End-to-End Intelligent Adaptive Grasping for Novel Objects Using an Assistive Robotic Manipulator

摘要

This paper presents the design and implementation of the motion controller and adaptive interface for the second generation of the UCF-MANUS intelligent assistive robotic manipulator system. Based on extensive user studies of the system, several features were implemented in the interface that could reduce the complexity of the human–robot interaction while also compensating for the deficits in different human factors, such as working memory, response inhibition, processing speed, depth perception, spatial awareness, and contrast sensitivity. To effectively and safely control the robotic arm, we designed several new features, including an adaptive human–robot interaction framework. To provide the user with a less complex and safer interaction with the robot, we added new functionalities such as ‘One-click mode’, ‘Move suggestion mode’, and ‘Gripper Control Assistant’. Furthermore, to equip our assistive robotic system with an adaptive User Interface, we designed and implemented compensators such as ‘Contrast Enhancement’, ‘Object Proximity Velocity Reduction’, and ‘Orientation Indicator’. Results from a multitude of experiments show that the system is indeed robust, safe, and computationally efficient in addition to addressing the user’s highly desired capabilities.