Visual Sparse Map Navigation Using Keyframes and Waypoints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Dense maps used in autonomous navigation are inefficient due to redundancy, require frequent updates, and consume high computational resources and memory, making them costly and resource-intensive.
Innovation Solution
A visual sparse map system for autonomous navigation that uses a robotic device equipped with a visual sensor, processor, and storage, which generates and utilizes a sparse map comprising visual feature points and keyframes to compute transition and rotation velocities for navigation, reducing redundancy and computational needs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If dense maps are used for autonomous navigation, then localization accuracy is improved, but memory consumption and computational cost increase significantly
Solution Approach 1:
The patent extracts only the essential and useful information from the environment to create a sparse map, removing redundant data points. Instead of storing all environmental features like dense maps, the system selectively stores only those features that are critical for navigation and localization, thereby reducing memory consumption while maintaining navigation effectiveness
Solution Approach 2:
The patent segments the map into discrete, manageable keyframes rather than storing continuous dense map data. Each keyframe represents a specific viewpoint with associated landmarks, allowing the system to process and store map information in divided, efficient units that reduce overall memory requirements compared to dense map representations
2Reliability
If dense maps are updated periodically to reflect environment changes, then navigation reliability is improved, but computational cost and processing time increase
Solution Approach 1:
The patent implements periodic action by updating the sparse map only at specific intervals or under certain conditions (e.g., when significant environmental changes are detected), rather than continuously updating dense map data. This selective updating approach maintains navigation reliability while minimizing the computational time and processing overhead associated with frequent map updates
3Area of stationary object
If dense maps are used for autonomous navigation, then complete environmental coverage is achieved, but device complexity and computational resources required increase
Solution Approach 1:
The patent extracts only the essential and useful information from the environment to create a sparse map, removing redundant data points. Instead of storing all environmental features like dense maps, the system selectively stores only those features that are critical for navigation and localization, thereby reducing memory consumption while maintaining navigation effectiveness
Solution Approach 2:
The patent segments the map into discrete, manageable keyframes rather than storing continuous dense map data. Each keyframe represents a specific viewpoint with associated landmarks, allowing the system to process and store map information in divided, efficient units that reduce overall memory requirements compared to dense map representations
Data Source
AI summary
A system and method for autonomous navigation using a visual sparse map. The system includes a robotic device having an RGB-D camera, a processor and a storage device storing computer executable code. The computer executable code is configured to: obtain the visual sparse map based on captured RGB-D images; capture an RGB image; acquire a current pose of the robotic device; find a keyframes nearest to the current pose of the robotic device; find a target waypoint that is ahead of the nearest keyframe at about a pre-defined distance; compute transition velocity and rotation velocity of the robotic device based on relative location between the robotic device and the target waypoint; and control operation of the robotic device using the computed transition velocity and rotation velocity to achieve autonomous navigation.