K-VARK: Kernelized Variance-Aware Residual Kalman Filter for Sensorless Force Estimation in Collaborative Robots

TL;DR

K-VARK introduces a kernelized, variance-aware Kalman filter that improves sensorless force estimation in collaborative robots by modeling residual torques with probabilistic, input-dependent variance, leading to more accurate and robust force estimation.

Contribution

The paper presents K-VARK, a novel kernelized, probabilistic residual Kalman filter that adaptively models residual torques with heteroscedastic variance for sensorless force estimation.

Findings

Achieves over 20% reduction in RMSE compared to existing methods.

Provides robust and accurate external force estimation for complex tasks.

Effectively handles dynamic disturbances through online covariance adaptation.

Abstract

Reliable estimation of contact forces is crucial for ensuring safe and precise interaction of robots with unstructured environments. However, accurate sensorless force estimation remains challenging due to inherent modeling errors and complex residual dynamics and friction. To address this challenge, in this paper, we propose K-VARK (Kernelized Variance-Aware Residual Kalman filter), a novel approach that integrates a kernelized, probabilistic model of joint residual torques into an adaptive Kalman filter framework. Through Kernelized Movement Primitives trained on optimized excitation trajectories, K-VARK captures both the predictive mean and input-dependent heteroscedastic variance of residual torques, reflecting data variability and distance-to-training effects. These statistics inform a variance-aware virtual measurement update by augmenting the measurement noise covariance, while the process noise covariance adapts online via variational Bayesian optimization to handle dynamic disturbances. Experimental validation on a 6-DoF collaborative manipulator demonstrates that K-VARK achieves over 20% reduction in RMSE compared to state-of-the-art sensorless force estimation methods, yielding robust and accurate external force/torque estimation suitable for advanced tasks such as polishing and assembly.