Autonomous Delivery Routing Across Indoor-Outdoor Path Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional path modeling methods are ineffective in environments with mixed transportation networks and fail to consider vehicle-specific attributes, such as dimensions and operational capacities, leading to inefficient route selection and inability to adapt to changes in infrastructure.
Innovation Solution
Customized navigation maps are generated for autonomous vehicles, incorporating geolocation data, infrastructure features, and vehicle attributes, allowing for real-time updates and optimal route selection both indoors and outdoors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional path modeling methods are used, then route prediction is simple and fast, but the methods fail to consider vehicle-specific attributes and cannot adapt to mixed transportation networks including indoor environments
Solution Approach 1:
The path modeling system is segmented into multiple specialized components: outdoor path modules, indoor path modules, vehicle attribute modules, and infrastructure feature modules. Each segment handles specific aspects of the routing problem, allowing the system to adapt to mixed transportation networks while maintaining manageable complexity through modular architecture.
Solution Approach 2:
The path modeling system is designed with universal functionality to handle both outdoor and indoor transportation networks through a unified framework. The system can process diverse path types (roads, sidewalks, trails, elevators, escalators, moving sidewalks, stairs, ramps) and vehicle types by integrating multiple path models and vehicle attribute considerations into a single adaptable system.
2Adaptability or versatility
If traditional path modeling methods are used, then computational resources are conserved, but the methods cannot quickly adapt to changes in physical structure or architecture of paths
Solution Approach 1:
The path modeling system implements dynamic adaptability through real-time updates of path networks and vehicle attributes. The system can quickly respond to changes in physical structure or architecture by updating its internal models without requiring complete recalculation, allowing adaptive response to infrastructure changes while optimizing computational resource usage through incremental updates.
Solution Approach 2:
The system performs preliminary modeling of path networks and vehicle attributes in advance, creating reusable templates and structures. When infrastructure changes occur, the system can efficiently adapt by modifying pre-established models rather than building from scratch, reducing computational resource consumption during adaptation events.
3Reliability
If traditional path modeling methods are used, then the system is simple to implement, but the methods fail to consider operational or functional capacities of vehicles such as power levels, ranges, and maximum speeds
Solution Approach 1:
The route selection system applies local quality assessment by evaluating vehicle attributes (power levels, ranges, maximum speeds) specifically against the requirements of each path segment. Rather than treating all routes uniformly, the system selectively applies vehicle capability constraints to relevant path characteristics, ensuring route feasibility while managing system complexity through targeted rather than comprehensive analysis.
Solution Approach 2:
The system dynamically adjusts routing decisions based on vehicle parameter variations. By monitoring changes in vehicle attributes (power levels, ranges, speeds) and corresponding path parameters (distance, elevation, speed limits), the system adapts route selection to ensure feasibility. This parameter-based approach allows the system to consider operational capacities without requiring completely complex decision-making architecture.
4Adaptability or versatility
If traditional path modeling methods are used, then processing time is minimized, but the methods are ineffective in environments with both traditional and non-traditional features or infrastructure
Solution Approach 1:
The path network is segmented into distinct types (outdoor paths, indoor paths, vertical transportation, horizontal transportation) with specialized handling for each. This segmentation allows the system to process different feature types through optimized routines, improving adaptability to mixed transportation features while reducing overall calculation time through efficient specialized processing of each segment type.
Solution Approach 2:
The system extends traditional two-dimensional path modeling into three dimensions by incorporating vertical transportation features (elevators, escalators, ramps, stairs) and indoor-outdoor transitions. This dimensional expansion enables handling of mixed transportation features including non-traditional infrastructure while maintaining efficient calculation through structured 3D spatial reasoning and layered path processing.
Data Source
AI summary
Customized navigation maps of an area are generated for autonomous vehicles based on a baseline map of the area, transportation systems within the area, and attributes of the autonomous vehicles. The customized navigation maps include a plurality of paths, and two or more of the paths may form an optimal route for performing a task by an autonomous vehicle. Customized navigation maps may be generated for outdoor spaces or indoor spaces, and include specific infrastructure or features on which a specific autonomous vehicle may be configured for travel. Routes may be determined based on access points at destinations such as buildings, and the access points may be manually selected by a user or automatically selected on any basis. The autonomous vehicles may be guided by GPS systems when traveling outdoors, and by imaging devices or other systems when traveling indoors.