Parking Vehicle Self-Localization With Adaptive Sensor Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The high energy consumption and demand for computing resources in autonomous vehicles for continuous environment sensing and localization in parking infrastructure, due to the need for multiple sensor systems to accurately determine position and orientation, are not efficiently managed by existing technologies.
Innovation Solution
A method that selectively activates specific sensor types and landmark detection algorithms based on a vehicle's pose and dominant landmark types, using a stored assignment instruction to generate and process environment sensor data, thereby reducing the need for continuous operation of all detector modules and conserving computing resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple sensor systems and landmark detection algorithms are continuously activated for accurate self-localization in parking infrastructure, then measurement precision and reliability are improved, but use of energy and computing resources increase significantly
Solution Approach 1:
The system dynamically adapts the configuration of sensor systems and landmark detection algorithms based on the vehicle's current pose and the environment characteristics stored in the digital map. Different sensor types and detection algorithms are selectively activated or deactivated depending on the specific parking infrastructure context, transforming a static full-activation system into a dynamic adaptive system that optimizes resource usage while maintaining localization accuracy
Solution Approach 2:
The system applies different sensor configurations and detection algorithms to different spatial locations within the parking infrastructure. By consulting the digital map to identify dominant landmark types in specific areas (e.g., optical landmarks in well-lit areas, radar landmarks in dark areas), the system tailors the sensing and processing resources to the local environmental characteristics, avoiding uniform activation of all systems throughout the entire infrastructure
2Reliability
If multiple sensor systems and landmark detection algorithms are continuously activated for accurate self-localization in parking infrastructure, then reliability is improved, but device complexity and computing resource demand increase significantly
Solution Approach 1:
The system dynamically adjusts the complexity of the sensor configuration and detection algorithm set based on the vehicle's pose and environmental context. By selectively activating only the necessary sensor types and detection algorithms for the current location (determined through digital map consultation), the system reduces the operational complexity and computing resource demand while maintaining reliable self-localization through appropriate algorithm selection for each context
Solution Approach 2:
The system segments the self-localization task by dividing the parking infrastructure into different zones with characteristic landmark types (stored in the digital map). For each zone, a specific subset of sensor systems and detection algorithms is activated. This segmentation allows the complex overall task to be broken down into manageable sub-tasks, each handled by a tailored configuration of sensors and algorithms, reducing the effective complexity at any given moment
Data Source
AI summary
According to a method for self-localization of a vehicle, a first pose of the vehicle is determined. Environment sensor data are generated by means of an environment sensor device and on the basis of this a landmark is detected in the environment. A position of the landmark is determined and in dependence on this a second pose of the vehicle is determined. A memorized assignment instruction is consulted, matching up the first pose with at last one preferred sensor type or at least one dominant landmark type, and depending on this a first portion of the environment sensor data is selected that was generated by means of a first environment sensor system of the environment sensor device configured according to a first sensor type. For the detecting of the landmark, a first landmark detection algorithm is applied to the first portion of the environment sensor data.