Shape Your Body: Value Gradients for Multi-Embodiment Robot Design

• URL: http://arxiv.org/abs/2606.00702v1
• Date: Sat, 30 May 2026 12:21:09 GMT
• Title: Shape Your Body: Value Gradients for Multi-Embodiment Robot Design
• Abstract summary: We propose to turn generalist multi-embodiment value functions into reusable models for robot design.<n>Instead of running a new reinforcement learning co-design loop for each robot, we first train an embodiment-aware policy and value function across many robot designs.
• Score: 16.640420524594443
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose to turn generalist multi-embodiment value functions into reusable models for robot design. Instead of running a new reinforcement learning co-design loop for each robot, we first train an embodiment-aware policy and value function across many robot designs. After training, the frozen value function is used as a differentiable surrogate to optimize candidate embodiments through value gradients. We evaluate our approach across different robot design settings, from perturbed single robots to held-out robots across morphology classes, with single models trained on up to 50 robots and design spaces of over 1100 continuous embodiment parameters. Beyond optimizing complete embodiments, we show that value gradients can identify performance-limiting design and control parameters, enabling both the optimization and the analysis of new robot designs.

Related papers

• Transformer Transformer: A Unified Model for Motion-Conditioned Robot Co-design [29.19489133790808]
  Transformer Transformer is a dynamics model, whose reward-agnostic state and action predictions can be converted into reward-specific value predictions.<n>We fabricated an optimized ALOHA design, which reduced tracking error by over 70% compared to the original design.
  arXiv  Detail & Related papers  (2026-07-28T14:47:14Z)
• RobotSeg: A Model and Dataset for Segmenting Robots in Image and Video [56.9581053843815]
  We introduce RobotSeg, a foundation model for robot segmentation in image and video.<n>It addresses the lack of adaptation to articulated robots, reliance on manual prompts, and the need for per-frame training mask annotations.<n>It achieves state-of-the-art performance on both images and videos.
  arXiv  Detail & Related papers  (2025-11-28T07:51:02Z)
• A Design Co-Pilot for Task-Tailored Manipulators [21.513483509321805]
  This work proposes an approach to automatically designing and optimizing robot morphologies tailored to a specific environment.<n>A fully differentiable framework realizes gradient-based fine-tuning of designed robots and inverse kinematics solutions.<n> Numerical experiments show that our approach finds robots that can navigate cluttered environments, manipulators that perform well across a specified workspace, and can be adapted to different hardware constraints.
  arXiv  Detail & Related papers  (2025-09-16T13:34:30Z)
• Holistic Construction Automation with Modular Robots: From High-Level Task Specification to Execution [7.012962572096341]
  In situ robotic automation in construction is challenging due to constantly changing environments, a shortage of robotic experts, and a lack of standardized frameworks bridging robotics and construction practices.<n>This work proposes a holistic framework for construction task specification, optimization of robot morphology, and mission execution using a mobile modular reconfigurable robot.
  arXiv  Detail & Related papers  (2024-12-30T11:11:13Z)
• MuTT: A Multimodal Trajectory Transformer for Robot Skills [14.84252843639553]
  MuTT is a novel encoder-decoder transformer architecture designed to predict environment-aware executions of robot skills. We pioneer the fusion of vision and trajectory, introducing a novel trajectory projection. This approach facilitates the optimization of robot skill parameters for the current environment, without the need for real-world executions.
  arXiv  Detail & Related papers  (2024-07-22T14:18:52Z)
• DiffGen: Robot Demonstration Generation via Differentiable Physics Simulation, Differentiable Rendering, and Vision-Language Model [72.66465487508556]
  DiffGen is a novel framework that integrates differentiable physics simulation, differentiable rendering, and a vision-language model. It can generate realistic robot demonstrations by minimizing the distance between the embedding of the language instruction and the embedding of the simulated observation. Experiments demonstrate that with DiffGen, we could efficiently and effectively generate robot data with minimal human effort or training time.
  arXiv  Detail & Related papers  (2024-05-12T15:38:17Z)
• RoboScript: Code Generation for Free-Form Manipulation Tasks across Real and Simulation [77.41969287400977]
  This paper presents textbfRobotScript, a platform for a deployable robot manipulation pipeline powered by code generation. We also present a benchmark for a code generation benchmark for robot manipulation tasks in free-form natural language. We demonstrate the adaptability of our code generation framework across multiple robot embodiments, including the Franka and UR5 robot arms.
  arXiv  Detail & Related papers  (2024-02-22T15:12:00Z)
• Robot Learning with Sensorimotor Pre-training [98.7755895548928]
  We present a self-supervised sensorimotor pre-training approach for robotics. Our model, called RPT, is a Transformer that operates on sequences of sensorimotor tokens. We find that sensorimotor pre-training consistently outperforms training from scratch, has favorable scaling properties, and enables transfer across different tasks, environments, and robots.
  arXiv  Detail & Related papers  (2023-06-16T17:58:10Z)
• GLSO: Grammar-guided Latent Space Optimization for Sample-efficient Robot Design Automation [16.96128900256427]
  We present Grammar-guided Latent Space Optimization (GLSO), a framework that transforms design automation into a low-dimensional continuous optimization problem. In this work, we present a framework that transforms design automation into a low-dimensional continuous optimization problem by training a graph variational autoencoder (VAE) to learn a mapping between the graph-structured design space and a continuous latent space.
  arXiv  Detail & Related papers  (2022-09-23T17:48:24Z)
• A Capability and Skill Model for Heterogeneous Autonomous Robots [69.50862982117127]
  capability modeling is considered a promising approach to semantically model functions provided by different machines. This contribution investigates how to apply and extend capability models from manufacturing to the field of autonomous robots.
  arXiv  Detail & Related papers  (2022-09-22T10:13:55Z)
• REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer [57.045140028275036]
  We consider the problem of transferring a policy across two different robots with significantly different parameters such as kinematics and morphology. Existing approaches that train a new policy by matching the action or state transition distribution, including imitation learning methods, fail due to optimal action and/or state distribution being mismatched in different robots. We propose a novel method named $REvolveR$ of using continuous evolutionary models for robotic policy transfer implemented in a physics simulator.
  arXiv  Detail & Related papers  (2022-02-10T18:50:25Z)

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.