Mechanisms and Computational Design of Multi-Modal End-Effector with Force Sensing using Gated Networks

TL;DR

MAGPIE addresses the need for a single end-effector that can function as both a foot and a grasping hand in limbed robots. It combines a multi-axis Hall-effect sensing mechanism with a computational design framework to tailor flexure, magnet, and sensor parameters, while accounting for nonlinearities and magnetic disturbances. Hardware validation, including GRBF-based ideal modeling and stacked GRU force estimation, demonstrates robust eight-axis force sensing and reliable foot-grasping performance with both flat and line configurations. The approach offers scalable, off-the-shelf sensing design and data-driven uncertainty handling, enabling more capable and versatile legged robots for locomotion and manipulation tasks.

Abstract

In limbed robotics, end-effectors must serve dual functions, such as both feet for locomotion and grippers for grasping, which presents design challenges. This paper introduces a multi-modal end-effector capable of transitioning between flat and line foot configurations while providing grasping capabilities. MAGPIE integrates 8-axis force sensing using proposed mechanisms with hall effect sensors, enabling both contact and tactile force measurements. We present a computational design framework for our sensing mechanism that accounts for noise and interference, allowing for desired sensitivity and force ranges and generating ideal inverse models. The hardware implementation of MAGPIE is validated through experiments, demonstrating its capability as a foot and verifying the performance of the sensing mechanisms, ideal models, and gated network-based models.

Figures (9)

• Figure 1: MAGPIE Hardware and Design Rendering in an isometric view.
• Figure 2: Computational design framework for the Hall effect-based multi-axis force sensing overview. The framework simulated the sensing to design for a desired sensitivity and force range. The framework generates an ideal model using Gaussian radial basis functions. A gated recurrent unit is employed to improve the force measurements and provide uncertainty in the sensing, such as an external significant magnetic field.
• Figure 3: The force sensing mechanism configuration in the hardware. The red and blue flexures are for ground contact and grasping force sensing, respectively. The magnet is attached on the longitudinal, and the sensor is on the lateral side to better isolate the impact forces from the sensor.
• Figure 4: Sensor and magnet placements, and deflection state with forces.
• Figure 5: Circuitry and sensors of the MAGPIE control unit.