EV Charging Socket Pose Estimation for Precise Robot Coupling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electric vehicle charging robots face difficulties in accurately estimating the orientation of charging sockets due to various types and complex shapes, which hinders precise alignment and coupling of charging connectors.
Innovation Solution
A method and device using RGB images and depth maps, employing neural networks for keypoint detection and pose estimation, derive an initial and optimal transformation matrix to accurately estimate the pose of the charging socket, regardless of its shape, enabling precise alignment and coupling by an autonomous charging robot.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional image-based orientation estimation methods are used for charging sockets, then the system is simple and low-cost, but the estimation accuracy deteriorates due to various socket types and complex shapes
Solution Approach 1:
The patent segments the charging socket detection task into multiple components: keypoint detection network identifies specific feature points on the socket, pose estimation network determines orientation from these keypoints, and depth information provides spatial context. This segmentation allows each component to specialize in one aspect, improving overall accuracy while maintaining manageable system complexity
Solution Approach 2:
The patent incorporates depth information from depth maps as an additional dimension beyond traditional 2D RGB images. This third dimension provides spatial context that helps distinguish between different socket types and orientations, significantly improving measurement precision for orientation estimation without requiring complex multi-sensor systems
2Manufacturing precision
If the charging robot uses accurate pose estimation to precisely align the charging connector, then the coupling accuracy improves, but the operational time increases due to complex processing
Solution Approach 1:
The patent performs preliminary action by pre-training the keypoint detection and pose estimation networks offline before actual charging operations. During real-time operation, the already-trained models quickly process images and depth maps, providing accurate pose estimates without requiring complex runtime computations. This separates the computationally intensive training phase from the time-critical execution phase
Solution Approach 2:
The patent replaces traditional mechanical alignment methods with vision-based pose estimation. Instead of using complex mechanical sensors and actuators to achieve precise alignment, the system uses neural networks to estimate socket pose from images and depth maps, then guides the robotic arm accordingly. This substitution reduces operational time while maintaining high coupling accuracy
Data Source
AI summary
The present disclosure provides is a method and device for accurately estimating a pose of a charging socket of an electric vehicle regardless of a shape of the charging socket, so that an electric vehicle charging robot may precisely move a charging connector toward the charging socket of the electric vehicle and couple the charging connector to the charging socket. According to an aspect of an exemplary embodiment, a method of estimating the pose of the charging socket of an electric vehicle includes: acquiring an RGB image and a depth map of the charging socket; detecting a keypoint of the charging socket based on the RGB image; deriving a first estimated pose of the charging socket based on the depth map; and deriving a second estimated pose of the charging socket based on the keypoint of the charging socket and the first estimated pose.