Articulated-Body Dynamics Network: Dynamics-Grounded Prior for Robot Learning

• URL: http://arxiv.org/abs/2603.19078v2
• Date: Fri, 20 Mar 2026 19:11:52 GMT
• Title: Articulated-Body Dynamics Network: Dynamics-Grounded Prior for Robot Learning
• Abstract summary: We present the Articulated-Body Dynamics Network (ABD-Net), a novel graph neural network architecture grounded in the computational structure of forward dynamics.<n>Our approach demonstrates increased sample efficiency and generalization to dynamics shifts compared to transformer-based and GNN baselines.<n>We further validate the learned policy on real Unitree G1 and Go2 robots, state-of-the-art humanoid and quadruped platforms.
• Score: 14.046146512352315
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent work in reinforcement learning has shown that incorporating structural priors for articulated robots, such as link connectivity, into policy networks improves learning efficiency. However, dynamics properties, despite their fundamental role in determining how forces and motion propagate through the body, remain largely underexplored as an inductive bias for policy learning. To address this gap, we present the Articulated-Body Dynamics Network (ABD-Net), a novel graph neural network architecture grounded in the computational structure of forward dynamics. Specifically, we adapt the inertia propagation mechanism from the Articulated Body Algorithm, systematically aggregating inertial quantities from child to parent links in a tree-structured manner, while replacing physical quantities with learnable parameters. Embedding ABD-NET into the policy actor enables dynamics-informed representations that capture how actions propagate through the body, leading to efficient and robust policy learning. Through experiments with simulated humanoid, quadruped, and hopper robots, our approach demonstrates increased sample efficiency and generalization to dynamics shifts compared to transformer-based and GNN baselines. We further validate the learned policy on real Unitree G1 and Go2 robots, state-of-the-art humanoid and quadruped platforms, generating dynamic, versatile and robust locomotion behaviors through sim-to-real transfer with real-time inference.

Related papers

• Controlled Dynamics Attractor Transformer [58.15454173718687]
  Transformer architectures have advanced representation learning and inference in deep models through self-attention mechanisms.<n>In parallel,associative memory (AM) frameworks map representations onto energy landscapes, offering interpretable retrieval mechanisms.<n>We propose Controlled Dynamics Attractor Transformer (CCAT), which couples a mixture von Mises-Fisher (Mo-vMF) attention energy with a Hopfield refinement energy.<n>CCAT achieves state-of-the-art performance across multiple benchmarks in graph anomaly detection and graph classification.
  arXiv  Detail & Related papers  (2026-06-13T09:04:22Z)
• Sim-to-Real Transfer for Muscle-Actuated Robots via Generalized Actuator Networks [53.12548325396181]
  Tendon drives paired with soft muscle actuation enable faster and safer robots.<n>We propose a sim-to-real pipeline that learns a neural network model of this complex actuation.<n>We successfully deploy precise goal-reaching and dynamic ball-in-a-cup policies trained entirely in simulation.
  arXiv  Detail & Related papers  (2026-04-10T16:52:54Z)
• Hebbian Attractor Networks for Robot Locomotion [44.84033948079516]
  Hebbian plasticity offers a promising path toward rapid adaptation in changing environments.<n>Hebbian Attractor Networks (HANs) induce emergent attractor dynamics.<n>Results show that slower updates, combined with averaged pre- and postsynaptic activations, promote convergence to stable weight configurations.
  arXiv  Detail & Related papers  (2026-03-23T19:20:14Z)
• D-REX: Differentiable Real-to-Sim-to-Real Engine for Learning Dexterous Grasping [66.22412592525369]
  We introduce a real-to-sim-to-real engine that leverages the Gaussian Splat representations to build a differentiable engine.<n>We show that our engine achieves accurate and robust performance in mass identification across various object geometries and mass values.<n>Those optimized mass values facilitate force-aware policy learning, achieving superior and high performance in object grasping.
  arXiv  Detail & Related papers  (2026-03-01T15:32:04Z)
• AdaWorldPolicy: World-Model-Driven Diffusion Policy with Online Adaptive Learning for Robotic Manipulation [12.592383721590402]
  We introduce a unified framework, World-Model-Driven Diffusion Policy with Online Adaptive Learning (AdaWorldPolicy)<n>Our core insight is that world models provide strong supervision signals, enabling online adaptive learning in dynamic environments.<n>AdaWorldPolicy achieves state-of-the-art performance, with dynamical adaptive capacity to out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2026-02-23T17:12:25Z)
• Machine Learning and Control: Foundations, Advances, and Perspectives [0.0]
  We show that concepts such as simultaneous and ensemble controllability offer new insights into the classification and representation properties of deep neural networks.<n>We also explore the relationship between dynamic and static neural networks, where depth is traded for width.<n>We describe how classical properties of diffusion processes, long established in the context of partial differential equations, contribute to explaining the success of modern generative artificial intelligence.
  arXiv  Detail & Related papers  (2025-09-30T10:47:26Z)
• Domain Translation of a Soft Robotic Arm using Conditional Cycle Generative Adversarial Network [0.8624680612413766]
  We introduce a domain translation framework based on a conditional cycle generative adversarial network (CCGAN)<n>Our model learns from input pressure signals conditioned on corresponding end-effector positions and orientations in both domains.
  arXiv  Detail & Related papers  (2025-08-16T15:47:35Z)
• Rodrigues Network for Learning Robot Actions [76.69283501115855]
  We propose the Neural Rodrigues Operator to inject kinematics-aware inductive bias into neural computation.<n>We design the Rodrigues Network (RodriNet), a novel neural architecture specialized for processing actions.<n>Our results suggest that integrating structured kinematic priors into the network architecture improves action learning in various domains.
  arXiv  Detail & Related papers  (2025-06-03T08:34:06Z)
• Multi-Agent Dynamic Relational Reasoning for Social Robot Navigation [50.01551945190676]
  Social robot navigation can be helpful in various contexts of daily life but requires safe human-robot interactions and efficient trajectory planning. We propose a systematic relational reasoning approach with explicit inference of the underlying dynamically evolving relational structures. We demonstrate its effectiveness for multi-agent trajectory prediction and social robot navigation.
  arXiv  Detail & Related papers  (2024-01-22T18:58:22Z)
• Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking [76.27433308688592]
  Accurately modeling quadrotor's system dynamics is critical for guaranteeing agile, safe, and stable navigation. We present a novel Physics-Inspired Temporal Convolutional Network (PI-TCN) approach to learning quadrotor's system dynamics purely from robot experience. Our approach combines the expressive power of sparse temporal convolutions and dense feed-forward connections to make accurate system predictions.
  arXiv  Detail & Related papers  (2022-06-07T13:51:35Z)
• GEM: Group Enhanced Model for Learning Dynamical Control Systems [78.56159072162103]
  We build effective dynamical models that are amenable to sample-based learning. We show that learning the dynamics on a Lie algebra vector space is more effective than learning a direct state transition model. This work sheds light on a connection between learning of dynamics and Lie group properties, which opens doors for new research directions.
  arXiv  Detail & Related papers  (2021-04-07T01:08:18Z)
• Neural Dynamic Policies for End-to-End Sensorimotor Learning [51.24542903398335]
  The current dominant paradigm in sensorimotor control, whether imitation or reinforcement learning, is to train policies directly in raw action spaces. We propose Neural Dynamic Policies (NDPs) that make predictions in trajectory distribution space. NDPs outperform the prior state-of-the-art in terms of either efficiency or performance across several robotic control tasks.
  arXiv  Detail & Related papers  (2020-12-04T18:59:32Z)
• Deep learning of contagion dynamics on complex networks [0.0]
  We propose a complementary approach based on deep learning to build effective models of contagion dynamics on networks. By allowing simulations on arbitrary network structures, our approach makes it possible to explore the properties of the learned dynamics beyond the training data. Our results demonstrate how deep learning offers a new and complementary perspective to build effective models of contagion dynamics on networks.
  arXiv  Detail & Related papers  (2020-06-09T17:18:34Z)

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.