Sensor-Based Localization Using Environmental Knowledge Base
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing localization techniques, particularly GNSS-based systems, face reliability issues due to signal spoofing, jamming, and natural disturbances, leading to inaccurate positioning and navigation, especially in environments where satellite signals are weak or unreliable.
Innovation Solution
A method and system that utilize a multi-dimensional electronic map generated by combining sensor information from various sources to uniquely describe each location within an environment, allowing for robust localization and navigation without relying on satellite coordinates, using a knowledge base built from initial data acquisition and continuously updated by sensor data from multiple devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If GNSS-based positioning systems are used, then positioning information can be obtained in open environments, but reliability deteriorates due to signal spoofing, jamming, and atmospheric disturbances
Solution Approach 1:
The patent introduces an intermediary localization system that uses sensor data (cameras, LIDAR, radar) to capture environmental features and create sensor-based location descriptions. This intermediary layer translates physical environment observations into location information, providing an alternative pathway that does not depend on vulnerable GNSS signals. The sensor fusion approach combines multiple sensing modalities to robustly describe the environment, making the system resistant to spoofing and jamming attacks.
Solution Approach 2:
The patent replaces the radio wave-based GNSS positioning mechanism with a sensor-based environmental perception mechanism. Instead of relying on satellite radio signals that can be spoofed or jammed, the system uses optical cameras, LIDAR, radar, and other sensors to directly observe and characterize the physical environment. This substitution fundamentally changes the positioning paradigm from signal-based to observation-based, eliminating vulnerability to radio frequency attacks.
2Reliability
If sensor-based localization is implemented, then robustness against GNSS failures is improved, but device complexity increases due to multiple sensors and processing requirements
Solution Approach 1:
The patent makes the sensor system multi-functional by using the same sensors (cameras, LIDAR, radar) for both localization and environmental perception tasks. The sensor data is processed to create sensor-based location descriptions for positioning, while simultaneously capturing environmental features for navigation and mapping. This multi-functionality reduces the need for separate specialized sensors, thereby limiting complexity growth while maintaining robustness.
Solution Approach 2:
The patent merges multiple sensing modalities (optical, electromagnetic, acoustic) and multiple processing functions (localization, mapping, navigation) into a unified sensor-based localization framework. By combining these functions and data sources, the system achieves robust GNSS-independent positioning without requiring separate dedicated systems for each function, thus controlling overall complexity while improving reliability.
3Measurement precision
If comprehensive sensor information is collected to describe each location, then positioning accuracy is improved, but data processing time increases
Solution Approach 1:
The patent performs preliminary action by pre-processing sensor data to create sensor-based location descriptions and environmental feature representations in advance. During runtime, the system compares current sensor observations with pre-computed location signatures from the knowledge base, significantly reducing real-time processing requirements. This offline pre-processing enables accurate positioning while minimizing online computation time.
Solution Approach 2:
The patent segments the large-scale environment into discrete locations, each characterized by a sensor-based location description. By dividing the continuous environment into manageable segments and pre-computing features for each segment, the system enables efficient comparison and matching during runtime. This segmentation approach balances detailed environmental characterization with computational efficiency.
Data Source
Figure 1~2
Figure 3~4
Figure 5
AI summary
The invention relates to a method of localizing a device (20) within an environment (40). In a step (S10), a first location information is acquired that is representative for a first specified position. In another step (S20), a first sensor information is acquired that is representative for the first specified position. In another step (S30), the first sensor information is allocated to the first location information in order to generate a first condition information that is unique for the first specified position. In another step (S40), a knowledge base (13) is provided which includes the first condition information. In another step (S50), the device (20) provides a current sensor information indicating a current condition of the environment (40) present at the current position of the device (20). In another step (S60), the device (20) is localized based on a matching between the current sensor information and the plurality of condition information.