response flexibility with efficient device retrieval
2Extent of automation
If mobile robot collects returned devices, then automation of collection is improved, but device deterioration and power consumption increase due to prolonged stay time
Solution Approach 1:
The management device determines collection routes and assigns mobile robots in advance based on predicted end times. This preliminary action ensures that mobile robots are ready to collect devices immediately upon return, minimizing stay time while maintaining high automation levels
Solution Approach 2:
The system dynamically adjusts collection routes and robot assignments based on real-time conditions and learned patterns. By making collection schedules flexible and adaptive rather than fixed, the system can respond to emergencies while maintaining efficient automated collection operations
3Ease of operation
If collection route is determined without considering past data, then simplicity of operation is maintained, but collection efficiency and power saving are reduced
Solution Approach 1:
The system performs self-service by automatically learning from past collection data and improving its own route determination without requiring manual intervention. The management device autonomously analyzes collection records and optimizes routes, maintaining operational simplicity while significantly improving collection efficiency
Solution Approach 2:
The patent replaces manual route planning with an automated machine learning system. Instead of staff manually determining collection routes, the system uses algorithms that learn from historical data to automatically optimize routes, substituting mechanical human decision-making with intelligent automated processing
Data Source
AI summary
The transportation system stores a learned model that is machine-learned so as to output a collection route that is collected by the mobile robot by inputting an end-of-use prediction result that is a result of predicting an end-of-use time of the device being lent, using learning data including collection result data indicating a collection result including a use end time at which the use of the device has ended and a collection completion time collected as a return product, and collection route data indicating a collection route collected by the mobile robot by using the device as a return product. The transport system inputs the end time prediction result to the learned model, acquires a collection route to be collected by the mobile robot using the equipment being lent as a returned item, and determines a mobile robot to be collected by the acquired collection route.