Robotic EV Charging Plug Localization for Port Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electric vehicle charging systems require manual user intervention, which can lead to inefficiencies and safety risks due to the need for manual connection of charging cables, especially with high-voltage systems, and vary in port locations across different vehicle models and manufacturers, necessitating a robust and cost-effective automated solution.
Innovation Solution
An automated charging system utilizing a robotic plug with a camera and tapered structure that performs localization through a multi-stage image processing method involving convolutional neural networks to accurately position and orient the plug relative to the vehicle's charging port, enabling hands-free operation and adaptability to different vehicle configurations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If manual connection of charging cable is used, then system complexity is reduced, but user safety is compromised due to exposure to high-voltage systems
Solution Approach 1:
The automated charging system performs the connection task autonomously without human intervention. The robotic arm with gripper automatically locates, approaches, and connects the charging plug to the vehicle port, while the system self-monitors alignment and connection status through camera feedback, eliminating the need for users to handle high-voltage components.
Solution Approach 2:
The patent replaces manual mechanical operations with an automated robotic system. The robotic arm uses motorized actuators for positioning and movement, while computer vision systems replace human visual detection for locating the charging port. This substitution eliminates direct human contact with high-voltage systems while maintaining precise control over the connection process.
2Object-affected harmful factors
If automated charging system is implemented, then user safety is improved, but device complexity increases due to robotic control and image processing requirements
Solution Approach 1:
The automated charging system is divided into distinct functional modules: a robotic arm module for positioning and movement, a gripper module for plug handling, a camera module for visual detection and alignment, and a control module for coordinating operations. This segmentation allows each component to be optimized independently and simplifies the overall control architecture by assigning specific tasks to dedicated subsystems.
Solution Approach 2:
The robotic arm serves multiple functions: it positions the plug, maintains alignment during approach, and facilitates connection. The camera system simultaneously performs detection of the charging port, monitoring of alignment, and verification of successful connection. This multi-functionality reduces the need for separate specialized components, thereby managing system complexity.
3Measurement precision
If multi-stage localization procedure is used, then positioning accuracy is improved, but processing time increases
Solution Approach 1:
The system performs a preliminary detection phase where the camera identifies the general location and orientation of the charging port before the robotic arm begins precise positioning. This preliminary action provides initial alignment data that guides the subsequent fine-positioning phase, reducing the time and computational resources needed for achieving final precise alignment.
Solution Approach 2:
The multi-stage localization procedure operates in periodic phases: a first image is captured and processed to determine coarse alignment, the robotic arm moves to an intermediate position, a second image is captured for fine alignment, and final positioning is executed. This periodic execution of detection-movement-detection cycles allows the system to balance accuracy requirements with time efficiency by only performing detailed processing when necessary.
Data Source
AI summary
An automated charging system for an electric vehicle is disclosed that includes a plug with a built-in camera assembly. The camera assembly captures images of a charging port of the electric vehicle, which are processed by one or more processors to estimate the location of the charging port relative to the plug. A multi-stage localization architecture is described that includes a gross localization procedure and a fine localization procedure. The gross localization procedure can implement a first convolutional neural network (CNN) to estimate a position of an object in the image. The fine localization procedure can implement a second CNN to estimate a position and orientation of the object. Actuators for moving the plug in a three-dimensional space can be controlled by the multi-stage localization architecture.