Autonomous Vehicle Route Planning for Dynamic No-Go Road Segments
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in efficiently planning routes that adapt to real-time environmental conditions and dynamic no-go regions, leading to suboptimal navigation and increased computational complexity.
Innovation Solution
The method involves identifying no-go roadway segments using a graph walk and assigning cost values to filtered roadway segments based on construction areas, unprotected left turns, and time to destination, which are stored in a local cache for quick retrieval, allowing the vehicle to plan its path reactively and efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the vehicle uses detailed map information and performs comprehensive route planning, then navigation accuracy and safety are improved, but computational complexity and processing time increase
Solution Approach 1:
The patent divides the map information into multiple local map regions, each representing a specific geographic area. Instead of processing the entire map at once, the system segments the navigation problem into smaller regional sub-problems, reducing computational complexity while maintaining navigation safety through localized detailed analysis.
Solution Approach 2:
The system applies different processing qualities to different regions by identifying relevant local map regions based on the vehicle's current location and destination. High-computation activities like cost value assignment and no-go region identification are performed only in relevant local regions rather than across the entire map, optimizing the balance between safety and computational load.
2Adaptability or versatility
If the vehicle dynamically updates route plans based on real-time conditions, then responsiveness to environmental changes is improved, but computational overhead increases
Solution Approach 1:
The system performs dynamic updates by re-determining local map regions and recalculating cost values only for affected areas when environmental conditions change. This localized reprocessing approach maintains adaptability to real-time conditions while significantly reducing computational overhead compared to full route recalculation.
Solution Approach 2:
The system pre-identifies no-go roadway segments and pre-calculates cost values for roadway segments during periods when computational resources are available. These pre-computed values are stored and retrieved during real-time navigation, reducing computational overhead during dynamic updates while maintaining responsiveness.
3Productivity
If the vehicle caches cost values for frequently accessed roadway segments, then route planning speed is improved, but memory usage increases
Solution Approach 1:
The system caches cost values specifically for roadway segments within identified local map regions, which are the most frequently accessed areas during navigation. This targeted caching approach improves route planning speed for relevant regions while minimizing memory usage by not caching entire map data.
Solution Approach 2:
The caching mechanism is applied segmentally to individual roadway segments within local map regions rather than caching all map data uniformly. This allows the system to prioritize caching for high-frequency access areas while managing overall memory consumption efficiently.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
A route (660) for a trip to a destination is generated using map information. A set of no-go roadway segments, where a vehicle (100) is not able to drive in an autonomous mode, relevant to the route is identified from the map information. A local region (800) around a current location of the vehicle is determined. A local map region (900) including roadway segments of the map information that correspond to locations within the local region is determined. The set of the plurality of no-go roadway segments is filtered from the roadway segments of the local map region. A cost value is assigned to each roadway segment of the filtered roadway segments of the local map region. Any assigned cost values are used to determining a plan for maneuvering the vehicle for a predetermined period into the future. The vehicle is maneuvered according to the plan.