Rapid co-design of Buoyancy-assisted robots for Challenging Locomotion using Gaussian Evolutionary Specialists

• URL: http://arxiv.org/abs/2606.07424v1
• Date: Fri, 05 Jun 2026 16:18:15 GMT
• Title: Rapid co-design of Buoyancy-assisted robots for Challenging Locomotion using Gaussian Evolutionary Specialists
• Abstract summary: We useReinforcement Learning to train controllers and evaluate designs for robot morphology optimization.<n>While RL has shown success inlocomotion, using it in the co-design inner loop is expensive due to repeated policy training.<n>We propose a framework that decouples design-space partitioning from policy learning to capture diverse behaviors explicitly.
• Score: 7.552166307522374
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Designing high-performance legged robots requires jointly optimizing morphology and control. Model-free Reinforcement Learning (RL) offers an alternative to model-predictive control for developing robust controllers without explicitly specifying robot dynamics. Thus, we have seen theuse of RL to train controllers and evaluate designs for robot morphology optimization. While RL has shown success inlocomotion, using it in the co-design inner loop is expensive due to repeated policy training. Universal policies conditioned on morphology offer a promising alternative, but suffer from behavioral diversity collapse, converging to a single strategy that performs sub-optimally across designs. On the other hand, end-to-end Mixture-of-Experts (MoE) architectures fail due to a collapse in its representation. We propose Gaussian Evolutionary Specialists (GES), a framework that decouples design-space partitioning from policy learning to capture diverse behaviors explicitly. GES assigns specialist policies to evolving Gaussian regions and iteratively refines them via training, probing, and territory expansion. The resulting specialists are integrated into a design sampling loop, replacing costly re-training with direct evaluation. When tested on the Buoyancy-Assisted Light Legged Unit (BALLU), GES discovers designs with 5 - 25% higher performance than naive universal policies. On hardware, a GES optimized design overcomes a 24 cm tall obstacle - 3x improvement over the baseline BALLU design. Moreover, GES curtails design optimization time by 37%.

Related papers

• HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving [51.268878540511054]
  We propose HAD, an end-to-end planning framework with a Hierarchical Diffusion Policy.<n>We show that HAD achieves new state-of-the-art performance on both NAVSIM and HUGSIM.
  arXiv  Detail & Related papers  (2026-04-04T04:12:47Z)
• Supervising Ralph Wiggum: Exploring a Metacognitive Co-Regulation Agentic AI Loop for Engineering Design [9.290591938055673]
  Agentic AI systems that use Large Language Model (LLM) agents to automate the engineering design process are prone to some of the same pathologies that plague humans.<n>We propose a novel Self-Regulation Loop (SRL) in which the Design Agent self-regulates and explicitly monitors its own metacognition.<n>We also propose a novel Co-Regulation Design Agentic Loop (CRDAL) in which a Metacognitive Co-Regulation Agent assists the Design Agent in metacognition.
  arXiv  Detail & Related papers  (2026-03-25T19:39:42Z)
• Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models [71.9060068259379]
  We propose cascaded domain-wise reinforcement learning to build general-purpose reasoning models.<n>Our 14B model, after RL, outperforms its SFT teacher, DeepSeek-R1-0528, on LiveCodeBench v5/v6 Pro and silver-medal performance in the 2025 International Olympiad in Informatics (IOI)
  arXiv  Detail & Related papers  (2025-12-15T18:02:35Z)
• Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter [52.111923076688505]
  Training Large Language Models (LLMs) with strong reasoning capabilities marks a significant milestone, unlocking new frontiers in complex problem-solving.<n>We propose TLT, a system that accelerates reasoning RL training losslessly by integrating adaptive speculative decoding.
  arXiv  Detail & Related papers  (2025-11-20T18:59:25Z)
• From Supervision to Exploration: What Does Protein Language Model Learn During Reinforcement Learning? [76.288870982181]
  Protein language models (PLMs) have advanced computational protein science through large-scale pretraining and scalable architectures.<n> reinforcement learning (RL) has broadened exploration and enabled precise multi-objective optimization in protein design.<n>We ask if RL improves sampling efficiency and, more importantly, if it reveals capabilities not captured by supervised learning.
  arXiv  Detail & Related papers  (2025-10-02T01:31:10Z)
• RoboMoRe: LLM-based Robot Co-design via Joint Optimization of Morphology and Reward [21.110738533383277]
  RoboMoRe is a framework that integrates morphology and reward shaping for co-optimization within the robot co-design loop.<n>In the coarse optimization stage, an LLM-based diversity reflection mechanism generates both diverse and high-quality morphology-reward pairs.<n>In the fine optimization stage, top candidates are iteratively refined through alternating LLM-guided reward and morphology gradient updates.
  arXiv  Detail & Related papers  (2025-05-30T22:16:07Z)
• Reinforcement Learning for AMR Charging Decisions: The Impact of Reward and Action Space Design [44.99833362998488]
  We propose a novel reinforcement learning (RL) design to optimize the charging strategy for autonomous mobile robots in large-scale block stacking warehouses.<n>Our study focuses on how different reward and action space configurations, ranging from flexible setups to more guided, domain-informed design configurations, affect the agent performance.
  arXiv  Detail & Related papers  (2025-05-16T11:33:29Z)
• Structural Design Through Reinforcement Learning [0.7874708385247352]
  SOgym is a novel open-source Reinforcement Learning environment designed to advance machine learning in Topology Optimization (TO) It generates physically viable and structurally robust designs by integrating the physics of TO into the reward function.
  arXiv  Detail & Related papers  (2024-07-10T00:38:08Z)
• Compositional Generative Inverse Design [69.22782875567547]
  Inverse design, where we seek to design input variables in order to optimize an underlying objective function, is an important problem. We show that by instead optimizing over the learned energy function captured by the diffusion model, we can avoid such adversarial examples. In an N-body interaction task and a challenging 2D multi-airfoil design task, we demonstrate that by composing the learned diffusion model at test time, our method allows us to design initial states and boundary shapes.
  arXiv  Detail & Related papers  (2024-01-24T01:33:39Z)
• ECoDe: A Sample-Efficient Method for Co-Design of Robotic Agents [11.449817465618658]
  Co-designing autonomous robotic agents involves simultaneously optimizing the controller and physical design of the agent. This can be challenging when the design space is large. We propose a multi-fidelity-based exploration strategy to improve the sample efficiency of co-design.
  arXiv  Detail & Related papers  (2023-09-08T02:54:31Z)
• Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration [71.95914457415624]
  Microprocessor architects are increasingly resorting to domain-specific customization in the quest for high-performance and energy-efficiency. We propose an alternative formulation that leverages Multi-Agent RL (MARL) to tackle this problem. Our evaluation shows that the MARL formulation consistently outperforms single-agent RL baselines.
  arXiv  Detail & Related papers  (2022-11-29T17:10:24Z)

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.