Timezone: »

Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity
Deepak Pathak · Christopher Lu · Trevor Darrell · Phillip Isola · Alexei Efros

Tue Dec 10 04:30 PM -- 04:35 PM (PST) @ West Ballroom A + B

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 videos and source code are provided in the supplementary material.

Author Information

Deepak Pathak (UC Berkeley, FAIR, CMU)
Chris Lu (UC Berkeley and Covariant.ai)
Trevor Darrell (UC Berkeley)
Phillip Isola (Massachusetts Institute of Technology)
Alexei Efros (UC Berkeley)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors