Driverless Vehicle Route Learning for Temporary Road Blockages
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Driverless vehicles face challenges in generating a travelling strategy when existing routing information is inadequate, such as temporary road closures or obstacles, leading to ineffective navigation.
Innovation Solution
The method involves recording and learning from the travelling trajectories of other vehicles, generating a new strategy when multiple vehicles follow the same path, and controlling the vehicle to adapt to these trajectories, with the ability to report and share strategies with other vehicles and a server.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the driverless vehicle relies on existing routing information to generate a travelling strategy, then the navigation system is simple to operate, but it becomes ineffective when facing temporary road closures or obstacles
Solution Approach 1:
The system performs preliminary actions by recording and storing travelling trajectories of other vehicles in advance. When the current vehicle encounters routing issues, these pre-recorded trajectories are immediately available for learning and strategy generation, eliminating the need for complex real-time analysis of alternative routes
Solution Approach 2:
The system introduces an intermediary learning module that mediates between the routing information and the travelling strategy generation. This module learns from other vehicles' trajectories and provides adaptive navigation solutions, simplifying the overall system architecture while improving reliability
2Adaptability or versatility
If the driverless vehicle records and learns from travelling trajectories of other vehicles in real-time, then the vehicle's adaptability to unexpected road conditions improves, but the processing time and computational load increase
Solution Approach 1:
Trajectory data from other vehicles is recorded and stored in advance during normal operations. When navigation issues arise, the system learns from this pre-collected data rather than gathering information in real-time, significantly reducing processing time while maintaining high adaptability
Solution Approach 2:
The system creates copies of successful travelling trajectories from other vehicles and uses these copies as templates for generating travelling strategies. This copying approach allows rapid adaptation to road conditions without extensive real-time computation
Data Source
AI summary
A method, apparatus and server for real-time learning of a travelling strategy of a driverless vehicle are provided. The method includes: when a first travelling strategy of the driverless vehicle is unable to be generated, recording travelling trajectories of other vehicles on a road; when a number of vehicles on a same travelling trajectory is greater than a preset first number threshold, generating a second travelling strategy using the same travelling trajectory; and controlling the driverless vehicle to travel using the second travelling strategy. A situation in which a driverless vehicle is unable to normally generate a travelling strategy can be improved effectively.