aiqbench analysis
This paper introduces K-VARK, an advanced algorithm that combines kernel methods with adaptive Kalman filtering to improve sensorless force estimation in collaborative robots. By modeling residual torque dynamics and adjusting noise covariances online, the approach achieves significant accuracy gains for tasks like polishing without requiring external sensors. The work represents a meaningful step forward in applying probabilistic machine learning techniques to enhance robotic safety and precision control.
K-VARK: Kernelized Variance-Aware Residual Kalman Filter for Sensorless Force Estimation in Collaborative Robots
arXiv:2512.13009v2 Announce Type: replace 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.
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.
Robotics (cs.RO)
arXiv:2512.13009 [cs.RO]
(or arXiv:2512.13009v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2512.13009 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 257 words
Related coverage
Benchmarking Kimi-K3 Across vLLM, SGLang, and ATOM on MI350X
AMD · Sep 22, 2026
J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses
LessWrong · Oct 8, 2026
Generalized Gaussian Temporal Difference Error for Uncertainty-aware Reinforcement Learning
arXiv · Jul 28, 2026
Productionizing TurboQuant on AMD GPUs for KV-Cache-Bound LLM Inference
AMD · Jun 11, 2026