Robotic Route Generation Using Annotated Maps and Scan Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for generating routes for robots are often fixed and redundant, leading to inefficiencies as robots may re-clean areas that have already been cleaned by others, wasting time and resources.
Innovation Solution
A system and method for automatic route generation in robotic devices, which involves a server communicating with robots and user devices to create annotated maps, allowing for the definition of functional constraints and preferred scanning segments, enabling robots to navigate and scan specific areas while avoiding undesired ones.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If fixed and redundant route generation methods are used, then route coverage is ensured, but time efficiency deteriorates due to re-cleaning already cleaned areas
Solution Approach 1:
The system transitions from fixed, static route generation to dynamic route generation that adapts in real-time. The autonomous vehicle receives live location data from other vehicles and dynamically adjusts its route to avoid areas that have already been cleaned, transforming the route planning from a rigid pre-defined path to a flexible, adaptive process that responds to changing environmental conditions.
Solution Approach 2:
The system implements feedback mechanisms where location data from autonomous vehicles is continuously shared and utilized for route planning. The server receives location information from vehicles and feeds this information back into the route generation process, allowing subsequent route planning decisions to be informed by actual vehicle positions and cleaning progress, thereby preventing redundant operations.
2Reliability
If traditional route training methods are used, then route reliability is ensured, but training time increases significantly
Solution Approach 1:
The system performs preliminary route planning on a server before the autonomous vehicle executes the route. Instead of requiring the vehicle to learn and train routes through repeated trial-and-error operations, the server pre-calculates optimal routes based on environment data, and the vehicle simply needs to follow these pre-planned instructions, dramatically reducing training time while maintaining reliability.
Solution Approach 2:
The server acts as an intermediary between environment mapping and route execution. Rather than the autonomous vehicle directly learning routes from environment data through time-consuming training, the server processes the environment map and generates route instructions as an intermediate step, which the vehicle then follows, eliminating the need for extensive vehicle-side training.
3Adaptability or versatility
If generic route generation is used, then system simplicity is maintained, but task specificity deteriorates as unique scanning requirements cannot be met
Solution Approach 1:
The system applies local quality by allowing different regions of the environment map to have different properties and requirements. Annotations can specify that certain areas require scanning while others do not, and routes are generated with specific scanning segments tailored to local task requirements. This enables the system to handle diverse, location-specific scanning needs without requiring a completely different approach for each area.
Solution Approach 2:
The server-based route generation system serves multiple functions: it generates routes, performs annotations, identifies scanning segments, and coordinates multiple vehicles. This universal platform handles various task types (cleaning, scanning, monitoring) and can adapt to different environmental configurations, making the system versatile while maintaining a unified architecture that doesn't require separate specialized systems for each function.
Data Source
AI summary
Systems and methods for automatic route generation for robotic devices are disclosed herein. According to at least one non-limiting exemplary embodiment, a user may generate a new route for a robot to execute by selecting one or more departments or objects to be scanned using an annotated computer readable map.