Optimizing robot grasping using soft origami zigzag gripper with artificial intelligence

Abstract

The covid-19 pandemic leads to an increased need for automation in food industries. Current soft robots require cast moulding, high assembly effort, large actuators, and upfront actuation awareness due to the absence of artificial intelligence. Soft origami structures exhibit high levels of compliance. We developed a 3D print-in-place under-actuated soft origami zigzag gripper using TPU with artificial intelligence object pose estimation to grasp objects with high repeatability of success under different conditions. A self-designed 3D robot arm is used for object grasping. Grasping performance tests were conducted using different gripper designs, robot arm speed, and gripping force on objects with different masses and morphology. The soft origami zigzag gripper has better-grasping performance than the hard gripper as analyzed by paired t-test. The logistic model of the soft origami zigzag gripper’s grasping performance achieved an accuracy of 0.940 and AUC=0.911. Jetson Nano running AI CNN Resnet18, enhanced grasping performance with vision object classification achieved an accuracy of 0.923 and F1 score of 0.956. The AI CNN MobileNetV2 is used for object classification and experimental results showed it had lower accuracy as compared to the AI CNN Resnet18. The object classification using artificial intelligence optimized the robot grasping to improve automation in food processing and food handling to avoid contamination. All these can be used in the automation process in the food industry to overcome health and safety challenges.