Legged Robot Docking with Feature-Based Pose Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robots with imperfect sensing face challenges in reliably docking with charging stations, especially legged robots which require precise leg coordination and terrain awareness to avoid obstacles and ensure safe docking.
Innovation Solution
A computer-implemented method for a legged robot that receives sensor data, determines an estimated pose for the docking station, identifies and matches docking station features to known features, and adjusts the pose for accurate docking, generating a docking station map to avoid hazardous regions and ensure successful charging.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If robots use imperfect sensing to detect docking stations, then they can operate in varied environments, but docking reliability deteriorates due to pose estimation errors
Solution Approach 1:
The patent introduces an intermediary feature matching process between the robot's sensor data and the docking station's known features. This intermediary step refines the pose estimation by comparing detected features (e.g., alignment towers, contact terminals) with pre-stored feature models, acting as a mediator that improves docking reliability without requiring perfect sensing
Solution Approach 2:
The system implements feedback by continuously comparing the robot's current pose estimation with the known docking station features and adjusting the pose accordingly. The feature matching process provides feedback on alignment accuracy, allowing the robot to correct its position and achieve reliable docking despite imperfect sensing
2Manufacturing precision
If legged robots perform precise leg coordination for docking, then docking accuracy improves, but the complexity of control increases
Solution Approach 1:
The patent applies preliminary action by pre-storing the geometric features and pose information of the docking station in advance. This allows the robot to perform feature matching and pose correction without complex real-time calculations during the actual docking process, reducing control complexity while maintaining high docking accuracy
Solution Approach 2:
The docking process is segmented into distinct phases: initial pose determination based on sensor data, feature identification and matching, and final pose correction. This segmentation allows each phase to be handled with appropriate control complexity, improving overall docking accuracy without requiring uniformly high complexity throughout the entire process
3Object-affected harmful factors
If robots generate detailed docking station maps to avoid obstacles, then safety improves, but the processing time and computational load increase
Solution Approach 1:
The patent applies local quality by generating docking station maps with varying levels of detail in different regions. Critical areas such as alignment towers and contact terminals are mapped with high precision to ensure safe docking, while less critical areas use coarser resolution, reducing overall processing time and computational load while maintaining safety
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.