Categories: Embodied Federalism

16 entries

Intelligence grows in systems that deal with the world: perception, planning and control, each doing its part.

Object-Centrism
Holds that scenes should be represented as sets of discrete objects, each with its own slot, rather than as undifferentiated feature maps.
Objectiveless Anarchism
Ambitious objectives are deceptive; open-ended search for novelty and interestingness finds stepping stones that goal-driven optimisation never would.
Open-Hardware Mutualism
Robot bodies, sensors and datasets should be shared openly so that embodied AI is built as a commons, not a moat.
Distributed Embodiment
One learning system should inhabit many bodies at once, pooling experience across a fleet of robots into a shared mind.
Edge-AI Localism
Inference belongs on the device, close to the sensors and the user, for latency, privacy, cost and resilience.
Emergent-Language Doctrine
Agents should invent their own communication through shared tasks, so language is grounded in use rather than copied from human text.
Morphological Computationalism
A well-designed body does much of the computing itself, so intelligence should be offloaded into materials, springs and shape.
Intuitive-Physics Doctrine
Holds that AI should first acquire the core physical intuitions infants show, such as object permanence, solidity and continuity, before anything more abstract.
Hierarchical Control
Control should be layered, with slow high-level planners setting goals and fast low-level controllers executing them.
Field-Robotics Libertarianism
Robots prove themselves only in uncontrolled real environments; whatever works in mud, rain and dust is right, whatever only works in the lab is not.
Vehicle Primitivism
A light-seeking little vehicle with two sensors and two wires already shows behaviour we call fear, love and curiosity; start there.
Morphological Anarchism
Bodies and brains should co-evolve freely; no fixed robot form, humanoid or otherwise, deserves to be the default.
Robot Federalism
A robot should be a federation of separate perception, planning and control modules with clean interfaces, not one end-to-end network.
Model-Market Anarchism
No model should rule; a free market of models, with routers sending each request to the cheapest one that is good enough, wins.
Swarm Robotics
Many simple, cheap robots following local rules can achieve robust collective behavior that no single complex robot could.
Sensor-Network Anarchism
Perception should be spread across countless cheap networked sensors that process locally and share signals, like neurons in a planetary nervous system.