Occupancy map segmentation for autonomous guided platform with deep learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous robots face challenges in providing fast, accurate, and reliable positional awareness and environmental awareness, as conventional techniques fail to incorporate real-time sensory data for adaptive task planning.
Innovation Solution
A method for preparing a segmented occupancy grid map using image information from visual and depth cameras, combined with neural network classifiers to segment environments into regions, and implement convolutional and recursive neural networks for real-time data processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional techniques are used for environmental awareness, then device complexity is reduced, but measurement precision and reliability of positional awareness deteriorate
Solution Approach 1:
The patent segments the environmental awareness system into multiple specialized components: depth cameras for distance measurement, visual spectrum cameras for color and texture detection, and neural network classifiers for pattern recognition. Each component handles a specific aspect of environmental perception, improving overall measurement precision while organizing complexity into manageable modules
Solution Approach 2:
The patent transitions from 2D image data to 3D spatial understanding by integrating depth camera measurements with visual spectrum data. The neural network classifiers process multi-dimensional features including depth, color, texture, and spatial relationships, enabling accurate positional awareness in three-dimensional space
2Adaptability or versatility
If real-time sensory data processing is implemented, then adaptability for task planning improves, but processing time and computational load increase
Solution Approach 1:
The patent implements preliminary action by pre-training neural network classifiers on extensive datasets of environmental features. The classifiers are pre-configured with knowledge of object patterns, textures, and spatial relationships, enabling them to rapidly classify new sensory data in real-time without extensive computational processing
Solution Approach 2:
The patent replaces traditional mechanical or rule-based environmental analysis with neural network-based computational intelligence. The neural networks automatically learn and adapt to environmental patterns from sensory data, providing versatile adaptive task planning capabilities while reducing processing time compared to conventional analytical methods
Data Source
AI summary
The technology disclosed includes systems and methods for preparing a segmented occupancy grid map based upon image information of an environment in which a robot moves. The image information is captured by at least one visual spectrum-capable camera and at least one depth measuring camera. The system includes logic to receive image information captured by at least one visual spectrum-capable camera and location information captured by at least one depth measuring camera located on a mobile platform. The system includes logic to extract from the image information, features in the environment. The system includes logic to determine a 3D point cloud of points having 3D information. The system includes logic to determine, from the 3D point cloud, an occupancy map of the environment. The system includes logic to segment the occupancy map into a segmented occupancy map of regions that represent rooms and corridors in the environment.