Lanillos et al. 2020: Robot Self/Other Distinction (ECAI 2020)

Prior model using active inference for self-other distinction in mirror setting; lacks motivation source

Neighborhood — ranked by edge-count

Papers (1)

paper

Active Inference with a Self-Prior in the Mirror-Mark Task
cites

Concepts (1)

concept

Self-Other Distinction
about
The implicit capacity the self-prior implements by assigning high density to familiar self-states and low density to non-self states

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

The embodied/disembodied distinction between robots and AI is collapsing.claim0.775
Embodied AI, self-modeling robots, and 'life as it could be' blur the brain-body Cartesian divide.
Robots capable of self-modeling can model their own body and unexpected damage using AI methods, with morphological and mental changes occurring in parallel.finding0.752
Evidence for blurring of embodied robot / non-embodied AI distinction through self-modeling
Steinbeis 2016 - The role of self-other distinction in understanding others' mental and emotional statesconcept0.746
Neuroscience reference on importance of self-other distinctions for social cognition; cited in discussion of preserving useful distinctions
Neither AIs nor humans should be considered autonomous and self-sufficient loops; AI is better understood as a companion for humans.claim0.744
Normative stance on human–AI relationship.
Patterns in AI self-reports should be compared across different models to identify structural commonalities.claim0.737
Updated Robot Definition: a machine capable of physical actions with direct world impacts, able to sense repercussions, partly or completely independent of human action — not binary but a spectrum determined by degree of autonomous control.claim0.732
The paper's proposed new definition of 'robot' as a continuum rather than binary category
The same charitable interpretation must be extended to all systems that display observable response patterns that are consistent with animal cognition, including artificial intelligences, metaplastic materials, and robotic systems.claim0.730
Call to extend the inference of sentience to non-biological systems as well.
Any system that persists must minimise surprisal, thereby gathering evidence for its own generative model, a process known as self-evidencing.claim0.726
Foundational claim of the paper, defining self-evidencing.