Underactuated Anthropomorphic Hand Research Articles

Deep learning-based control framework for dynamic contact processes in humanoid grasping.

Humanoid grasping is a critical ability for anthropomorphic hand, and plays a significant role in the development of humanoid robots. In this article, we present a deep learning-based control framework for humanoid grasping, incorporating the dynamic contact process among the anthropomorphic hand, the object, and the environment. This method efficiently eliminates the constraints imposed by inaccessible grasping points on both the contact surface of the object and the table surface. To mimic human-like grasping movements, an underactuated anthropomorphic hand is utilized, which is designed based on human hand data. The utilization of hand gestures, rather than controlling each motor separately, has significantly decreased the control dimensionality. Additionally, a deep learning framework is used to select gestures and grasp actions. Our methodology, proven both in simulation and on real robot, exceeds the performance of static analysis-based methods, as measured by the standard grasp metric Q1. It expands the range of objects the system can handle, effectively grasping thin items such as cards on tables, a task beyond the capabilities of previous methodologies.

Design optimization of an underactuated tendon-driven anthropomorphic hand based on grasp quality measures

AbstractFor an underactuated anthropomorphic hand, apart from replicating the geometry, biomimicry of human counterpart requires design based on functional biomimesis. Optimization based on grasping capabilities to generate a stable grasp for underactuated anthropomorphic hands has been a recent focus. In this article, we optimize the actuation parameters of the underactuated mechanism based on grasp quality measures. Optimization of the hand design parameters like pulley radii, spring stiffnesses, and pre-load angles was undertaken based upon the grasp robustness metric. A quasi-static model based on a soft synergistic compliant grasp of the underactuated hand is formalized. Numerical simulations based on evolutionary strategies are applied to the grasp model to optimize the underactuated parameters. Finally, validation of the results based on the grasp wrench space is presented. The results show that an anthropomorphic hand with an optimized underactuated mechanism performs better grasps.

Teleoperation of the SCHUNK S5FH under-actuated anthropomorphic hand using human hand motion tracking

This paper describes the development of a remote handling control of an anthropomorphic robotic hand, the SCHUNK S5FH, using the human hand as master by measuring its motion with OptiTrack Technology. The goal of this work is to enhance manipulation studies on the human hand and to instantly transfer those studies on robotic hands. A preliminary study on methods and devices used for fingers tracking led to the choice of a simplified kinematic model of the human hand on the basis of the available motion tracking system. Using the same criteria, the analysis of protocols for markers allocation led to define the number and a method for their arrangement on the fingers and palm. In order to overcome the limitation of the Motion Capture System, a method for identification and labeling has been developed according to their anatomical arrangement. Afterwards, the tracking is performed using the constraints between marker positions on the kinematic chain of the hand and a dynamic labeling algorithm robust with respect to noise, outliers and loss of markers. The validation is performed using the right hand of different subjects and considering different tasks involving flexion/extension and abduction/adduction of fingers and thumb opposition. For testing and validation, preliminary studies on synergies for manipulation tasks such as screwing a cup, has been conducted on the human hand and transferred on the robotic hand.

Design of an underactuated anthropomorphic hand with mechanically implemented postural synergies

Neurology shows that human controls dozens of muscles for hand poses in a coordinated manner and such coordination is referred as to a postural synergy. The concept of postural synergies was recently adopted in the control of robotic hands. With the synergies implemented digitally in a controller, all the motors in an anthropomorphic robotic hand can be controlled via a few synergy inputs. Aiming at exploring alternative approaches for synergy realization, this paper proposes to implement the postural synergies using a mechanical transmission unit. Two rotation inputs can be scaled, combined, and mapped to the rotary outputs to drive an anthropomorphic hand, enabling not only various grasping tasks but also a manipulation motion. Synergy synthesis and design of the anthropomorphic hand are firstly presented. The transmission unit as the implementation of the postural synergies is then elaborated. Tests were performed to quantify how well the synergies could be reproduced via this transmission unit. The results suggest it might be promising to construct a low cost yet versatile prosthetic hand by implementing the postural synergies mechanically.