Embodied Theory of Mind Data for Humanoid Robot Social Learning

A novel architecture called embodied theory of mind was developed to link high-level cognitive skills to the low-level perceptual abilities of a humanoid robot. The implemented system determines visual saliency based on inherent object attributes, high-level task constraints, and the attentional states of others. The work is authored by Brian Scassellati and copies are available exclusively from MIT Libraries.

Use Cases

• Training robots to detect eye contact and head orientation based on perceptual data.
• Developing models to attribute intent to moving objects based on motion trajectory analysis.
• Evaluating social learning mechanisms, such as movement mimicry, in robotic systems.
• Building systems that interpret behavior according to social rules like theory of mind.

Strengths

• System components are evaluated by comparisons to human performance on similar tasks.
• The complete system is evaluated in the context of a basic social learning mechanism.
• Architecture draws from established models of Baron-Cohen (1995) and Leslie (1994).

Limitations

• Row count, file formats, and sample data are unknown, limiting suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• License is closed, restricting access and reuse.

Provenance

Source

Brian Scassellati

Collection Method

Likely contains experimental data from a humanoid robot system implementing an embodied theory of mind architecture.

Time Range

null

Freshness

Last update date is unknown; freshness unverified.

Geography

null