Emergent

/ɪˈmɜːdʒ(ə)nt/ — adj. arising from a system's interactions, not present in any of its parts alone

A synthetic ethology platform for ESP32-class hardware.

Introduction

The problem is simple to state and hard to do well: make a small, cheap, battery-powered machine look alive.

Not intelligent in the large-model sense, not conversational, and not necessarily useful for a fixed task. Instead, we want a machine that appears to have:

internal variables that drift over time,
competing needs and priorities,
a body that constrains what it can do,
an environment that pushes back,
a history and imperfect memory,
consequences that follow from its actions,
changing preferences and habits,
periods of activity and rest,
enough stochasticity that its future is not trivially predictable.

Humans are extremely sensitive to motion, timing, and contingency — a few sensors, motors, delays, and feedback loops are enough for us to describe behavior using words like curious, cautious, bored, or interested. In this project, such words are observer-level summaries of dynamics, not claims about subjective experience. The concrete engineering goal is:

Construct a machine whose behavior is best understood in terms of internal regulation, learning, and interaction with its environment, rather than in terms of fixed scripts.

The central constraints are deliberate:

No large neural network.
No cloud inference.
No hand-authored behavior tree.

Glossary

emergent /ɪˈmɜːdʒ(ə)nt/ adj.

arising from a system's interactions, not present in any of its parts alone.
ethology /ɪˈθɒlədʒi/ n.

the study of animal behavior under natural, or naturalistic, conditions.
homeostasis /ˌhəʊmɪəʊˈsteɪsɪs/ n.

the regulation of internal variables to keep them within a viable range.
drive /draɪv/ n.

a pressure toward action, produced by an internal variable deviating from its target.
contingency /kənˈtɪndʒənsi/ n.

a reliable relation between an action and what tends to follow it.
stigmergy /ˈstɪɡmɜːdʒi/ n.

coordination through traces left in a shared environment, rather than direct signaling.
subsumption /səbˈsʌmpʃ(ə)n/ n.

a control scheme in which layered behaviors can override one another with no central planner.
synthetic psychology n. phr.

building simple mechanisms and observing which psychological terms people apply to them.

Status

Layer	Fact
Implemented	20 Hz loop: sense → physiology → drives → memory → action → actuate → learn. Learned sensor→actuator reflexes trained by drive reduction. Named-channel body. SoftAP dashboard. Life-state JSON. Station firmware as a separate state machine.
Tested	Host-native tests for bit packing, age saturation, rate-limit clamp, LEDC cap, and organism behavior (energy dynamics, contingency bias, reflex learning rule) against a fake body. Not real hardware.
Simulated	The unmodified engine in a modelled room with a station (`src/sim`): learned reflexes lift mean lifespan from 1.26 h to 1.86 h (hand-wired bound 2.46 h). Learns to reach and stay on the dock; not yet to leave when full, and nothing accumulates across lives. Watch one organism.
Hardware tested	Nothing. No board has run this.
Designed / planned	Body declared in a JSON file with per-input ranges, stepper and mic-envelope channel kinds (example build); approach-and-dock on hardware; extra boards.
Hypothesis	That drives + decaying memory + learned reflexes + noise will look alive on real hardware, including charging as an attractor. Unverified.

Changelog · Full roadmap · Research notes · Example build (7 in, 5 out)

Build

cd src/esp32
pio run -e esp32dev              # or -e esp32-s3-devkitc-1
pio run -e esp32dev -t uploadfs   # flash the dashboard filesystem
pio run -e esp32dev -t upload     # flash the firmware
pio test -e native                # host-native unit + behavior-scenario tests

Full spec: the paper (PDF). Firmware layout, adding a board/channel, and the dashboard API: src/esp32/README.md. Firmware releases: GitHub Releases.