A Hybrid Learning and Optimization Framework to Achieve Physically Interactive Tasks with Mobile Manipulators

TL;DR

This paper introduces a hybrid learning and optimization framework enabling mobile manipulators to perform complex, physically interactive tasks more effectively by combining human demonstrations, probabilistic modeling, and online impedance parameter optimization.

Contribution

It presents a novel framework integrating human demonstrations, GMM/GMR encoding, and online impedance tuning to improve interactive task performance of mobile manipulators.

Findings

Outperforms constant stiffness approaches in trajectory tracking

Generates more accurate interaction forces

Maintains system passivity during interactions

Abstract

This paper proposes a hybrid learning and optimization framework for mobile manipulators for complex and physically interactive tasks. The framework exploits an admittance-type physical interface to obtain intuitive and simplified human demonstrations and Gaussian Mixture Model (GMM)/Gaussian Mixture Regression (GMR) to encode and generate the learned task requirements in terms of position, velocity, and force profiles. Next, using the desired trajectories and force profiles generated by GMM/GMR, the impedance parameters of a Cartesian impedance controller are optimized online through a Quadratic Program augmented with an energy tank to ensure the passivity of the controlled system. Two experiments are conducted to validate the framework, comparing our method with two approaches with constant stiffness (high and low). The results showed that the proposed method outperforms the other two cases in terms of trajectory tracking and generated interaction forces, even in the presence of disturbances such as unexpected end-effector collisions.