Coordinate-Independent Robot Model Identification

2026-03-15

AI Summary

This work proposes a coordinate-invariant framework for robot dynamics identification that overcomes biases inherent in traditional methods due to arbitrary choices of coordinate systems, units, and scales. By leveraging the dual metric induced by the system’s Riemannian metric, the approach normalizes generalized force residuals and maps them back onto the robot’s configuration space, thereby eliminating coordinate dependence. The method innovatively employs this dual metric to achieve physically meaningful force normalization while preserving convexity of the objective function through an affine metric formulation and Schur complement-based reconstruction. It further accommodates physical consistency constraints and geometric regularization. Experimental validation on both a Crazyflie–pendulum system and a LandSalp robot demonstrates substantial improvements in identification accuracy across both high- and low-data regimes, with particularly notable gains in shape coordinates.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Natural Language Processing: Safety and Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Robot model identification is commonly performed by least-squares regression on inverse dynamics, but existing formulations measure residuals directly in coordinate force space and therefore depend on the chosen coordinate chart, units, and scaling. This paper proposes a coordinate-independent identification method that weights inverse-dynamics residuals by the dual metric induced by the system Riemannian metric. Using the force--velocity vector--covector duality, the dual metric provides a physically meaningful normalization of generalized forces, pulling coordinate residuals back into the ambient mechanical space and eliminating coordinate-induced bias. The resulting objective remains convex through an affine-metric and Schur-complement reformulation, and is compatible with physical-consistency constraints and geometric regularization. Experiments on an inertia-dominated Crazyflie--pendulum system and a drag-dominated LandSalp robot show improved identification accuracy, especially on shape coordinates, in both low-data and high-data settings.

Problem

• robot model identification
• coordinate dependence
• inverse dynamics
• residual bias
• generalized forces

Innovation

• coordinate-independent identification
• dual metric
• Riemannian metric
• inverse dynamics
• convex optimization