Autonomous Driving Track Generation at Interruption Positions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous driving technologies struggle to maintain continuous driving in areas where the positional relation between a road and surrounding vehicles causes frequent interruptions.
Innovation Solution
A computing device and autonomous driving system that include a server communication section to receive information about interruption positions and manual driving information from vehicle-mounted devices, an extraction section to identify control points related to changes in vehicle direction, and a creation section to generate knowledge information enabling the generation of tracks for changing vehicle direction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If autonomous driving uses only sensor information and map data, then the system can operate with basic navigation capabilities, but autonomous driving is frequently interrupted at spots with complex positional relations between road and surrounding vehicles
Solution Approach 1:
The system performs preliminary actions by collecting manual driving information in advance and storing it in the database. When autonomous driving encounters an interruption position, the system retrieves pre-stored manual driving trajectories from the database to generate appropriate tracks, enabling continuous autonomous driving without interruption.
Solution Approach 2:
The database acts as an intermediary between sensor/map data and autonomous driving control. It stores manual driving information and provides retrieved trajectories that bridge the gap when standard autonomous driving fails at complex positions, enabling the system to handle scenarios beyond basic sensor and map data capabilities.
2Adaptability or versatility
If the system collects and processes manual driving information from multiple vehicles, then knowledge information for complex positions can be generated, but the data processing complexity and storage requirements increase
Solution Approach 1:
The system extracts only the necessary manual driving information (position, trajectory, speed, steering angle) related to interruption positions and stores it in the database. This selective extraction reduces data volume while maintaining the essential information needed for generating tracks at complex positions.
Solution Approach 2:
Instead of storing complete raw sensor data from multiple vehicles, the system creates simplified copies in the form of structured manual driving information containing position, trajectory, speed, and steering angle. This copying approach reduces storage requirements and processing complexity while preserving the essential characteristics needed for autonomous driving at complex positions.
Data Source
AI summary
A computing device includes a server communication that receives, from a vehicle-mounted device in a first vehicle, information about a position of interruption in autonomous driving and receives, from a vehicle-mounted device in a second vehicle, information about manual driving of the second vehicle in a region of the interruption position. A control point is extracted from the manual driving information in the region of the interruption position as a spot related to a change of a running direction, and knowledge information is created containing running information that is a speed or a steering angle of a vehicle on a trajectory passing through the control point. Also received is knowledge information enabling generation of a track for changing a running direction of a vehicle. The knowledge information and information indicating a trajectory of a vehicle generated using the knowledge information is transmitted to a vehicle-mounted device of a vehicle.