Using Tactile Sensing to Improve Performance when Grasping Moving Objects

Abstract

To operate in unstructured settings, robots require control strategies that effectively respond to temporal changes in their environment. In the domain of robotic manipulation, most state-of-the-art approaches assume the objects to be grasped are static. Although some research has investigated the challenges of grasping moving objects, these studies have tended to use grasping plans which require a real-time estimate of a gripper-object interception point, which can be difficult to precisely obtain. The goal of this research was to investigate the performance benefits of using a controller with a reactive component for grasping tasks involving moving objects. We hypothesised that using a reactive control strategy, based on tactile sensing in the fingertips, would lead to improved performance and robustness across a wider range of grasping conditions. To test this hypothesis, the ability of a two-finger gripper to grasp a moving ball under a range of dynamic conditions was tested in simulation using the Gazebo robotic simulator and ODE physics engine. Tests revealed that for controllers where the grasp was not informed by tactile sensing, grasping success dropped significantly with increased misalignment between the centre point of the gripper and the point of interception with the moving object. In contrast, the performance of a reactive grasping strategy based on tactile sensing was found to be more robust across these conditions. These findings indicate that tactile sensing could play an important role in enabling robots to interact more effectively with dynamic objects.