Robot-Carried Object Referencing for Accurate Post-Grasp Pose
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional robotics systems struggle with accurately determining the pose of objects after they have been grasped, leading to inaccuracies and potential collisions or safety issues due to unpredictable shifting of objects during handling.
Innovation Solution
The system employs a method that includes using information about an expected object pose, repositioning the object for better perception data, and processing estimates from a neural network to generate accurate object references, utilizing three-dimensional information to register a known model with real-time pose data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional robotics systems use standard object detection methods, then the system complexity remains manageable, but the measurement precision of object pose after grasping deteriorates due to unpredictable object shifting
Solution Approach 1:
The system performs preliminary actions by capturing perception data of the object before grasping and generating an initial object reference. This pre-grasping measurement is stored and later used to predict object pose during carrying, avoiding the need for continuous complex measurements while maintaining accuracy despite object shifting.
Solution Approach 2:
The system introduces an intermediary object reference that decouples the direct dependency between the object and the robot's coordinate system. This reference acts as a mediator that tracks the object's pose independently, allowing accurate pose estimation without requiring complex real-time sensing during carrying operations.
2Reliability
If the system continuously monitors object position during carrying, then the reliability of object handling improves, but the loss of time for data processing and the increased device complexity worsen
Solution Approach 1:
The system performs the complex perception and object reference generation actions before grasping occurs. This preliminary processing captures all necessary spatial information in advance, eliminating the need for continuous real-time monitoring during object carrying, thus reducing processing time while maintaining reliability.
Solution Approach 2:
The system uses the pre-generated object reference to self-update the object pose prediction during carrying without requiring external continuous intervention. The prediction module autonomously maintains accurate pose estimation using the initial reference and robot state information, reducing the need for additional sensing and processing resources.
3Measurement precision
If the system uses detailed perception data for object pose estimation, then the measurement precision improves, but the difficulty of detecting and measuring the object worsens due to object shifting during grasping
Solution Approach 1:
The system captures detailed perception data and generates accurate object references before the object is grasped and potential shifting occurs. This timing ensures that the measurement is taken when the object is stationary and easily detectable, avoiding the difficulties of measuring a moving or shifting object during carrying.
Data Source
AI summary
A method in accordance with a particular embodiment of the present technology includes retrieving an object from a starting location by grasping the object between two end effectors of a mobile robot. The method further includes generating, by data-processing hardware operably associated with the mobile robot, an object reference corresponding to a pose of the object at a time after retrieving the object and while the object is in contact with the end effectors. Generating the object reference is based at least partially on perception data corresponding to the object and includes generating a three-dimensional reference corresponding to a feature of the object based at least partially on a two-dimensional estimate from a neural network and a three-dimensional reference corresponding to a different feature of the object. Finally, the method includes controlling the mobile robot based at least partially on the object reference.