Sensor Fusion for Unmanned Vehicle Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current sensing systems for unmanned vehicles are less than ideal, as they are often accurate only under specific environmental conditions or types of movement, limiting their flexibility and accuracy in navigation.
Innovation Solution
The system employs sensor fusion to collect and determine positional information by combining data from multiple sensing systems, including GPS, IMU, and vision sensors, to enhance navigation accuracy and flexibility for unmanned vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single sensing system is used for navigation, then the system complexity is reduced, but the measurement precision and reliability deteriorate under varying environmental conditions
Solution Approach 1:
The patent combines multiple sensing systems (GPS, inertial sensors, visual odometry, wheel encoders) into a unified navigation system that integrates their respective strengths. The sensor fusion algorithm merges data from these diverse sources to achieve high measurement precision across varying environmental conditions, resolving the contradiction between accuracy and system complexity.
Solution Approach 2:
The navigation system is designed to perform multiple functions using different sensor subsets depending on environmental conditions. The system can operate with GPS in open areas, switch to inertial navigation in GPS-denied environments, or use visual odometry in structured environments, making the system universally applicable while maintaining precision.
2Reliability
If multiple sensing systems are integrated to improve accuracy, then the measurement precision improves, but the device complexity increases
Solution Approach 1:
The sensor fusion algorithm dynamically adjusts the weighting and contribution of each sensing system based on current environmental conditions and sensor performance. This dynamic adaptation allows the system to maintain high reliability by optimally utilizing available sensors without requiring all sensors to operate at full complexity simultaneously.
Solution Approach 2:
The system incorporates feedback mechanisms where the performance and reliability of individual sensors are continuously monitored, and this information feeds back into the fusion algorithm to adjust weighting factors. This feedback loop ensures that the most reliable data sources are prioritized, maintaining navigation reliability while managing system complexity.
3Adaptability or versatility
If sensor fusion is implemented to compensate for individual sensor inaccuracies, then the positional information accuracy improves, but the computational requirements and processing complexity increase
Solution Approach 1:
The sensor fusion process is segmented into distinct computational modules, each handling specific sensor types or fusion operations. This segmentation allows for optimized processing of different sensor data streams independently, reducing overall computational complexity while maintaining the adaptability benefits of comprehensive sensor fusion.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Systems, methods, and devices are provided for collecting positional information for and controlling a movable object. In one aspect of the present disclosure, a method for collecting positional information for a movable object includes: receiving data from a first sensing system coupled to the movable object; receiving data from a second sensing system coupled to the movable object; determining a weight value for the data from the second sensing system based on a strength of the signal received by the sensor of the second sensing system; and calculating the positional information of the movable object based on (i) the data from the first sensing system and (ii) data from the second system factoring in the weight value.