Learning to control self-assembling morphologies: A study of generalization via modularity
Author(s)Isola, Phillip John
MetadataShow full item record
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/.
DepartmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Advances in Neural Information Processing Systems
Pathak, Deepak et al. “Learning to control self-assembling morphologies: A study of generalization via modularity.” Advances in Neural Information Processing Systems, 32 (December 2019) © 2019 The Author(s)
Final published version