Vision-driven collaborative robotic grasping system tele-operated by surface electromyography

Úbeda, Andrés; Zapata-Impata, Brayan S.; Méndez, Santiago Timoteo Puente; Gil, Pablo; Candelas, Francisco A.; Torres, Fernando

doi:10.20944/preprints201806.0449.v1

Cited by 6 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nowadays, with the development of neuromorphic vision in grasping field, the robotic grasping system can be newly categorized into standard vision-based and neuromorphic vision-based approaches along the different perception methods. Lots of standard vision-based robotic grasping systems are explored for many applications, such as garbage sorting [5], construction [6] and human interaction [7]. However, the grasping quality would be affected severely due to the poor perceiving quality, such as the motion blur and poor observing ability in low-light condition.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Grasping Strategies Using Event Camera

Huang¹,

Halwani²,

Muthusamy³

et al. 2021

Preprint

View full text Add to dashboard Cite

Robotic vision plays a key role for perceiving the environment in grasping applications. However, the conventional framed-based robotic vision, suffering from motion blur and low sampling rate, may not meet the automation needs of evolving industrial requirements. This paper, for the first time, proposes an event-based robotic grasping framework for multiple known and unknown objects in a cluttered scene. Compared with standard frame-based vision, neuromorphic vision has advantages of microsecond-level sampling rate and no motion blur. Building on that, the model-based and model-free approaches are developed for known and unknown objects' grasping respectively. For the model-based approach, event-based multi-view approach is used to localize the objects in the scene, and then point cloud processing allows for the clustering and registering of objects. Differently, the proposed model-free approach utilizes the developed event-based object segmentation, visual servoing and grasp planning to localize, align to, and grasp the targeting object. The proposed approaches are experimentally validated with objects of different sizes, using a UR10 robot with an eye-in-hand neuromorphic camera and a Bar-

show abstract

Section: Introductionmentioning

confidence: 99%

Real-Time Grasping Strategies Using Event Camera

Huang¹,

Halwani²,

Muthusamy³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Other approaches that explored the use of muscles on other body parts to generate the EMG signals require sensing elements to be placed at those points which, beyond being unintuitive, can induce discomfort when used for prolonged periods of time. Performing fully autonomous grasps for the wide variety of activities of daily living (ADLs) by relying only on perception of the surroundings (such as through a vision system) is in development [13], but this requires additional equipment, making the overall setup cumbersome. Similar issues arise when attempting to track the human eye to estimate grasp intentions of the user, as performed by Noronha et al in [14].…”

Section: Introductionmentioning

confidence: 99%

Grasp Prediction Toward Naturalistic Exoskeleton Glove Control

Chauhan

Sebastian

Ben-Tzvi

2020

IEEE Trans. Human-Mach. Syst.

View full text Add to dashboard Cite

This paper presents accurate grasp prediction algorithms that can be used for naturalistic, synergistic control of exoskeleton gloves with minimal user input. Recent research in exoskeleton systems has focused mainly on the development of novel soft or hard mechanical designs and actuation systems for rehabilitative and assistive applications. On the other hand, estimating user intent for intelligent grasp assistance is a problem that has remained largely unaddressed. As demonstrated by existing studies, the complex motions of human hand can be mapped to a latent space, thereby reducing perceived noise in individual joint angles as well as the number of variables upon which the prediction must be performed. To this extent, we present two latent space grasp prediction algorithms for intelligent exoskeleton glove control. The first presented algorithm is based on a linear regression to determine the slope and prediction horizon. The second algorithm is based on a Gaussian process trajectory matching where the trajectory of the grasping motion is probabilistically compared to existing data in order to form a prediction. Both algorithms were tested on published motion data collected from healthy subjects. In addition, the experimental validation of the algorithms was done using the RML glove (Robotics and Mechatronics Lab), which yielded similar prediction accuracy as compared to the simulation results. The proposed prediction algorithm can act as the backbone for a shifting authority controller that simultaneously amplifies the user's motion while guiding them toward their desired grasp. Preliminary work in this direction is also described in the paper, with directions for future research.

show abstract

“…Alternatively, EMG sensors can be placed at other locations on the body and those muscles can be used to control the exoskeleton at the cost of highly unintuitive operation. EMG based approaches can be coupled with vision based sensing to better estimate user intent [17,18] with the drawback of requiring additional hardware and therefore an even larger operational setup.…”

Section: Introductionmentioning

confidence: 99%

A Series Elastic Actuator Design and Control in a Linkage Based Hand Exoskeleton

Chauhan

Ben-Tzvi

2019

Volume 3, Rapid Fire Interactive Presentations: Advances in Control Systems; Advances in Robotics and Mechatronics; Automotive

View full text Add to dashboard Cite

This paper presents the design of a series elastic actuator and a higher level controller for said actuator to assist the motion of a user’s hand in a linkage based hand exoskeleton. While recent trends in the development of exoskeleton gloves has been to exploit the advantages of soft actuators, their size and power requirements limit their adoption. On the other hand, a series elastic actuator can provide compliant assistance to the wearer while remaining compact and lightweight. Furthermore, the linkage based mechanism integrated with the SEA offers repeatability and accuracy to the hand exoskeleton. By measuring the user’s motion intention through compression of the elastic elements in the actuator, a virtual dynamic system can be utilized that assists the users in performing the desired motion while ensuring the motion stability of the overall system. This work describes the detailed design of the actuator followed by performance tests using a simple PD controller on the integrated robotic exoskeleton prototype. The performance of the proposed high level controller is tested using the integrated exoskeleton glove mechanism for a single finger, using two types of input motion. Preliminary results are discussed as well as plans for integrating the proposed actuator and high level controller into a complete hand exoskeleton prototype to perform intelligent grasping.

show abstract

Vision-driven collaborative robotic grasping system tele-operated by surface electromyography

Cited by 6 publications

References 23 publications

Real-Time Grasping Strategies Using Event Camera

Real-Time Grasping Strategies Using Event Camera

Grasp Prediction Toward Naturalistic Exoskeleton Glove Control

A Series Elastic Actuator Design and Control in a Linkage Based Hand Exoskeleton

Contact Info

Product

Resources

About