# Robot in the mirror: toward an embodied computational model of mirror self-recognition

arXiv: https://arxiv.org/abs/2011.04485 · HTML: https://mlsanity.com/paper/2011.04485/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2020.

## Built on by (most cited first, 5 of 5)

- [Active Inference in Robotics and Artificial Agents: Survey and Challenges](https://mlsanity.com/paper/2112.01871/) (2021)
- [World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges](https://mlsanity.com/paper/2301.05832/) (2023)
- [Neuroscience-inspired perception-action in robotics: applying active inference for state estimation, control and self-perception](https://mlsanity.com/paper/2105.04261/) (2021)
- [Active Inference with a Self-Prior in the Mirror-Mark Task](https://mlsanity.com/paper/2604.09673/) (2026)
- [MirrorBench: Evaluating Self-centric Intelligence in MLLMs by Introducing a Mirror](https://mlsanity.com/paper/2604.14785/) (2026)

## Abstract (arXiv)

Self-recognition or self-awareness is a capacity attributed typically only to humans and few other species. The definitions of these concepts vary and little is known about the mechanisms behind them. However, there is a Turing test-like benchmark: the mirror self-recognition, which consists in covertly putting a mark on the face of the tested subject, placing her in front of a mirror, and observing the reactions. In this work, first, we provide a mechanistic decomposition, or process model, of what components are required to pass this test. Based on these, we provide suggestions for empirical research. In particular, in our view, the way the infants or animals reach for the mark should be studied in detail. Second, we develop a model to enable the humanoid robot Nao to pass the test. The core of our technical contribution is learning the appearance representation and visual novelty detection by means of learning the generative model of the face with deep auto-encoders and exploiting the prediction error. The mark is identified as a salient region on the face and reaching action is triggered, relying on a previously learned mapping to arm joint angles. The architecture is tested on two robots with a completely different face.