Legged Robot Docking Pose Correction With Feature Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Battery-powered legged robots face challenges in reliably docking with charging stations due to imperfect sensing, which can lead to energy depletion and potential damage, especially in remote environments where recovery is difficult.
Innovation Solution
A computer-implemented method that uses sensor data to determine an estimated pose for the docking station, identifies and matches docking station features, and adjusts the pose for accurate alignment, generating a docking station map to avoid obstacles and ensure safe docking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the robot uses initial pose estimation for docking, then the docking process can be initiated, but the docking accuracy is insufficient due to imperfect sensing
Solution Approach 1:
The system captures images of the docking station, identifies features in the images, compares them with known docking station features, and uses this feedback to calculate a corrected pose that compensates for initial estimation errors and imperfect sensing
Solution Approach 2:
The system performs preliminary pose estimation before docking, then refines this estimate by identifying docking station features in advance and calculating corrections based on the comparison between observed and expected feature orientations
2Measurement precision
If the robot relies on imperfect sensing alone, then the system complexity remains low, but docking accuracy deteriorates leading to potential damage
Solution Approach 1:
The system introduces an image capture device as an intermediary between the robot's sensing system and the docking station, using visual feature identification and comparison as a mediator to achieve higher docking accuracy without requiring complex sensor systems
3Reliability
If the robot does not generate terrain information, then the processing load is reduced, but safe docking cannot be ensured in complex environments
Solution Approach 1:
The system performs preliminary capture of images of the docking station and generates terrain information and foot placement constraints in advance, before the actual docking operation, allowing safe docking to be ensured without adding complexity to the real-time docking process
Data Source
AI summary
A computer-implemented method when executed by data processing hardware of a legged robot causes the data processing hardware to perform operations including receiving sensor data corresponding to an area including at least a portion of a docking station. The operations include determining an estimated pose for the docking station based on an initial pose of the legged robot relative to the docking station. The operations include identifying one or more docking station features from the received sensor data. The operations include matching the one or more identified docking station features to one or more known docking station features. The operations include adjusting the estimated pose for the docking station to a corrected pose for the docking station based on an orientation of the one or more identified docking station features that match the one or more known docking station features.