Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity
Deepak Pathak, Chris Lu, Trevor Darrell, Phillip Isola, Alexei A. Efros
- Year
- 2019
- Access
- Open access
Abstract
Contemporary sensorimotor learning approaches typically start with an existing complex agent (e.g., a robotic arm), which they learn to control. In contrast, this paper investigates a modular co-evolution strategy: a collection of primitive agents learns to dynamically self-assemble into composite bodies while also learning to coordinate their behavior to control these bodies. Each primitive agent consists of a limb with a motor attached at one end. Limbs may choose to link up to form collectives. When a limb initiates a link-up action, and there is another limb nearby, the latter is magnetically connected to the 'parent' limb's motor. This forms a new single agent, which may further link with other agents. In this way, complex morphologies can emerge, controlled by a policy whose architecture is in explicit correspondence with the morphology. We evaluate the performance of these dynamic and modular agents in simulated environments. We demonstrate better generalization to test-time changes both in the environment, as well as in the structure of the agent, compared to static and monolithic baselines. Project video and code are available at https://pathak22.github.io/modular-assemblies/
Keywords
Related papers
A dual-loop framework for manufacturability-aware topology optimization of electric vehicle structures via wire arc additive manufacturing
Qiang Cui, Chuan Yu, Daoqian Yang +2 more
Robotics and Computer-Integrated Manufacturing · 2026
Geometric digital twin: A digital and intelligent model for aero-engine assembly accuracy prediction
Ke Shang, Xin Jin, Teli Xu +4 more
Robotics and Computer-Integrated Manufacturing · 2026
Revolutionizing Industries Through AI-Driven Robotics
Aryan Chaudhary
Recent Advances in Computer Science and Communications · 2026
Design and dynamic performance prediction of a novel large-aperture offset-feed deployable antenna
Chuang Shi, Tianming Liu, Ning Xue +6 more
Aerospace Science and Technology · 2026