Related Experiment Video
Updated: Jan 27, 2026
08:52
Novel Object Recognition Test for the Investigation of Learning and Memory in Mice
Published on: August 30, 2017
77.3K
An Application of Deep Learning to Tactile Data for Object Recognition under Visual Guidance
Ghazal Rouhafzay1, Ana-Maria Cretu2
1Department of Systems and Computer Engineering, Carleton University, Ottawa, ON K1S 5B6, Canada. ghazal.rouhafzay@carleton.ca.
Sensors (Basel, Switzerland)
|April 3, 2019
Summary
This study introduces a new robotic tactile object recognition framework using visual cues to guide data collection. A hybrid Convolutional Neural Network (CNN) approach achieved 98.97% accuracy, enhancing robotic perception capabilities.
Area of Science:
- Robotics
- Artificial Intelligence
- Neuroscience
Background:
- Human object recognition integrates tactile and kinesthetic data.
- Humans use object contours for shape perception and recognition.
- Robotic systems can benefit from bio-inspired tactile sensing strategies.
Purpose of the Study:
- To propose a novel framework for robotic tactile object recognition.
- To integrate visual information for guiding tactile data acquisition.
- To develop and evaluate advanced classification methods for tactile data.
Main Methods:
- A framework using visual attention points to guide tactile data acquisition from virtual objects.
- Bimodal (cutaneous and kinesthetic) tactile data collection using a virtual Force Sensing Resistor (FSR) array.
- Classification using Convolutional Neural Networks (CNNs) and conventional methods (SVM, k-NN) with contourlet transformation.
Main Results:
- A hybrid CNN approach with visual attention-guided contours achieved 98.97% accuracy.
- The CNN trained on visually guided contours outperformed other methods.
- Adaptive sensor surface sizing improved data acquisition based on object geometry.
Conclusions:
- The proposed framework effectively enhances robotic tactile object recognition.
- Integrating visual attention significantly improves recognition accuracy.
- Bio-inspired multimodal tactile sensing and advanced deep learning are promising for robotics.
Related Concept Videos
01:27Tactile and Chemical Senses
745
Tactile senses encompass touch, temperature, and pain, each mediated by specific receptors. Touch receptors detect mechanical energy or pressure against the skin. Sensory fibers from these receptors enter the spinal cord and relay information to the brain stem. Here, most fibers cross over to the opposite side of the brain. The touch information then moves to the thalamus, which projects a map of the body's surface onto the somatosensory areas of the parietal lobes in the cerebral cortex.
745
01:14Avoidance Learning and Learned Helplessness
2.5K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
2.5K
01:29Potential Due to a Polarized Object
759
A neutral atom consists of a positively charged nucleus surrounded by a negatively charged electron cloud. When placed in an external electric field, the external electric force pulls the electrons and nucleus apart, opposite to the intrinsic attraction between the nucleus and the electrons. The opposing forces balance each other with a slight shift between the center of masses of the nucleus and the electron cloud, resulting in a polarized atom. On the other hand, a few molecules, like water,...
759
01:24Potential Due to a Magnetized Object
780
Magnetic dipoles in magnetic materials are aligned when placed under an external magnetic field. For paramagnets and ferromagnets, dipole alignment occurs in the direction of the magnetic field. However, the dipoles align opposite to the field in the case of diamagnets. This state of magnetic polarization due to the external field is called magnetization. Magnetization is defined as the dipole moment per unit volume. It plays a similar role to polarization in electrostatics.
The vector...
The vector...
780
01:24Data Reporting and Recording
5.4K
Reporting and recording are crucial in data documentation. The timely, thorough, and accurate documentation of facts is essential when recording patient data. Failure to record findings during an assessment or interpretation of a problem will result in loss of information and make the patient document unreliable. The reader is left with general impressions if the information is not specific. A recording is documenting data of the individual's health information in a traceable, secure, and...
5.4K
00:59How Data are Classified: Numerical Data
37.2K
Data that are countable or measurable in specific units are called numerical or quantitative data. Quantitative data are always numbers. Quantitative data are the result of counting or measuring the attributes of a population. Amount of money, pulse rate, weight, number of people living in a town, and number of students who opt for statistics are examples of quantitative data.
Quantitative data may be either discrete or continuous. All quantitative data that take on only specific numerical...
Quantitative data may be either discrete or continuous. All quantitative data that take on only specific numerical...
37.2K