Unoccupied Autonomous Vehicle Lane Data Collection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Maintaining up-to-date map data for autonomous and semi-autonomous vehicles is costly and inefficient, as existing solutions require dedicated vehicles for data collection, which is expensive and resource-intensive due to the need for frequent updates across multiple roadways.
Innovation Solution
Unoccupied autonomous vehicles select and collect lane data from 'lanes-of-interest' based on criteria such as data staleness, construction, and defects, using onboard or cloud-based systems to determine the most relevant lanes for data collection while traveling, thereby leveraging existing vehicle operations without additional resource costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If dedicated vehicles are used for map data collection, then data collection coverage and frequency are improved, but operational costs and resource consumption increase significantly
Solution Approach 1:
The patent applies multi-functionality by enabling autonomous vehicles to perform both their primary transportation function and map data collection function simultaneously. The system allows unoccupied autonomous vehicles to collect lane data from lanes-of-interest during normal operations, eliminating the need for separate dedicated data collection vehicles. This resolves the contradiction by making the vehicle fleet serve dual purposes, improving data collection frequency without proportionally increasing operational costs.
Solution Approach 2:
The system implements self-service by allowing autonomous vehicles to autonomously determine when and where to collect data based on pre-defined criteria such as data staleness, construction activity, and defect evidence. The vehicles independently select lanes-of-interest and execute data collection without requiring manual dispatch or dedicated infrastructure, thereby improving productivity while minimizing additional resource consumption.
2Loss of information
If unoccupied autonomous vehicles collect data from all lanes, then data completeness is improved, but safety and comfort concerns arise
Solution Approach 1:
The patent applies local quality by selectively collecting data only from specific lanes identified as lanes-of-interest rather than uniformly collecting data from all lanes. The system evaluates each lane based on pre-defined criteria (data staleness, construction, defects) and directs data collection only where needed. This resolves the contradiction by achieving data completeness for critical areas while avoiding unnecessary exposure to safety and comfort risks in other lanes.
Solution Approach 2:
The system implements partial action by collecting data from a subset of lanes (lanes-of-interest) rather than all lanes. The lane selection module identifies specific lanes that require monitoring based on pre-defined criteria, and the autonomous vehicle collects data only from those selected lanes. This approach achieves sufficient data completeness for safety-critical applications while minimizing the vehicle's exposure to potentially harmful conditions.
3Loss of information
If lane selection is based on multiple criteria including staleness, construction, and defects, then data relevance is improved, but system complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the lane selection process into distinct functional modules: a lane selection module that identifies lanes-of-interest based on pre-defined criteria, and a data collection module that executes data gathering from selected lanes. The selection criteria themselves are segmented into separate evaluation categories (data staleness, construction activity, defect evidence). This modular segmentation manages system complexity by organizing the decision-making process into discrete, manageable components while maintaining comprehensive data relevance.
Data Source
AI summary
In one embodiment, a method for collecting lane data is disclosed. The method includes collecting lane data, for a lane of a plurality of lanes of a road, from one or more sensors of a vehicle traveling in the lane. The method includes receiving an identifier of a lane of the plurality of lanes. The identified lane is a lane-of-interest and is different from the lane that the vehicle is traveling in. The method includes determining that the vehicle is not occupied. The method includes causing, in response to determining that the vehicle is not occupied, the vehicle to travel in the lane-of-interest. The method includes collecting lane data, for the lane-of-interest from the one or more sensors.