An official website of the United States government
This paper presents an online data collection method that captures human intuition about what grasp types are preferred for different fundamental object shapes and sizes. Survey questions are based on an adopted taxonomy that combines grasp pre-shape, approach, wrist orientation, object shape, orientation and size which covers a large swathe of common grasps. For example, the survey identifies at what object height or width dimension (normalized by robot hand size) the human prefers to use a two finger precision grasp versus a three-finger power grasp. This information is represented as a confidence-interval based polytope in the object shape space. The result is a database that can be used to quickly find potential pre-grasps that are likely to work, given an estimate of the object shape and size.
more »
« less
Grasp Taxonomy for Robot Assistants Inferred from Finger Pressure and Flexion
Grasp is an integral part of manipulation actions in activities of daily living and programming by demonstration is a powerful paradigm for teaching the assistive robots how to perform a grasp. Since finger configuration and finger force are the fundamental features that need to be controlled during a grasp, using these variables is a natural choice for learning by demonstration. An important question then becomes whether the existing grasp taxonomies are appropriate when one considers these modalities. The goal of our paper is to answer this question by investigating grasp patterns that can be inferred from a static analysis of the grasp data, as the object is securely grasped. Human grasp data is measured using a newly developed data glove. The data includes pressure sensor measurements from eighteen areas of the hand, and measurements from bend sensors placed at finger joints. The pressure sensor measurements are calibrated and mapped into force by employing a novel data-driven approach. Unsupervised learning is used to identify patterns for different grasp types. Multiple clustering algorithms are used to partition the data. When the results are taken in aggregate, 25 human grasp types are reduced to 9 different clusters.
more »
« less
- PAR ID:
- 10096225
- Date Published:
- Journal Name:
- 2019 International Symposium on Medical Robotics (ISMR)
- Page Range / eLocation ID:
- 1 to 7
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Soft robotic grippers can gently grasp and maneuver objects. However, they are difficult to model and control due to their highly deformable fingers and complex integration with robotic systems. This paper investigates the design requirements as well as the grasping capabilities and performance of a soft gripper system based on fluidic prestressed composite (FPC) fingers. An analytical model is constructed as follows: each finger is modeled using the chained composite model (CCM); strain energy and work done by pressure and loads are computed using polynomials with unknown coefficients; net energy is minimized using the Rayleigh–Ritz method to calculate the deflected equilibrium shapes of the finger as a function of pressure and loads; and coordinate transformation and gripper geometries are combined to analyze the grasping performance. The effects of prestrain, integration angle, and finger overlap on the grasping performance are examined through a parametric study. We also analyze gripping performance for cuboidal and spherical objects and show how the grasping force can be controlled by varying fluidic pressure. The quasi-static responses of fabricated actuators are measured under pressures and loads. It is shown that the actuators’ modeled responses agree with the experimental results. This work provides a framework for the theoretical analysis of soft robotic grippers and the methods presented can be extended to model grippers with different types of actuation.more » « less
-
null (Ed.)Abstract In this study, a numerical framework for joint rotation configuration models of a finger is proposed. The basic idea is to replicate the finger’s geometric posture observed when the human hand grasps a cylindrical object with various cross sections. In the model development, objects with the cross section adopted from the curves of order two (the family of conic sections) are taken into consideration to realize various finger postures. In addition, four different grasp styles, which simulate the individual-specific contact pattern between the surfaces of object and finger, are modeled and applied for the formulation of numerical models. An idea on how to change flexion/extension patterns in the middle of excursion of movement is proposed and discussed. Series of numerical studies have been conducted and analyzed to evaluate the proposed models. From the results, one can see the models’ feasibility and viability as a solution to describing finger’s flexion/extension movements (FEMs) for grasping patterns.more » « less
-
null (Ed.)Current designs of powered prosthetic limbs are limited by the nearly exclusive use of DC motor technology. Soft actuators promise new design freedom to create prosthetic limbs which more closely mimic intact neuromuscular systems and improve the capabilities of prosthetic users. This work evaluates the performance of a hydraulically amplified self-healing electrostatic (HASEL) soft actuator for use in a prosthetic hand. We compare a linearly-contracting HASEL actuator, termed a Peano-HASEL, to an existing actuator (DC motor) when driving a prosthetic finger like those utilized in multi-functional prosthetic hands. A kinematic model of the prosthetic finger is developed and validated, and is used to customize a prosthetic finger that is tuned to complement the force-strain characteristics of the Peano-HASEL actuators. An analytical model is used to inform the design of an improved Peano-HASEL actuator with the goal of increasing the fingertip pinch force of the prosthetic finger. When compared to a weight-matched DC motor actuator, the Peano-HASEL and custom finger is 10.6 times faster, has 11.1 times higher bandwidth, and consumes 8.7 times less electrical energy to grasp. It reaches 91% of the maximum range of motion of the original finger. However, the DC motor actuator produces 10 times the fingertip force at a relevant grip position. In this body of work, we present ways to further increase the force output of the Peano-HASEL driven prosthetic finger system, and discuss the significance of the unique properties of Peano-HASELs when applied to the field of upper-limb prosthetic design. This approach toward clinically-relevant actuator performance paired with a substantially different form-factor compared to DC motors presents new opportunities to advance the field of prosthetic limb design.more » « less
-
The ability to learn from human demonstration endows robots with the ability to automate various tasks. However, directly learning from human demonstration is challenging since the structure of the human hand can be very different from the desired robot gripper. In this work, we show that manipulation skills can be transferred from a human to a robot through the use of micro-evolutionary reinforcement learning, where a five-finger human dexterous hand robot gradually evolves into a commercial two-finger-gripper robot, while repeated interacting in a physics simulator to continuously update the policy that is first learned from human demonstration. To deal with the high dimensions of robot parameters, we propose an algorithm for multi-dimensional evolution path searching that allows joint optimization of both the robot evolution path and the policy. Through experiments on human object manipulation datasets, we show that our framework can efficiently transfer the expert human agent policy trained from human demonstrations in diverse modalities to a target commercial robot.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ISMR.2019.8710191
