Tactile sensing enables secure gentle robot grasping of unknown objects
Tactile Sensing-based Secure and Gentle Grasping of Unknown Objects
Robotics
Summary
Grasping objects safely and firmly without breaking or dropping them is hard for robots, especially when the objects are new and unknown. The authors present a system where a robot uses touch sensors on its gripper to feel and adjust its hold in real time, learning how much force to apply without prior object knowledge. This method uses smart predictions to avoid slipping or damaging the object during dynamic handling. Their approach works well on delicate items like tofu and marshmallows as well as rough objects like rocks.
What this means in practice
- •For robotics engineers: Develop robot grippers that safely handle unknown and delicate items by using tactile sensing and online force control during dynamic manipulation.
- •For automation system integrators: Integrate tactile-based grasp control to improve the handling safety and reliability of robotic arms in flexible manufacturing lines with unknown object types.
Authors
Feng Han
Abstract
Reliable robotic manipulation requires maintaining a firm grasp while strictly avoiding both contact slip and structural damage to the object. Satisfying these inherent \textit{secure-and-gentle} grasping constraints is challenging for unknown objects. We present a novel online data-driven predictive control framework for safe dynamic robotic grasping of unknown objects. The proposed system features a pair of compact, single-channel tactile-sensing modules that characterize the gripper-object dynamic interaction in real time, entirely bypassing the need for prior knowledge or offline training. A finite-state-machine-based grasping force probing mechanism is developed to establish the initial grasping force and explicitly identify grasping force constraints. Through online dynamics learning, a Gaussian Process (GP) model captures gripper-object interaction dynamics. The model uncertainties are further used to form robust grasping constraints, which are embedded into a model predictive control scheme. We demonstrate error convergence in a probabilistic sense. The proposed control framework runs at 100~Hz in real time to dynamically manipulate and handle objects rather than static holding. Extensive experimental evaluations across diverse contact surface topologies and various types of objects validate superior performance and efficiency compared to baseline strategies. The proposed method is able to manipulate objects ranging from delicate items, such as raw tofu and marshmallows, to rough objects, such as rocks.