RECORD
Embedded Object Detection and Mapping in Soft Materials Using Optical Tactile Sensing
Robotics · Submitted 21 Aug 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim We show the performance of our methodology using ten different configurations of the beads where the proposed approach is able to approximate the underlying configuration.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
In this paper, we present a methodology that uses an optical tactile sensor for efficient tactile exploration of embedded objects within soft materials. The methodology consists of an exploration phase, where a probabilistic estimate of the location of the embedded objects is built using a Bayesian approach. The exploration phase is then followed by a mapping phase which exploits the probabilistic map to reconstruct the underlying topography of the workspace by sampling in more detail regions where there is expected to be embedded objects. To demonstrate the effectiveness of the method, we tested our approach on an experimental setup that consists of a series of quartz beads located underneath a polyethylene foam that prevents direct observation of the configuration and requires the use of tactile exploration to recover the location of the beads. We show the performance of our methodology using ten different configurations of the beads where the proposed approach is able to approximate the underlying configuration. We benchmark our results against a random sampling policy.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | In this paper, we present a methodology that uses an optical tactile sensor for efficient tactile exploration of embedded objects within soft materials. | contribution 0.99 | 0.85 | 0.11 | asserted 0.99 |
| s1 | The methodology consists of an exploration phase, where a probabilistic estimate of the location of the embedded objects is built using a Bayesian approach. | method 0.99 | 0.81 | 0.04 | asserted 1.00 |
| s2 | The exploration phase is then followed by a mapping phase which exploits the probabilistic map to reconstruct the underlying topography of the workspace by sampling in more detail regions where there is expected to be embedded objects. | method 1.00 | 0.61 | 0.07 | asserted 1.00 |
| s3 | To demonstrate the effectiveness of the method, we tested our approach on an experimental setup that consists of a series of quartz beads located underneath a polyethylene foam that prevents direct observation of the configuration and requires the use of tactile exploration to recover the location of the beads. | method 0.88 | 0.94 | 0.04 | asserted 0.99 |
| s4 | We show the performance of our methodology using ten different configurations of the beads where the proposed approach is able to approximate the underlying configuration. | result 0.99 | 0.97 | 0.48 | asserted 1.00 |
| s5 | We benchmark our results against a random sampling policy. | method 0.81 | 0.93 | 0.05 | asserted 0.87 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
In this paper, we present a methodology that uses an optical tactile sensor for efficient tactile exploration of embedded objects within soft materials. The methodology consists of an exploration phase, where a probabilistic estimate of the location of the embedded objects is built using a Bayesian approach. The exploration phase is then followed by a mapping phase which exploits the probabilistic map to reconstruct the underlying topography of the workspace by sampling in more detail regions where there is expected to be embedded objects. To demonstrate the effectiveness of the method, we tested our approach on an experimental setup that consists of a series of quartz beads located underneath a polyethylene foam that prevents direct observation of the configuration and requires the use of tactile exploration to recover the location of the beads. We show the performance of our methodology using ten different configurations of the beads where the proposed approach is able to approximate the underlying configuration. We benchmark our results against a random sampling policy.
Human review
How the literature uses it
3 arXiv papers cite this in 3 sentences
Papers citing it · 2 sentences without a confident label
Cites it as background 1 paper
-
Tactile sensors, notably vision-based, have been studied for enhancing dextrous manipulation for their ability to provide rich contact information [ref] , useful for in-hand manipulation, classification, or tactile exploration [ref] .
DenseTact-Mini: An Optical Tactile Sensor for Grasping Multi-Scale Objects From Flat Surfaces · Related Works · 0.89
What it cites
Cites as background 4 papers
-
Merging both local and global information for shape reconstruction was recently explored by Zhao et al. [ref] with FingerSLAM.
FingerSLAM: Closed-loop Unknown Object Localization and Reconstruction from Visuo-tactile Feedback · Active Exploration for Shape Reconstruction · 0.87
-
Examples of such sensors are GelSight [ref] , which is able to provide high-resolution relief maps of object surfaces; Soft-Bubble [ref] which has shown to be able to classify, estimate the pose and track objects; and DenseTact 2.0 [ref] , capable of not only reconstruct the shape of the object but also provide a 6-axis wrench estimation.
Soft-bubble: A highly compliant dense geometry tactile sensor for robot manipulation · Introduction · 0.97
-
A more recent work involving the use of GelSight was developed by Wang et al. [ref] integrating the use of visual and tactile exploration with learned shape priors for 3D shape reconstruction.
3D Shape Perception from Monocular Vision, Touch, and Shape Priors · Active Exploration for Shape Reconstruction · 0.93
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.