Designing Prosthetic Hands With Embodied Intelligence: The KIT Prosthetic Hands

Abstract

Hand prostheses should provide functional replacements of lost hands. Yet current prosthetic hands often are not intuitive to control and easy to use by amputees. Commercially available prostheses are usually controlled based on EMG signals triggered by the user to perform grasping tasks. Such EMG-based control requires long training and depends heavily on the robustness of the EMG signals. Our goal is to develop prosthetic hands with semi-autonomous grasping abilities that lead to more intuitive control by the user. In this paper, we present the development of prosthetic hands that enable such abilities as first results toward this goal. The developed prostheses provide intelligent mechatronics including adaptive actuation, multi-modal sensing and on-board computing resources to enable autonomous and intuitive control. The hands are scalable in size and based on an underactuated mechanism which allows the adaptation of grasps to the shape of arbitrary objects. They integrate a multi-modal sensor system including a camera and in the newest version a distance sensor and IMU. A resource-aware embedded system for in-hand processing of sensory data and control is included in the palm of each hand. We describe the design of the new version of the hands, the female hand prosthesis with a weight of 377 g, a grasping force of 40.5 N and closing time of 0.73 s. We evaluate the mechatronics of the hand, its grasping abilities based on the YCB Gripper Assessment Protocol as well as a task-oriented protocol for assessing the hand performance in activities of daily living. Further, we exemplarily show the suitability of the multi-modal sensor system for sensory-based, semi-autonomous grasping in daily life activities. The evaluation demonstrates the merit of the hand concept, its sensor and in-hand computing systems.

Explorations of Autonomous Prosthetic Grasping via Proximity Vision and Deep Learning

“…Lastly, Starke et Al. recently presented a semi-autonomous control strategy for object recognition and grasp selection via RGB camera, inertial and distance sensors, directly interfaced with the user via a display and a single myoelectric channel, completely self-contained within the KIT robotic hand [28], [29].…”

Shoulder Movement-Centered Measurement and Estimation Scheme for Underarm-Throwing Motions

“…However, people with profound weakness, spasticity, athetosis, or deformity in the upper limbs struggle to control their hands to hold or release a ball using their fingers with proper timing. Typical aids for them include hand orthoses [7][8][9] and prosthetic hands [10][11][12]. Although people intend these aids for daily life activities, they are not suitable for assisting throws that require fine or agile coordination [13,14].…”

Modular Design, Communication and Control Systems of a 3D-printed Humanoid Robotic Hand

“…Motors with small dimensions and less mass are preferred. In the literature are described prostheses with different types of actuators: linear motors [6,10]; servo motors [11]; DC motors [5,9]; and pneumatic cylinders [12,13]. Important parameters of actuators that are investigated are: minimum and maximum speed, accuracy, repeatability, dimensions, weight and cost [3].…”