Related Experiment Video
Updated: Dec 27, 2025

Creating Objects and Object Categories for Studying Perception and Perceptual Learning
Published on: November 2, 2012
Learning to Predict Perceptual Distributions of Haptic Adjectives
Benjamin A Richardson1, Katherine J Kuchenbecker1
1Haptic Intelligence Department, Max Planck Institute for Intelligent Systems, Stuttgart, Germany.
This study introduces a machine learning method enabling robots to perceive tactile properties like hardness and roughness, accounting for human perception variability. The approach models both the intensity and variation in haptic perception for improved robotic intelligence.
Area of Science:
- Robotics
- Artificial Intelligence
- Human-Computer Interaction
Background:
- Human tactile perception is subjective and variable, posing challenges for robotic systems.
- Previous robotic haptic intelligence research focused on binary attributes, neglecting intensity and variability.
Purpose of the Study:
- To develop a machine learning method for robots to predict ordinal haptic adjective distributions.
- To incorporate human perceptual variability and attribute intensity into robotic tactile sensing.
Main Methods:
- Collected ordinal haptic adjective labels from human subjects for 60 objects.
- Extracted features from multi-modal tactile data gathered by a robot.
- Designed a machine learning model integrating partial label distribution knowledge for training.
Main Results:
- The developed method predicts a probability distribution over ordinal haptic labels from a single interaction.
- Demonstrated the model's ability to capture both intensity and variation in haptic perception.
- Analyzed the influence of individual sensor modalities on adjective prediction.
Conclusions:
- The study successfully models intensity and variation in haptic perception, crucial for human-like robotic tactile intelligence.
- This work advances robotic capabilities in understanding and replicating nuanced tactile experiences.
Related Concept Videos
Sensory Modalities
General senses refer to the broad category of sensory information detected by receptors in the body and can be further grouped into somatic and visceral senses. Somatic sensations include touch, pressure, temperature, and pain and are essential for navigating our environment and...
Perceiving Loudness, Pitch, and Location
Place theory, or place coding, suggests that different pitches are heard because various sound waves activate specific locations along the cochlea's basilar membrane. The brain determines the pitch of a sound by...
Sensory Perception: Organization of the Somatosensory System
The receptor level:
The receptor level is the first stage of sensation. It involves the detection of a stimulus by specialized sensory receptors. The stimulus must arrive within the receptor's receptive field. Next, the receptor converts the energy of the...
Somatosensation
Tactile and Chemical Senses
Perceptual Constancy
Size constancy is the recognition that an object remains the same size, even when its image on the retina changes. For instance, a bus is perceived to be large enough to carry people, even if it looks tiny from...

