Extended Tactile Perception: Vibration Sensing through Tools and Grasped Objects

Taunyazov, Tasbolat; Shui, Song, Luar; Lim, Eugene; See, Hian Hian; Lee, David; Tee, Benjamin C. K.; Soh, Harold

doi:10.1109/iros51168.2021.9636677

Cited by 18 publications

(12 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Robot–object and robot–human interfacing or robot tactile sensing engineering solutions have been broadly investigated to address an ever-growing demand for unique and useful applications, from a simple “pick and place” task to more complex tasks such as crop harvesting, utilization of tools, and surface material identification . The ability to perform varying static and dynamic measurements, whether it is to detect holding, shear, rotational, or slippage forces , or even to infer information through vibration of direct contact , or of a type of a held tool is of particular importance. The common link between all these approaches is the need to sense forces/pressures when applying force to the gripping mechanism so that the robot has some proprioceptive awareness and is able to adjust accordingly.…”

Section: Introductionmentioning

confidence: 99%

Multimodal Fibrous Static and Dynamic Tactile Sensor

Fastier-Wooller

Nguyen³

et al. 2022

ACS Appl. Mater. Interfaces

View full text Add to dashboard Cite

A highly versatile, low-cost, and robust tactile sensor capable of acquiring load measurements under static and dynamic modes employing a poly(vinylidene fluoride-co-trifluoroethylene) [P(VDF-TrFE)] micronanofiber element is presented. The sensor is comprised of three essential layers, a fibrous core P(VDF-TrFE) layer and two Ni/Cu conductive fabric electrode layers, with a total thickness of less than 300 μm. Using an in situ electrospinning process, the core fibers are deposited directly to a soft poly(dimethylsiloxane) (PDMS) fingertip. The core layer conforms to the surface and requires no additional processing, exhibiting the capability of the in situ electrospinning fabrication method to alleviate poor surface contacts and resolve issues associated with adhesion. The fabricated tactile sensor displayed a reliable and consistent measurement performance of static and instantaneous dynamic loads over a total of 30 000 test cycles. The capabilities and implications of the presented tactile sensor design for multimodal sensing in robot tactile sensing applications is further discussed and elucidated.

show abstract

Section: Introductionmentioning

confidence: 99%

Multimodal Fibrous Static and Dynamic Tactile Sensor

Fastier-Wooller

Nguyen³

et al. 2022

ACS Appl. Mater. Interfaces

View full text Add to dashboard Cite

show abstract

“…A typical classification task is slip detection, which has been researched for stable robot grasp. [ 49,50,93 ] Shear force direction classification was also presented as a machine learning object for a better grasp. [ 161 ]…”

Section: Applications Of Machine Learning For Tactile Sensingmentioning

confidence: 99%

“…Contact force intensity has been estimated using regression learning (Figure 11a), [20,52,54,114] and so has force contact position. [22,54,93,172] In addition, the relative orientation of tactile sensor to the contacted object surface has also been regressed. [172] Touch location can also be achieved using classification learning, with each class representing an area of contact positions.…”

Section: Supervised Learning In Robot Tactile Perceptionmentioning

confidence: 99%

Machine Learning for Tactile Perception: Advancements, Challenges, and Opportunities

Lin

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

The past decades have seen the rapid development of tactile sensors in material, fabrication, and mechanical structure design. The advancement of tactile sensors has heightened the expectation of sensor functions, and thus put forward a higher demand for data processing. However, conventional analysis techniques have not kept pace with the tactile sensor development and still suffer from some severe drawbacks, like cumbersome models, poor efficiency, and expensive costs. Machine learning, with its prominent ability for big data analysis and fast processing speed, can offer many possibilities for tactile data analysis. Herein, the machine learning techniques employed for processing tactile signals are reviewed. Supervised learning and unsupervised learning for analog signals are covered, and processing spike signals with machine learning are summarized. Furthermore, the applications in robotic tactile perception and human activity monitoring are presented. Finally, the current challenges and future prospects in sensors, data, algorithms, and benchmarks are discussed.

show abstract

“…Hence, the identification of multiple objects with different properties must be considered. Several studies have been conducted that food identification by learning their material characteristics from tactile or vibration signals and successfully performed appropriate actions for each food by robot (15,16) . This identification method introduced a neural network to identify multiple foods without needing to select an appropriate model for each object.…”

Section: Background and Related Workmentioning

confidence: 99%

Motion Planning for Cutting Flexible Objects Based on Contact State Recognition

2023

View full text Add to dashboard Cite

Humans possess an outstanding ability to understand contact states, thereby leading to appropriate actions. In this study, we consider the operation of autonomous machining tasks on heterogeneous materials using robots; this mechanism poses a challenge as robotic machining is mainly performed on homogeneous materials using the current robotic technology. Herein, we propose a method to recognize contact states, e.g. the materials and deformation types of fragile objects, to selectively process parts of tissues without damaging other tissues. Furthermore, an identification method is proposed based on a time-delay neural network (TDNN) to identify fragile objects and their deformation types, such as elastic and plastic, for real-time applications. We used a multi degrees-of-freedom (DoF) robotic arm to cut and process fragile objects. We examined the planning of an appropriate trajectory based on the contact states identified by the TDNN during cutting motion. The selective cutting motion of a robot was demonstrated with high success rates despite variations in the cutting speed.

show abstract

Extended Tactile Perception: Vibration Sensing through Tools and Grasped Objects

Cited by 18 publications

References 44 publications

Multimodal Fibrous Static and Dynamic Tactile Sensor

Multimodal Fibrous Static and Dynamic Tactile Sensor

Machine Learning for Tactile Perception: Advancements, Challenges, and Opportunities

Motion Planning for Cutting Flexible Objects Based on Contact State Recognition

Contact Info

Product

Resources

About