Autonomous Vehicle Path Planning With On-the-Fly Map Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving vehicles face challenges in determining paths without preexisting map data, as conventional methods rely heavily on map data and may cease automatic operation when such data is unavailable, making it difficult to continue operating autonomously in unfamiliar environments.
Innovation Solution
The system generates map data on the fly using sensor data from cameras, radar, and LIDAR units, allowing autonomous vehicles to determine paths using existing hardware and software without the need for additional modifications or ceasing operation, by integrating perception and planning modules that process sensor data to create real-time map information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional trajectory planning techniques rely heavily on preexisting map data, then path determination accuracy is improved, but operational continuity deteriorates when map data is unavailable
Solution Approach 1:
The patent introduces map generation modules as intermediaries between sensor data and trajectory planning. These modules create map data on-the-fly from sensor inputs when preexisting map data is unavailable, acting as a mediator that enables the trajectory planning module to function without requiring precollected map data, thus resolving the contradiction between accuracy and operational continuity
Solution Approach 2:
The autonomous vehicle performs map generation itself using its own sensor data rather than relying on externally provided preexisting maps. The vehicle serves its own mapping needs by processing sensor data through map generation modules, enabling it to operate autonomously in environments without precollected map data
2Reliability
If the vehicle ceases automatic operation when map data is unavailable, then safety is improved, but adaptability deteriorates
Solution Approach 1:
The patent implements dynamic map data generation that adapts to the vehicle's current environment in real-time. Rather than using static preexisting maps, the system dynamically creates map data from sensor inputs, allowing the vehicle to adapt to any environment while maintaining safety through continuous environmental awareness and trajectory planning
3Adaptability or versatility
If additional hardware or software modifications are made to operate without map data, then operational flexibility is improved, but device complexity increases
Solution Approach 1:
The patent makes existing sensor units serve multiple functions: they continue to provide data for immediate trajectory planning while also serving as the data source for map generation modules. This multi-functionality allows the system to operate without preexisting map data without requiring additional specialized hardware, thus improving operational flexibility while minimizing increased complexity
Data Source
AI summary
An ADV may determine whether there is preexisting map data for an environment or geographical area/location where the ADV is located/travelling. If there is no preexisting data, the ADV may generate map data based on sensor data obtained from one or more sensors of the ADV. The ADV may determine a path for the ADV based on the generated map data. If there is preexisting map data, the ADV may determine a path for the ADV based on the preexisting map data.