Visually Guided Acquisition of Contact Dynamics and Case Study in Data-Driven Haptic Texture Modeling

Abdulali, Arsen; Atadjanov, Ibragim R.; Jeon, Seokhee

doi:10.1109/toh.2020.2965449

Cited by 13 publications

(9 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These experiments should allow us to further elucidate parameters that define a good active haptic device and a good haptic interaction. Once we have standardized a complete set of benchmarks, we intend to create a graphical user interface to guide the experimenter through each test, which should increase the quality of the resulting metrics and reduce the experimenter's mental workload [38]. Our third direction is to benchmark more devices and make our findings and measurements accessible for all researchers by adding features to the Haptipedia website.…”

Section: Discussionmentioning

confidence: 99%

Haptify: A Measurement-Based Benchmarking System for Grounded Force-Feedback Devices

Fazlollahi

Kuchenbecker

2023

IEEE Trans. Robot.

View full text Add to dashboard Cite

Grounded force-feedback (GFF) devices are an established and diverse class of haptic technology based on robotic arms. However, the number of designs and how they are specified make comparing devices difficult. We thus present Haptify, a benchmarking system that can thoroughly, fairly, and noninvasively evaluate GFF haptic devices. The user holds the instrumented device end-effector and moves it through a series of passive and active experiments. Haptify records the interaction between the hand, device, and ground with a seven-camera optical motion-capture system, a 60-cm-square custom force plate, and a customized sensing end-effector. We demonstrate six key ways to assess GFF device performance: workspace shape, global free-space forces, global free-space vibrations, local dynamic forces and torques, frictionless surface rendering, and stiffness rendering. We then use Haptify to benchmark two commercial haptic devices. With a smaller workspace than the 3D Systems Touch, the more expensive Touch X outputs smaller free-space forces and vibrations, smaller and more predictable dynamic forces and torques, and higher-quality renderings of a frictionless surface and high stiffness.

show abstract

Section: Discussionmentioning

confidence: 99%

Haptify: A Measurement-Based Benchmarking System for Grounded Force-Feedback Devices

Fazlollahi

Kuchenbecker

2023

IEEE Trans. Robot.

View full text Add to dashboard Cite

show abstract

“…In addition to the normal forces applied to fingertips, other forces can be also calculated based on the calculated contact forces, such as frictional forces during the sliding process. Considering the fidelity of the force feedback, a contact force model that corresponds to real manipulation behaviors is required, such as using data-driven methods [36], [37].…”

Section: Discussionmentioning

confidence: 99%

Configuration-Based Optimization for Virtual Hand Haptic Simulation

Tong

Wang

Zhang

et al. 2022

IEEE Trans. Haptics

View full text Add to dashboard Cite

Interacting with virtual objects via haptic feedback using the user's hand directly (virtual hand haptic interaction) provides a natural and immersive way to explore the virtual world. It remains a challenging topic to achieve 1 kHz stable virtual hand haptic simulation with no penetration amid hundreds of hand-object contacts. In this paper, we advocate decoupling the high-dimensional optimization problem of computing the graphichand configuration, and progressively optimizing the configuration of the graphic palm and fingers, yielding a decoupled-andprogressive optimization framework. We also introduce a method for accurate and efficient hand-object contact simulation, which constructs a virtual hand consisting of a sphere-tree model and five articulated cone frustums, and adopts a configuration-based optimization algorithm to compute the graphic-hand configuration under non-penetration contact constraints. Experimental results show both high update rate and stability for a variety of manipulation behaviors. Non-penetration between the graphic hand and complex-shaped objects can be maintained under diverse contact distributions, and even for frequent contact switches. The update rate of the haptic simulation loop exceeds 1 kHz for the whole-hand interaction with about 250 contacts.

show abstract

“…Abdulali et al 18 introduced the utilization of a Radial Basis Function Network (RBFN) to model anisotropic haptic textures. Subsequently, in a later work 17 , they presented a comprehensive visually guided data collection system designed to aid users in gathering acceleration signals with varying speed, force, and direction. In addition, they proposed a recursive constraint projection (RCP) algorithm for data segmentation, which also proves effective for processing streaming data.…”

Section: Related Workmentioning

confidence: 99%

“…A parameter estimation algorithm is presented for sound synthesis in 12 , which overcomes the limitation of linear modal synthesis (i.e., frictional multibody contact formulation 10 ). However, the introduction of more sophisticated textures (i.e., anisotropic textures) has led to challenges with the intricate physical models and computational demands in real-time physics-based simulations of tool-surface interactions 5 , 17 , 18 . Although simplification attempts have been made but at the cost of reducing perceptual realism, impacting virtual experience authenticity.…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, data-driven approach eliminates the need for intricate parameter adjustments and instead aim to establish correlations between user inputs (such as speed, force, and direction) and outputs (including vibrotactile signals and sound). In the early data-driven approach, vibrotactile signals were modeled and rendered using techniques such as Linear Predictive Coding (LPC) 16 , Auto Regressive Moving Average (ARMA) 2 , radial basis function network (RBFN) 17 , 18 , neural networks (NNs) 19 and Waveform Segment Table 3 . Yet, despite these efforts, their performance was not adequate.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A multimodal multitask deep learning framework for vibrotactile feedback and sound rendering

Joolee,

Uddin

2024

Sci Rep

View full text Add to dashboard Cite

Data-driven approaches are often utilized to model and generate vibrotactile feedback and sounds for rigid stylus-based interaction. Nevertheless, in prior research, these two modalities were typically addressed separately due to challenges related to synchronization and design complexity. To this end, we introduce a novel multimodal multitask deep learning framework. In this paper, we developed a comprehensive end-to-end data-driven system that encompasses the capture of contact acceleration signals and sound data from various texture surfaces. This framework introduces novel encoder-decoder networks for modeling and rendering vibrotactile feedback through an actuator while routing sound to headphones. The proposed encoder-decoder networks incorporate stacked transformers with convolutional layers to capture both local variability and overall trends within the data. To the best of our knowledge, this is the first attempt to apply transformer-based data-driven approach for modeling and rendering of vibrotactile signals as well as sounds during tool-surface interactions. In numerical evaluations, the proposed framework demonstrates a lower RMS error compared to state-of-the-art models for both vibrotactile signals and sound data. Additionally, subjective similarity evaluation also confirm the superiority of proposed method over state-of-the-art.

show abstract

Visually Guided Acquisition of Contact Dynamics and Case Study in Data-Driven Haptic Texture Modeling

Cited by 13 publications

References 40 publications

Haptify: A Measurement-Based Benchmarking System for Grounded Force-Feedback Devices

Haptify: A Measurement-Based Benchmarking System for Grounded Force-Feedback Devices

Configuration-Based Optimization for Virtual Hand Haptic Simulation

A multimodal multitask deep learning framework for vibrotactile feedback and sound rendering

Contact Info

Product

Resources

About