AGV Route Network Discovery from Human Actor Location Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated guided vehicles (AGVs) in warehouses often calculate optimal paths that may not align with human or designated actor routes, leading to inefficiencies, safety concerns, and the need for manual programming of lane information and traveling rules, which is error-prone and time-consuming.
Innovation Solution
A computing device receives location data from designated actors to determine a route network of paths, selecting a path for AGVs based on frequency information and providing instructions for navigation, allowing AGVs to follow or avoid designated actor routes for improved interaction and safety.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If AGVs calculate optimal paths using traditional algorithms, then path efficiency is improved, but alignment with human actor routes deteriorates
Solution Approach 1:
The system collects location data from human actors and uses it to generate route network information that feeds back into AGV path planning. This feedback loop ensures AGVs adapt to actual human movement patterns while maintaining computational optimization, resolving the contradiction between algorithmic efficiency and human route alignment.
Solution Approach 2:
The system pre-generates route network information from historical human actor location data before AGVs need to navigate. This preliminary action creates a database of preferred human routes that AGVs can query during operation, allowing path optimization to occur while respecting established human patterns without real-time conflict.
2Measurement precision
If manual programming of lane information is performed, then route accuracy is improved, but time consumption and error rate worsen
Solution Approach 1:
The system automatically generates route network information by processing location data from human actors without requiring manual programming. The AGV system serves itself by extracting routing preferences from observed human behavior, eliminating the need for time-consuming manual lane information entry while maintaining high route accuracy through data-driven path selection.
Solution Approach 2:
The system replaces manual mechanical programming of route information with an automated computational process. Instead of operators manually inputting lane data, the system uses algorithms to process location data and generate route networks automatically, substituting human labor with automated information processing while improving both accuracy and speed.
3Reliability
If AGVs follow established human routes, then safety and harmony improve, but path optimization flexibility deteriorates
Solution Approach 1:
The system dynamically adjusts path planning by combining static route network information (established human routes) with real-time optimization needs. AGVs can adapt their paths based on current conditions while respecting preferred human corridors, creating a dynamic balance between safety through route following and flexibility through situational optimization.
Solution Approach 2:
The system applies different routing strategies in different contexts: in areas with established human routes, AGVs follow those patterns for safety; in areas without human traffic or during special conditions, AGVs can optimize paths freely. This local differentiation maintains safety where needed while preserving optimization flexibility where appropriate.
Data Source
AI summary
Systems and methods are provided for automated route discovery. A computing device can receive location data for designated actor(s) of a plurality of actors operating within an environment. The plurality of actors can also include a robotic device. The computing device can determine a route network of paths taken by the designated actor(s) within the environment, where the route network includes information about frequencies of paths taken by the designated actor(s) based on the location data. The computing device can receive a starting location and a destination location for the robotic device. The computing device can select a selected path from the starting location to the destination location based on the route network taken by the designated actor(s). The computing device can provide an instruction to the robotic device to use the selected path to travel from the starting location to the destination location.