Dynamic Tactile Exploration for Texture Classification using a Miniaturized Multi-modal Tactile Sensor and Machine Learning

Lima, Bruno Monteiro Rocha; Fonseca, Vinícius Prado da; Oliveira, Thiago Eustaquio Alves de; Zhu, Qi; Petriu, Emil M.

doi:10.1109/syscon47679.2020.9275871

Cited by 13 publications

(10 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fingertip of the robotic finger was equipped with a fixed miniaturized tactile sensor, which was developed by De Oliveira et al (2017) . This miniaturized sensor was also used in a previous study by Lima et al (2020) . The scaled-down version of this module is depicted in Figure 2 .…”

Section: Methodsmentioning

confidence: 99%

“…Different from ( Lima et al, 2020 ), the tactile sensing module used in this study has a rounded profile and flexible materials that enable exploratory motions, resembling the shape of a human fingertip. During experiments, the sensor was securely held in place by an articulated robotic finger mounted on a plastic base.…”

Section: Methodsmentioning

confidence: 99%

“…Authors of de Oliveira et al (2015b) proposed a data-driven analysis for shape discrimination tasks using a robotic finger that performs the sliding movement. Lima et al (2020) developed an experiment with a sliding tactile-enabled robotic fingertip to explore textures dynamically. The robotic fingertip’s design contains a multimodal tactile sensor that makes contact with the surface.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Active learning strategies for robotic tactile texture recognition tasks

Das,

Prado da Fonseca,

Soares

2024

Front. Robot. AI

View full text Add to dashboard Cite

Accurate texture classification empowers robots to improve their perception and comprehension of the environment, enabling informed decision-making and appropriate responses to diverse materials and surfaces. Still, there are challenges for texture classification regarding the vast amount of time series data generated from robots’ sensors. For instance, robots are anticipated to leverage human feedback during interactions with the environment, particularly in cases of misclassification or uncertainty. With the diversity of objects and textures in daily activities, Active Learning (AL) can be employed to minimize the number of samples the robot needs to request from humans, streamlining the learning process. In the present work, we use AL to select the most informative samples for annotation, thus reducing the human labeling effort required to achieve high performance for classifying textures. We also use a sliding window strategy for extracting features from the sensor’s time series used in our experiments. Our multi-class dataset (e.g., 12 textures) challenges traditional AL strategies since standard techniques cannot control the number of instances per class selected to be labeled. Therefore, we propose a novel class-balancing instance selection algorithm that we integrate with standard AL strategies. Moreover, we evaluate the effect of sliding windows of two-time intervals (3 and 6 s) on our AL Strategies. Finally, we analyze in our experiments the performance of AL strategies, with and without the balancing algorithm, regarding f1-score, and positive effects are observed in terms of performance when using our proposed data pipeline. Our results show that the training data can be reduced to 70% using an AL strategy regardless of the machine learning model and reach, and in many cases, surpass a baseline performance. Finally, exploring the textures with a 6-s window achieves the best performance, and using either Extra Trees produces an average f1-score of 90.21% in the texture classification data set.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Active learning strategies for robotic tactile texture recognition tasks

Das,

Prado da Fonseca,

Soares

2024

Front. Robot. AI

View full text Add to dashboard Cite

show abstract

“…The paper explains how the data from the tactile modules can be used to establish connections between egocentric and allocentric frames of reference for object orientation. Tactile texture recognition: In [19] and [20] , the authors present the utilization of the miniaturized multi-modal tactile sensor to classify different tactile textures. The sensor measured the variations of pressure, acceleration, angular velocity, and magnetic flux signals caused by the dynamic contact with 13 commonly used tactile textures.…”

Section: Hardware Descriptionmentioning

confidence: 99%

“…Tactile texture recognition: In [19] and [20] , the authors present the utilization of the miniaturized multi-modal tactile sensor to classify different tactile textures. The sensor measured the variations of pressure, acceleration, angular velocity, and magnetic flux signals caused by the dynamic contact with 13 commonly used tactile textures.…”

Section: Hardware Descriptionmentioning

confidence: 99%