Route Planning Using Deep Convolutional Neural Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current map-based navigation systems fail to consider user characteristics and preferences when recommending routes, leading to inapplicable solutions in real-life scenarios.
Innovation Solution
A system utilizing a deep convolutional neural network that determines a series of road intersections and their target entrances and exits based on road characteristic information and historical routes to generate optimized routes from a start location to a destination, incorporating user-specific preferences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a deep convolutional neural network is used to determine road intersections and entrances/exits, then route planning accuracy is improved, but device complexity increases
Solution Approach 1:
The patent segments the route planning task into multiple sequential determination steps: first determining a series of road intersections, then determining target entrances and exits for each intersection. This segmentation allows the complex neural network processing to be broken down into manageable stages, improving accuracy while managing device complexity through structured computation.
Solution Approach 2:
The patent performs preliminary determination of road intersections before determining the specific entrances and exits. This preliminary action establishes a sequence of key points that guides subsequent detailed processing, allowing the system to prepare and organize data in advance, thereby improving overall route planning accuracy without overwhelming device resources at any single moment.
2Adaptability or versatility
If user characteristics and preferences are integrated into route recommendations, then adaptability is improved, but information processing requirements increase
Solution Approach 1:
The patent applies local quality by integrating user characteristics and preferences specifically into the route selection process at critical decision points (road intersections and entrances/exits). Rather than uniformly processing all route data with equal complexity, the system selectively applies personalized filtering and optimization at locations where user preferences most impact route quality, thereby improving adaptability while managing information processing requirements.
Data Source
AI summary
The preset application discloses a method for route planning. At least one device including at least one processor and a storage may implement the method. The method may include one or more of the following operations. The device may first obtain a start location and a destination, road characteristic information and a plurality of historical routes. The device may then train a model based on the plurality of historical routes. Then the device may run the trained model to sequentially determine a plurality of road intersections between the start location and the destination, and a target entrance and target exit that corresponding to each of the plurality of the road intersections based on characteristic information. Finally, the device may generate a recommended route from the start location to the based on the target entrances and target exits.