Wheelchair Docking Pose Estimation From 2D Image Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Wheelchair users, especially those with upper limb disabilities, face challenges in precisely maneuvering their wheelchairs for docking operations due to limited space and lack of specialized facilities, making it difficult to align with objects like tables, beds, or vehicles.
Innovation Solution
A system and method that converts a user-selected 2D point in a 2D image to a 3D point in a 3D point cloud, determines edges and poses using convex and concave hulls, and controls motorized wheels to dock the wheelchair accurately.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If wheelchair users manually maneuver the wheelchair for docking operations, then the user has full control over the wheelchair, but the precision and accuracy of docking alignment deteriorates due to limited user capability and lack of specialized facilities
Solution Approach 1:
The patent replaces manual mechanical maneuvering with an automated vision-based system. A camera captures images of the target object, and a processor automatically calculates the optimal docking pose and controls the wheelchair's motorized wheels to execute the docking maneuver, substituting human mechanical control with automated optical-mechanical integration.
Solution Approach 2:
The system enables the wheelchair to perform docking operations autonomously by capturing images with its own camera, processing the images to determine docking parameters, and automatically executing the docking maneuver without requiring external assistance or specialized facilities.
2Measurement precision
If specialized docking facilities are provided to improve docking precision, then the docking alignment accuracy improves, but the device complexity and infrastructure requirements increase
Solution Approach 1:
The patent makes the wheelchair itself a universal docking system by integrating a camera and image processing capability into the wheelchair. This allows the wheelchair to perform docking operations at any location without requiring specialized docking facilities, making the system adaptable to diverse environments including homes, hospitals, and public spaces.
Solution Approach 2:
The patent introduces an image-based intermediary system that mediates between the wheelchair and the target object. Instead of requiring physical docking facilities, the system uses captured images as an intermediary to calculate and achieve precise docking alignment, eliminating the need for complex infrastructure.
3Ease of operation
If the wheelchair uses a 2D image for docking, then the system complexity is reduced and ease of operation improves, but the accuracy of 3D pose determination may deteriorate
Solution Approach 1:
The patent resolves the 2D-to-3D accuracy problem by utilizing the known geometric constraints of the wheelchair and target object. The system processes 2D image data while incorporating spatial relationship constraints to calculate accurate 3D docking pose parameters, effectively bridging the dimensional gap through mathematical modeling.
Solution Approach 2:
The system changes the approach by not directly measuring 3D parameters from the 2D image, but instead calculating docking pose parameters (position and orientation) through image processing and geometric reasoning. This parameter transformation approach maintains accuracy while keeping the user interface simple.
Data Source
AI summary
A system and method of docking a wheelchair relative to an object such as a table. The method includes converting a user-selected 2D point in a 2D image of a scene into a 3D point in a 3D point cloud of the scene. A first group of edges is determined from the 3D point cloud based on the 3D point. The method includes defining an intermediate dock pose and an approximated reference edge. The method includes determining a second group of edges from the 3D point cloud and at least one potential reference edge. The method includes determining a dock pose based on one of the at least one potential reference edge and moving the wheelchair towards the dock pose.