Due to less appropriate sensors for representing the pose of soft robotic hand, the soft robotic hand usually works in an open loop control system. In this paper, only two simple sensors were used in a soft pneumatic gripper (SPG) control system to make it possess innervated-like ability. The control system was conducted with only two sensors, air pressure sensor and bending sensor where the air pressure sensor is able to detect grasping force and the bending sensor is able to detect grasping position The bending sensor was characterized by testing on pressure vs. bending and bending vs. size relationships. The principle of circular-shaped object size recognition was presented in Algorithm 1. Multi-group tests had been done on grasping different size and material objects, and test results had a strong effect on size recognition ability of the SPG. Finally, adaptive grasping control process was presented in Algorithm 2. The tests on grasping the same size objects had been done. The test results demonstrate that the SPG is able to maintain stable grasping state for a long time based on size recognition ability no matter what material the object is. At the same time, it had no effect on the grasping state at the time of existing disturbance, which had been verified by four different disturbance tests. The SPG will benefit the development of soft robotics field in picking and sorting fruits and vegetables, and an application of the SPG affixed on the home-made palletizing robot was described and conducted at last.
Read full abstract