Warehouse Transport Robot Navigation Using Environment and Capability Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automation solutions for intralogistics operations, such as driverless transport systems, require high investment costs, significant space, and inflexible pre-defined routes, limiting their adoption in dynamic warehouse environments where flexibility is needed.
Innovation Solution
A transport robot system that includes a communication interface for receiving and sending environment and capability models, allowing for fully automated, semi-automated, or manual operation. The environment model defines key points in the warehouse as a topological map, while the capability model provides movement sequence data for automated navigation and task execution, enabling flexible route planning and adaptation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If driverless transport systems (FTS) are used for automated transport, then automation level is improved, but flexibility deteriorates due to pre-defined routes requiring re-planning when layout changes occur
Solution Approach 1:
The system dynamically adapts transport routes by learning from human operator demonstrations. When layout changes occur, the system automatically updates its navigation model by observing new paths taken by human operators, transforming the static pre-defined route system into a dynamic learning system that adapts to environmental changes without manual re-planning
Solution Approach 2:
The system performs self-learning by automatically acquiring navigation knowledge through observation of human operators. The robot independently updates its internal model of warehouse layouts and transport routes by processing sensor data from demonstrated paths, eliminating the need for external experts to manually re-plan routes when configurations change
2Productivity
If current automation solutions are introduced, then productivity is improved, but investment costs increase significantly
Solution Approach 1:
Instead of using complex pre-programmed automation systems, the invention copies human operator knowledge and behavior patterns. The robot learns by observing and replicating human transport routes and operations, creating a simplified automation solution that achieves high productivity without the high investment costs associated with traditional FTS infrastructure
Solution Approach 2:
The system changes the fundamental parameter of knowledge representation from static pre-defined routes to dynamic learned behaviors. By transforming the automation approach from rigid programming to flexible learning, the system achieves high productivity with reduced complexity and lower investment requirements
3Extent of automation
If driverless transport systems are deployed, then automation is achieved, but space requirements increase due to infrastructure needs
Solution Approach 1:
The invention extracts the essential automation function from the complex FTS infrastructure. By removing unnecessary infrastructure components and retaining only the core navigation and transport capabilities through learned behavior, the system achieves automation with significantly reduced space requirements
4Adaptability or versatility
If FTS routes are re-planned when layout adjustments are made, then adaptability is improved, but time is lost due to re-planning requirements
Solution Approach 1:
The system performs automatic self-adaptation by continuously learning from human operator demonstrations. When layout changes occur, the robot independently updates its navigation model by observing new paths, eliminating the time-consuming manual re-planning process while maintaining high route adaptability
Data Source
AI summary
A transport robot is used to carry out transport orders for transport of goods in a warehouse with a plurality of transport robots. The transport robot includes a communication interface configured to receive an environment model of the warehouse and a capability model of the plurality of transport robots. The environment model defines a plurality of key points of the warehouse and, for each key point, at least one neighboring key point. The capability model defines, for each of the key points of the environment model, movement sequence data for an automated movement to the at least one neighboring key point. The transport robot includes a control unit configured to carry out a transport order from a starting key point to a destination key point of the plurality of key points to automatically control movement of the transport robot based on the environment model and the capability model.