Multifingered force-aware control for humanoid robots

TL;DR

This paper designs a controller that adapts the motion of the torso, arm, wrist, and fingers, redistributing forces to maintain stable contact with objects of varying mass distribution or unstable contacts, and introduces a model-based control scheme that minimizes the distance between the Center of Pressure and the centroid of the fingertips contact polygon.

Abstract

In this paper, we address force-aware control and force distribution in robotic platforms with multi-fingered hands. Given a target goal and force estimates from tactile sensors, we design a controller that adapts the motion of the torso, arm, wrist, and fingers, redistributing forces to maintain stable contact with objects of varying mass distribution or unstable contacts. To estimate forces, we collect a dataset of tactile signals and ground-truth force measurements using five Xela magnetic sensors interacting with indenters, and train force estimators. We then introduce a model-based control scheme that minimizes the distance between the Center of Pressure (CoP) and the centroid of the fingertips contact polygon. Since our method relies on estimated forces rather than raw tactile signals, it has the potential to be applied to any sensor capable of force estimation. We validate our framework on a balancing task with five objects, achieving a $82.7\%$ success rate, and further evaluate it in multi-object scenarios, achieving $80\%$ accuracy. Code and data can be found here https://github.com/hsp-iit/multifingered-force-aware-control.

Figures (6)

• Figure 1: Real robot (left) and its virtual counterpart RerunSDK (right). ergoCub, equipped with tactile sensors, balances a tray with an unknown object by minimizing the distance between the supporting polygon center and the estimated Center of Pressure (cyan sphere), computed from normal forces (orange arrows).
• Figure 2: Overview of the control pipeline. Finger positions (magenta spheres) are projected onto the plane (yellow rectangle), and normal force components (orange arrows) are used to compute the CoP (cyan sphere) in the plane frame. From this, a new target pose for the plane is generated, and finger and joint positions are updated with a corrective term for inaccuracies.
• Figure 3: a) Data collection setup. b) Indenters. c) Effect of hysteresis on the tactile readings. The graphic above shows the indented force (N) over time (s), while the bottom graphic shows the output of the sensor's taxel over time.
• Figure 4: Consistency validation across sensors shows variability in tactile outputs under identical applied forces.
• Figure 5: Starting position on the tray. The superimposed hand shows the position of the hand under the tray.