Integration of perception capabilities in gripper design using graspability maps

Agricultural environments impose high demands on robotic grippers since the objects to be grasped (e.g., fruit) suffer from inherent uncertainties in size, shape, weight, and texture, are typically highly sensitive to excessive force, and tend to be partly or fully occluded. This paper presents a methodology for evaluating the influence of perception capabilities on grasping and on gripper design using graspability maps. Graspability maps are spatial representations of grasp quality grades from wrist poses (position and orientation) about an object and are generated using simulation. A new module was developed to enable the insertion of object pose errors for testing the effects of perception inaccuracies on grasping. The methodology was implemented for comparing two grippers (Fin-Ray and Lip-type) for harvesting two sweet-pepper cultivars. A 3D model of each gripper was constructed and suitable grasp quality measures were developed and validated in a physical environment. Task and gripper-specific grasp quality measures were developed for each implementation. Sensitivity analyses included varying pepper dimensions and perception inaccuracies. These were followed by analyses of the influence of gripper design parameters on grasp capabilities. Results indicate that the Lip-type gripper is less sensitive to inaccuracies in object orientation, while both grippers are similarly sensitive to inaccuracies in object position. Specific perception system demands and design recommendations are given for each gripper, and cultivar. The results illustrate the importance of integrating perception analysis in the gripper design phase and the utility of the graspability simulation tool for design analysis.