SoftTouch: A Sensor-Placement Framework for Soft Robotic Hands

Abstract

Sensor placement for grasping tasks in conventional robotic hands has been extensively studied, with goals including sensorizing essential contact areas or determining the effect of number of sensors on performance. However, with the new generation of dexterous soft robotic hands that deform to the shape of the object, the former frameworks may not be sufficient. In particular, we find that real-world experiments are essential to determine the value of different sensors and the effect of different sensor placements due to the complex interactions between the deformable robot body, sensor material properties, and sensor and task performance. In this paper, we propose a sensor-placement framework for dexterous soft robotic hands that is easily reconfigurable to different hand designs using off-the-shelf sensors. Our three-step framework selects and evaluates candidate sensor configurations to de-termine the effectiveness of sensors in each configuration for estimating qualitative and quantitative manipulation metrics. We tested our framework on a soft robotic hand to select the optimum sensor placement for a given set of manipulation patterns using force and inertial sensors. Our studies show that sensors placed at contact points are best for predicting the qualitative success of the manipulation. However, when it comes to estimating quantitative manipulation metrics, off-the-shelf sensors placed at contact points decrease performance for some manipulation types. This performance decrease may be due to the disturbance they create to surface texture, deformation patterns, and weight of soft robotic systems.