Autonomous Vehicle Corner Negotiation via Mapping Table Lookup
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Low-cost autonomous driving vehicles, particularly at level 3, face challenges in negotiating corners due to the lack of a localization module and limited sensor quality, leading to inadequate corner sensing without significant increases in cost by upgrading sensors and adding localization modules.
Innovation Solution
A computer-implemented method that perceives the driving environment using sensor data, extracts features to identify corner entrance points, performs a lookup in a corner mapping table to determine the turning radius, and negotiates a corner turning trajectory to control the vehicle, utilizing driving statistics and machine learning models to determine corner configurations without relying on maps or localization processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensors and localization module are upgraded to improve corner sensing capability, then corner negotiation accuracy is improved, but system cost significantly increases
Solution Approach 1:
The patent creates a virtual corner mapping table that copies and stores corner configuration information from multiple data sources (maps, localization data, sensor data) into a simplified lookup structure. This virtual copy enables corner negotiation without requiring expensive upgrades to physical sensors or localization modules, as the system retrieves pre-processed corner information from the mapping table instead.
Solution Approach 2:
The system performs preliminary processing of corner information by collecting data from various sources and pre-computing corner mapping tables that contain turning radii and trajectory parameters. This preliminary action allows the autonomous vehicle to negotiate corners efficiently during runtime without requiring complex real-time sensor processing or expensive hardware upgrades.
2Reliability
If corner negotiation accuracy is improved through better sensing, then safety is improved, but device complexity increases
Solution Approach 1:
The corner mapping table serves multiple functions: it stores geometric corner information, provides turning radius data, enables trajectory generation, and works with various sensor configurations. This universal data structure allows the system to achieve reliable corner negotiation without requiring complex, specialized sensor systems, as the same mapping table can be used across different vehicle configurations.
3Device complexity
If real-time corner negotiation is achieved without map and localization, then system cost is reduced, but measurement precision of corner parameters may worsen
Solution Approach 1:
The patent merges corner information from multiple sources including map data, localization data, and sensor data into a unified corner mapping table. By combining these diverse data sources, the system achieves accurate corner parameter measurement without requiring expensive dedicated sensors or localization modules, as the fused information compensates for the limitations of individual low-cost components.
Data Source
AI summary
An ADV perceives a driving environment surrounding the ADV based on sensor data obtained from a variety of sensors mounted on the ADV including, for example, perceiving and recognizing a corner the ADV may be about to turn. Based on the perception data of the driving environment, a set of features representing the characteristics of an entrance point of a corner that the ADV is about to turn. Based on the characteristics of the corner, an entrance point of the corner is determined. Based on the entrance point, a lookup operation is performed in a corner mapping table to locate a mapping entry matching the entrance point. A turning radius is then obtained from the mapping entry of the corner mapping table. The turning radius obtained from the corner mapping table is then utilized to plan a trajectory (e.g., steering angle) to drive the ADV to turn the corner.