ECo-MoE: Embodiment-Conditioned Mixture of Experts Increases the Evolvability of Robots

• URL: http://arxiv.org/abs/2605.24225v1
• Date: Fri, 22 May 2026 21:11:47 GMT
• Title: ECo-MoE: Embodiment-Conditioned Mixture of Experts Increases the Evolvability of Robots
• Abstract summary: We introduce a model of evolution and learning in robots that co-optimizes a distribution of latent design vectors (genotypes) and a mixture of control experts (neural modules)<n>We refer to this process as "evo by demo" and explore how it may be used to guide freeform evolution toward canonical structures.
• Score: 9.541468090679913
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we introduce a model of evolution and learning in robots that co-optimizes a distribution of latent design vectors (genotypes) and a mixture of control experts (neural modules), which are gated by the latent coordinates of each decoded design (phenotype). This provides a scalable alternative to co-design algorithms that either train an individual policy for every robot, which is inefficient, or a monolithic universal controller for all robots, which results in overly conservative structures and behaviors. Our approach lies somewhere between these two extremes, preserving ancestral knowledge in a unified yet modular framework in which different body plans activate and deactivate different combinations of learned sensorimotor circuits for goal-directed behavior. This allows one part of the controller to be overhauled to better suit new species of designs as they emerge without disrupting the hard-earned knowledge contained within other expert modules. It also allows pretrained expert policies to be directly plugged into the mixture, which can steer evolution into otherwise unexplored areas of latent space containing desired morphological traits. We refer to this process as "evo by demo" and explore how it may be used to guide freeform evolution toward canonical structures defined by the pretrained model. Videos and code can be found at: https://eco-moe.github.io.

Related papers

• Learning Context-Aware Neural ODE Dynamics for Adaptive Robotic Control [55.01272784312405]
  We propose a context-aware dynamics model based on neural ordinary differential equations.<n>We validate the approach across diverse robotic platforms, including a quadrotor in simulation, as well as a Sphero BOLT robot and a Fanuc manipulator in real-world experiments.
  arXiv  Detail & Related papers  (2026-06-13T20:55:46Z)
• Evolution and learning in differentiable robots [0.0]
  We use differentiable simulations to rapidly and simultaneously optimize individual neural control of behavior across a large population of candidate body plans. Non-differentiable changes to the mechanical structure of each robot in the population were applied by a genetic algorithm in an outer loop of search. One of the highly differentiable morphologies discovered in simulation was realized as a physical robot and shown to retain its optimized behavior.
  arXiv  Detail & Related papers  (2024-05-23T15:45:43Z)
• DARLEI: Deep Accelerated Reinforcement Learning with Evolutionary Intelligence [77.78795329701367]
  We present DARLEI, a framework that combines evolutionary algorithms with parallelized reinforcement learning. We characterize DARLEI's performance under various conditions, revealing factors impacting diversity of evolved morphologies. We hope to extend DARLEI in future work to include interactions between diverse morphologies in richer environments.
  arXiv  Detail & Related papers  (2023-12-08T16:51:10Z)
• DiffuseBot: Breeding Soft Robots With Physics-Augmented Generative Diffusion Models [102.13968267347553]
  We present DiffuseBot, a physics-augmented diffusion model that generates soft robot morphologies capable of excelling in a wide spectrum of tasks. We showcase a range of simulated and fabricated robots along with their capabilities.
  arXiv  Detail & Related papers  (2023-11-28T18:58:48Z)
• Drive Anywhere: Generalizable End-to-end Autonomous Driving with Multi-modal Foundation Models [114.69732301904419]
  We present an approach to apply end-to-end open-set (any environment/scene) autonomous driving that is capable of providing driving decisions from representations queryable by image and text. Our approach demonstrates unparalleled results in diverse tests while achieving significantly greater robustness in out-of-distribution situations.
  arXiv  Detail & Related papers  (2023-10-26T17:56:35Z)
• Open-endedness induced through a predator-prey scenario using modular robots [0.0]
  This work investigates how a predator-prey scenario can induce the emergence of Open-Ended Evolution (OEE) We utilize modular robots of fixed morphologies whose controllers are subject to evolution.
  arXiv  Detail & Related papers  (2023-09-20T12:58:51Z)
• Universal Morphology Control via Contextual Modulation [52.742056836818136]
  Learning a universal policy across different robot morphologies can significantly improve learning efficiency and generalization in continuous control. Existing methods utilize graph neural networks or transformers to handle heterogeneous state and action spaces across different morphologies. We propose a hierarchical architecture to better model this dependency via contextual modulation.
  arXiv  Detail & Related papers  (2023-02-22T00:04:12Z)
• Co-evolving morphology and control of soft robots using a single genome [0.0]
  We present a new method to co-evolve morphology and control of robots. Our method derives both the "brain" and the "body" of an agent from a single genome and develops them together. We evaluate the presented methods on four tasks and observe that even if the search space was larger, having a single genome makes the evolution process converge faster.
  arXiv  Detail & Related papers  (2022-12-22T07:34:31Z)
• Evolving Modular Soft Robots without Explicit Inter-Module Communication using Local Self-Attention [9.503773054285556]
  We focus on Voxel-based Soft Robots (VSRs) We use the same neural controller inside each voxel, but without any inter-voxel communication. We show experimentally that the evolved robots are effective in the task of locomotion.
  arXiv  Detail & Related papers  (2022-04-13T16:03:39Z)
• Morpho-evolution with learning using a controller archive as an inheritance mechanism [4.364091192392204]
  We propose a framework that combines an evolutionary algorithm to generate body-plans and a learning algorithm to optimise the parameters of a neural controller. By inheriting an appropriate controller from an archive rather than learning from a randomly initialised one, we show that both the speed and magnitude of learning increases over time. The framework also provides new insights into the complex interactions between evolution and learning, and the role of morphological intelligence in robot design.
  arXiv  Detail & Related papers  (2021-04-09T09:32:36Z)
• Deep Imitation Learning for Bimanual Robotic Manipulation [70.56142804957187]
  We present a deep imitation learning framework for robotic bimanual manipulation. A core challenge is to generalize the manipulation skills to objects in different locations. We propose to (i) decompose the multi-modal dynamics into elemental movement primitives, (ii) parameterize each primitive using a recurrent graph neural network to capture interactions, and (iii) integrate a high-level planner that composes primitives sequentially and a low-level controller to combine primitive dynamics and inverse kinematics control.
  arXiv  Detail & Related papers  (2020-10-11T01:40:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.