Technology Category
Intelligent Robots: State EstimationPlanning, Routing, and Scheduling: Activity and Plan RecognitionMachine Learning: Calibration & Uncertainty Quantification
Estimation of Payload Inertial Parameters from Human Demonstrations by Hand Guiding
🤖 AI Summary
Non-programming users face significant challenges in efficiently teaching contact-based tasks to collaborative robots.
Method: This paper proposes a novel online method for estimating the payload inertial parameters (PIPs)—including mass, center of mass, and inertia tensor—of end-effectors without requiring dedicated calibration. Leveraging the naturally occurring non-contact motion phases during hand-guided teaching, the approach integrates recursive least-squares estimation with excitation condition analysis. It automatically identifies dynamically informative trajectory segments directly from teaching data, enabling simultaneous PIP identification within a rigid-body dynamics framework.
Contribution/Results: Experimental validation demonstrates high accuracy in mass estimation; centroid and inertia tensor estimates are shown to depend critically on excitation sufficiency—particularly acceleration-rich motion—confirming the essential role of dynamic excitation. To our knowledge, this is the first method unifying contact-task programming with online PIP identification. It substantially lowers the operational barrier for non-expert users, enhances tool-change flexibility, and improves system deployment efficiency.
Technology Category
Application Category
📝 Abstract
As the availability of cobots increases, it is essential to address the needs of users with little to no programming knowledge to operate such systems efficiently. Programming concepts often use intuitive interaction modalities, such as hand guiding, to address this. When programming in-contact motions, such frameworks require knowledge of the robot tool's payload inertial parameters (PIP) in addition to the demonstrated velocities and forces to ensure effective hybrid motion-force control. This paper aims to enable non-expert users to program in-contact motions more efficiently by eliminating the need for a dedicated PIP calibration, thereby enabling flexible robot tool changes. Since demonstrated tasks generally also contain motions with non-contact, our approach uses these parts to estimate the robot's PIP using established estimation techniques. The results show that the estimation of the payload's mass is accurate, whereas the center of mass and the inertia tensor are affected by noise and a lack of excitation. Overall, these findings show the feasibility of PIP estimation during hand guiding but also highlight the need for sufficient payload accelerations for an accurate estimation.
Problem
Research questions and friction points this paper is trying to address.
Estimates payload inertial parameters from human demonstrations
Enables non-expert programming of in-contact motions
Uses non-contact motion parts for parameter estimation
Innovation
Methods, ideas, or system contributions that make the work stand out.
Estimates payload inertial parameters from hand guiding
Uses non-contact motions for parameter estimation
Eliminates need for dedicated PIP calibration
🔎 Similar Papers
No similar papers found.
