EV Charge Port Pose Estimation Using 2D-Depth Feature Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional vision-based methods struggle to accurately estimate the position and pose of a charge port on electric vehicles due to the lack of distinctive geometric features on the vehicle body, making automated vehicle charging systems inefficient.
Innovation Solution
A method that combines 2D image and depth information to estimate the position and pose of a charge port by extracting contours from a 2D image and deprojecting them into 3D space using depth information, aided by a camera system with depth sensing capability, and a robotic arm with an end effector designed to connect to the charge port.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional vision-based methods are used to estimate charge port position, then the system is simple to implement, but the measurement precision is insufficient due to lack of distinctive geometric features
Solution Approach 1:
The patent transitions from 2D image processing to 3D point cloud processing by incorporating depth information from a depth camera. This dimensional change enables accurate charge port localization by utilizing the third dimension (depth) to compensate for the lack of distinctive 2D geometric features on the vehicle body surface.
Solution Approach 2:
The patent introduces a reference feature (such as a marker or distinctive vehicle component) as an intermediary element to facilitate charge port localization. This reference feature serves as a mediator between the vision system and the charge port, providing identifiable geometric characteristics that enable accurate pose estimation through coordinate transformation.
2Measurement precision
If multiple camera systems with depth sensing are integrated, then the measurement precision improves, but the device complexity increases
Solution Approach 1:
The patent combines 2D image data from a standard camera with 3D depth data from a depth camera into a unified point cloud representation. This merging of multiple data sources creates a comprehensive 3D model of the vehicle surface, enabling accurate charge port localization while leveraging the complementary strengths of different sensing modalities.
Solution Approach 2:
The patent creates a digital 3D copy of the vehicle surface and charge port geometry through point cloud reconstruction. This digital replica serves as a virtual model that can be processed and analyzed without physically interacting with the actual vehicle, enabling precise pose estimation through computational geometry operations.
3Measurement precision
If 3D point cloud processing is used instead of 2D image processing, then the measurement precision improves, but the processing time increases
Solution Approach 1:
The patent segments the 3D point cloud data into distinct regions corresponding to the vehicle body surface and the charge port feature. This segmentation allows the system to focus computational resources on processing only the relevant portions of the point cloud, reducing overall processing time while maintaining high measurement precision for charge port localization.
Solution Approach 2:
The patent performs preliminary processing of the point cloud data by filtering, downsampling, and organizing the 3D points into structured formats before conducting the actual charge port detection. These preliminary actions prepare the data in advance, making subsequent pose estimation computations more efficient and reducing real-time processing requirements.
Data Source
AI summary
The invention is notably directed to a computer-implemented method for automatically charging an electric vehicle via an end effector (10) of a robotic arm (40) of an automated vehicle charging robot. The end effector is assumed to be structured so as to be able to connect to a charge port (220) of a vehicle. In addition, the automated vehicle charging robot further includes a camera system (102) having depth sensing capability. The method comprises the following steps. First, a reference position of a reference feature (210) of the vehicle is estimated thanks to the camera system. Next, a pose of the charge port of the vehicle is determined based on the estimated reference position. The robotic arm is subsequently instructed to actuate the end effector, based on the determined pose of the charge port, to connect the end effector to the charge port with a view to charging the vehicle. The reference position is estimated as follows. Both a 2D image and a depth image of a surface portion of the vehicle are obtained. This surface portion includes the reference feature, i.e., the feature of interest. Contour points of the reference feature are then extracted from the 2D image obtained. The 3D coordinates of the extracted contour points are subsequently reconstructed based on the depth image obtained. A geometric object (such a 2D plane) is then matched to the reconstructed 3D coordinates, e.g., by fitting the geometric object to the reconstructed 3D coordinates. Eventually, the reference position of the reference feature is determined based on the matched geometric object. The invention is further directed to related automated vehicle charging robots and computer program products.