Autonomous Path Navigation Using Deep Neural Networks
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 path following and obstacle avoidance.
Innovation Solution
The implementation of deep neural networks (DNNs) for analyzing image data to determine a vehicle's orientation and lateral position relative to a path, enabling real-time control and object/obstacle detection for improved navigation and safety.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If deep neural networks are used for analyzing image data to determine vehicle orientation and lateral position, then navigation accuracy is improved, but computational complexity and processing time increase
Solution Approach 1:
The system performs preliminary actions by pre-processing image data to extract relevant features before feeding them to the deep neural network. This reduces the computational burden during real-time navigation while maintaining accuracy, as the network only needs to process pre-extracted features rather than raw image data.
Solution Approach 2:
The navigation system is segmented into multiple functional modules: image acquisition module, deep neural network module for determining orientation and lateral position, and control module for generating steering directions. This segmentation allows each module to be optimized independently, reducing overall computational complexity while maintaining navigation accuracy.
2Speed
If deep neural networks process image data in real-time for autonomous navigation, then responsiveness is improved, but energy consumption increases
Solution Approach 1:
The system implements periodic action by processing image data at optimized intervals rather than continuously. The control module generates steering directions based on periodic updates from the deep neural network, reducing energy consumption while maintaining real-time responsiveness for autonomous navigation.
Solution Approach 2:
The system applies partial action by using the deep neural network only for critical navigation decisions rather than processing all image data at full resolution. The network processes selectively extracted features and key image regions, reducing computational load and energy consumption while maintaining navigation accuracy.
3Loss of information
If the system determines both orientation and lateral position using DNN, then environmental awareness is improved, but system complexity increases
Solution Approach 1:
The deep neural network is designed as a multi-functional system that simultaneously determines both vehicle orientation and lateral position relative to the path from the same image data input. This universal approach reduces system complexity compared to using separate systems for each function, while maintaining comprehensive environmental awareness.
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.