An official website of the United States government
Robot teleoperation is an emerging field of study with wide applications in exploration, manufacturing, and healthcare, because it allows users to perform complex remote tasks while remaining distanced and safe. Haptic feedback offers an immersive user experience and expands the range of tasks that can be accomplished through teleoperation. In this paper, we present a novel wearable haptic feedback device for a teleoperation system that applies kinesthetic force feedback to the fingers of a user. The proposed device, called a ‘haptic muscle’, is a soft pneumatic actuator constructed from a fabric-silicone composite in a toroidal structure. We explore the requirements of the ideal haptic feedback mechanism, construct several haptic muscles using different materials, and experimentally determine their dynamic pressure response as well as sensitivity (their ability to communicate small changes in haptic feedback). Finally, we integrate the haptic muscles into a data glove and a teleoperation system and perform several user tests. Our results show that most users could detect detect force changes as low as 3% of the working range of the haptic muscles. We also find that the haptic feedback causes users to apply up to 52% less force on an object while handling soft and fragile objects with a teleoperation system.
more »
« less
Deep Learning Based Shopping Assistant For The Visually Impaired
Contemporary developments in computer vision and artificial intelligence show promise to greatly improve the lives of those with disabilities. In this paper, we propose one such development: a wearable object recognition device in the form of eyewear. Our device is specialized to recognize items from the produce section of a grocery store, but serves as a proof of concept for any similar object recognition wearable. It is user friendly, featuring buttons that are pressed to capture images with the built-in camera. A convolutional neural network (CNN) is used to train the object recognition system. After the object is recognized, a text-to-speech system is utilized to inform the user which object they are holding in addition to the price of the product. With accuracy rates of 99.35%, our product has proven to successfully identify objects with greater correctness than existing models.
more »
« less
- Award ID(s):
- 1710716
- PAR ID:
- 10088295
- Date Published:
- Journal Name:
- IEEE International Conference on Consumer Electronics
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Wearable internet of things (IoT) devices can enable a variety of biomedical applications, such as gesture recognition, health monitoring, and human activity tracking. Size and weight constraints limit the battery capacity, which leads to frequent charging requirements and user dissatisfaction. Minimizing the energy consumption not only alleviates this problem, but also paves the way for self-powered devices that operate on harvested energy. This paper considers an energy-optimal gesture recognition application that runs on energy-harvesting devices. We first formulate an optimization problem for maximizing the number of recognized gestures when energy budget and accuracy constraints are given. Next, we derive an analytical energy model from the power consumption measurements using a wearable IoT device prototype. Then, we prove that maximizing the number of recognized gestures is equivalent to minimizing the duration of gesture recognition. Finally, we utilize this result to construct an optimization technique that maximizes the number of gestures recognized under the energy budget constraints while satisfying the recognition accuracy requirements. Our extensive evaluations demonstrate that the proposed analytical model is valid for wearable IoT applications, and the optimization approach increases the number of recognized gestures by up to 2.4× compared to a manual optimization.more » « less
-
A scarf is inherently reconfigurable: wearers often use it as a neck wrap, a shawl, a headband, a wristband, and more. We developed uKnit, a scarf-like soft sensor with scarf-like reconfigurability, built with machine knitting and electrical impedance tomography sensing. Soft wearable devices are comfortable and thus attractive for many human-computer interaction scenarios. While prior work has demonstrated various soft wearable capabilities, each capability is device- and location-specific, being incapable of meeting users’ various needs with a single device. In contrast, uKnit explores the possibility of one-soft-wearable-for-all. We describe the fabrication and sensing principles behind uKnit, demonstrate several example applications, and evaluate it with 10-participant user studies and a washability test. uKnit achieves 88.0%/78.2% accuracy for 5-class worn-location detection and 80.4%/75.4% accuracy for 7-class gesture recognition with a per-user/universal model. Moreover, it identifies respiratory rate with an error rate of 1.25 bpm and detects binary sitting postures with an average accuracy of 86.2%.more » « less
-
We propose a haptic device that alters the perceived softness of real rigid objects without requiring to instrument the objects. Instead, our haptic device works by restricting the user's fingerpad lateral deformation via a hollow frame that squeezes the sides of the fingerpad. This causes the fingerpad to become bulgier than it originally was—when users touch an object's surface with their now-restricted fingerpad, they feel the object to be softer than it is. To illustrate the extent of softness illusion induced by our device, touching the tip of a wooden chopstick will feel as soft as a rubber eraser. Our haptic device operates by pulling the hollow frame using a motor. Unlike most wearable haptic devices, which cover up the user's fingerpad to create force sensations, our device creates softness while leaving the center of the fingerpad free, which allows the users to feel most of the object they are interacting with. This makes our device a unique contribution to altering the softness of everyday objects, creating “buttons” by softening protrusions of existing appliances or tangibles, or even, altering the softness of handheld props for VR. Finally, we validated our device through two studies: (1) a psychophysics study showed that the device brings down the perceived softness of any object between 50A-90A to around 40A (on Shore A hardness scale); and (2) a user study demonstrated that participants preferred our device for interactive applications that leverage haptic props, such as making a VR prop feel softer or making a rigid 3D printed remote control feel softer on its button.more » « less
-
The paper presents the design of a lower leg orthotic device based on dimensional synthesis of multi-loop six-bar linkages. The wearable device is comprised of a 2R serial chain, termed the backbone, sized according to the wearer’s limb anthropometric dimensions. The paper is a result of our current efforts in proposing a systematic process for the development of 3D printed customized assistive devices for patients with reduced limb mobility, based on anthropometric data and physiological task. To design the wearable device, the physiological task of the limb is obtained using an optical motion capture system and its dimensions are set such that it matched the lower leg kinematics as closely as possible. As a next step a six-bar linkage is synthesized and ensured that its motion is as close as possible to the physiological task. Next, the 2R backbone is replaced by the wearer’s limb to provide the skeletal structure for the multiloop wearable device. During the final stage of the process the 2R backbone is relocated to parallel the human’s limb on one side, providing support and stability. The designed device can be secured to the thigh of the user to guide the lower leg without causing any discomfort and to ensure a natural physiological gait trajectory. This results in orthotic device for assisting people with lower leg injuries with compact size and better wearability.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
