Deep Neural Path Navigation for Vehicle Orientation and Lateral Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous vehicle navigation systems are often inaccurate and inefficient, lacking awareness of their environment, which hinders precise control and safety.
Innovation Solution
The use of deep neural networks (DNNs) to process image data from various sources, determining a vehicle's orientation and lateral position relative to a path, and controlling its location in real-time, while also performing object and obstacle detection for enhanced safety.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current autonomous control implementations are used, then vehicle navigation can be performed, but accuracy and efficiency are insufficient
Solution Approach 1:
The patent replaces traditional mechanical control systems with a deep neural network-based vision system. The DNN processes image data from cameras to directly determine vehicle orientation and lateral position relative to the path, eliminating the need for complex mechanical sensors and control mechanisms. This substitution enables more accurate and efficient autonomous navigation by leveraging the pattern recognition capabilities of deep learning algorithms.
2Reliability
If environment awareness is added to autonomous vehicles, then safety is improved, but system complexity increases
Solution Approach 1:
The deep neural network is designed to perform multiple functions simultaneously: it detects the path, determines vehicle orientation, calculates lateral position, and identifies obstacles all within a single integrated system. This multi-functionality approach allows the vehicle to gain comprehensive environment awareness and improved safety without proportionally increasing system complexity, as one DNN architecture handles multiple navigation and safety tasks.
3Measurement precision
If deep neural networks are used for real-time image processing, then navigation accuracy is improved, but computational requirements increase
Solution Approach 1:
The patent extracts and processes only the essential features from image data that are necessary for navigation - specifically focusing on path detection, orientation estimation, and lateral position calculation. The DNN is trained to identify and process only the relevant visual information needed for autonomous path following, filtering out unnecessary computational overhead. This extraction approach maintains high position determination accuracy while reducing overall computational energy consumption by avoiding processing of irrelevant data.
Data Source
AI summary
A method, computer readable medium, and system are disclosed for performing autonomous path navigation using deep neural networks. The method includes the steps of receiving image data at a deep neural network (DNN), determining, by the DNN, both an orientation of a vehicle with respect to a path and a lateral position of the vehicle with respect to the path, utilizing the image data, and controlling a location of the vehicle, utilizing the orientation of the vehicle with respect to the path and the lateral position of the vehicle with respect to the path.