Robot Dynamics Learning

Follow this topic Ask about this topic

Momentum

11 papers in the last four weeks, with none the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 27

Oct 6, 2026cs.RO

FlashNeRD: Performance-First Contact-Rich Neural Robot Dynamics

Compared with analytical physics, learned dynamics models promise robot simulation that is faster, inherently differentiable, and easily adaptable to real data. Neural Robot Dynamics (NeRD) pursues this by keeping collision detection analytical and replacing a simulator's numerical dynamics for the robot with a learned model. Three limitations remain. NeRD offers little speedup over the simulator it learned from, accepts contact only at predefined points, and has no two-way coupling with objects it manipulates. FlashNeRD removes all three with a parallel streaming architecture that makes each prediction faster and more accurate, an encoder that accepts contacts wherever they occur, and two-way coupling with objects simulated by analytical solvers. Experiments across five robots show faster and more accurate dynamics, faster policy learning, and faster inference-time planning. Across three robots, FlashNeRD's dynamics model is up to

55\times

faster than an optimized NeRD and more accurate over long rollouts. This speedup extends to policy learning, where PPO trains an ANYmal locomotion policy in 34 seconds,

3.8\times

faster than the analytical simulator and

2.7\times

faster than an optimized NeRD. With DIAL-MPC, a sampling-based MPC method, the robot climbs all six test platforms where fixed-contact NeRD manages one, at approximately half the analytical simulator's planning time. Cube-reorientation policies trained with FlashNeRD complete within 2% of the simulator-trained policy's target count.

Mohammadmehdi Ataei, Mohammad Amin Nabian, Jie Xu +9

NVIDIA

Robot Dynamics Learning Robotics Simulation Robotic Control

Oct 6, 2026cs.RO

OpenWAM: An Open Framework for Composable World-Action Models

World-action models (WAMs) couple future prediction with robot control, yet existing systems often vary the video backbone, interaction structure, supervision, and inference procedure simultaneously, making their design choices difficult to compare. We introduce OPENWAM, an open world-action modeling framework built around a common causal robot-video foundation and configurable video-action interaction. Starting from Wan2.2-5B, we perform causal robot-video pretraining on over 10,000 hours of video, then integrate an action expert through a shared Mixture-of-Transformers architecture that supports joint, video-then-action, action-then-video, and decoupled generation. OPENWAM achieves high success rates on four LIBERO suites and real-world bimanual tasks; robot-video training with causal adaptation improves VTA success on LIBERO-Long from 68.4% to 97.8%. The same configurable architecture naturally extends to inverse and forward dynamics, allowing us to study how counterfactual transitions improve independently trained dynamics models beyond demonstrations alone. When only the video predictor is adapted to a new task, a frozen local-context inverse dynamics model trained on counterfactual data and demonstrations achieves 84.0% mean success across four held-out LIBERO-90 tasks, compared with 47.0% for a full-context inverse model and 21.5% for a local-context model trained only on demonstrations. For forward dynamics, counterfactual supervision reduces RGB prediction error by 34.5% and raises outcome identification from 21.1% to 71.3% among 16 same-state outcomes. OPENWAM provides a common testbed for comparing WAM interaction designs and for studying dynamics learning from video data beyond successful demonstrations.

Heng Yu, David D. Yuan, Juze Zhang +7

Stanford University

World Models for Robotics Robot Dynamics Learning World Action Models Robot Learning

Oct 5, 2026cs.RO

AIM: Adaptive Interaction Modeling Networks for Real-to-Sim Soft-Body Simulation

Deformable-object manipulation is essential for robotic tasks such as folding laundry and handling food, where robots must control shape changes as well as object motion. Predictive soft-body simulation supports these tasks by anticipating deformation under external interactions. However, spatial neighborhoods can misrepresent deformation dependencies, introducing local errors that accumulate over successive predictions. Models fitted to individual scenes must also accommodate changes in object geometry and manipulation conditions. In this work, we propose AIM, an Adaptive Interaction Modeling framework that treats real-to-sim soft-body simulation as a local-global interaction modeling problem. AIM uses motion history and geometry to adapt particle relations over current spatial neighbors and retained connections, while geometry-conditioned global communication coordinates object-wide responses. A unified kinematic control-point interface represents different manipulation configurations, and multi-step autoregressive supervision trains the model on its own predicted trajectories. Experiments on PhysTwin and PGND demonstrate improved motion accuracy and visual fidelity, with a 20.0% reduction in future-prediction tracking error relative to PhysTwin and a 22.8% reduction in mean long-horizon particle error across six object categories relative to PGND. The framework further supports transfer across actions, object instances, and scenes, including zero-shot transfer from robot interactions to human manipulation without target-domain dynamics fitting.

Tiancheng Yang, Dingshuo Chen, Tianle Chen +2

NLPR, MAIS, Institute of Automation, Chinese Academy of Sciences · School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences +1

Robotics Simulation Robot Dynamics Learning Deformable Object Simulation

Oct 4, 2026cs.RO

Optimal Control with Learned Critics under Unmodeled State Dependencies

Model Predictive Control (MPC) provides a structured and constraint-aware mechanism for decision-making, but its reliance on optimization-friendly analytical dynamics models limits its use in tasks with contacts and other hard-to-model state dependencies. Model-free reinforcement learning avoids explicit modeling assumptions but typically requires large amounts of interaction data. We present a learning-based MPC framework that combines the data efficiency and structure of local model-based planning with learned components that compensate for incomplete dynamics and finite-horizon myopia. The method augments a nominal analytical model with a residual dynamics network that learns missing state-dependent effects from data and combines the resulting planner with a learned action-value critic that injects long-horizon MDP structure into the local iLQR optimization. To make this practical at reinforcement-learning scale, we develop a GPU-accelerated batched iLQR solver that evaluates learned dynamics and critic networks inside the optimal-control loop and solves thousands of trajectory-optimization problems in parallel. The complete system is integrated into a robotics simulator, enabling scalable model-based reinforcement learning under incomplete dynamics. Experiments on biased and incompletely modeled control tasks show that the approach improves closed-loop control performance while preserving the model-based structure needed for efficient constrained trajectory optimization.

Philipp Schoch, Markus Ryll

Autonomous Aerial Systems Lab Technical University of Munich

Residual Dynamics Learning Robot Dynamics Learning Model Predictive Control Model-Based RL

Oct 1, 2026cs.RO

Learning a Resolution-Consistent Jacobian Field for Bio-Inspired Rigid-Soft Finger

Bio-inspired tendon-driven rigid-soft coupled dexterous fingers exhibit strong nonlinearity and configuration-dependent sensitivity, making accurate modeling challenging. In discrete-time control, Jacobian-based kinematic algorithms typically rely on point-wise local linear approximations, which makes their performance sensitive to sensor sampling frequency and controller update frequency. To address this issue, we propose Jacobian Flow Matching (JFM), a structured learning framework based on Conditional Flow Matching (CFM), to learn a resolution-consistent Jacobian field that models actuation-to-motion transitions as a dynamical flow. The proposed framework supports both single-step prediction and continuous rollout via ODE integration, enabling consistent inference across temporal resolutions. Experiments on a tendon-driven rigid-soft finger show that the proposed method suppresses outlier errors and improves single-step prediction accuracy, reducing the global average RMSE by over 53% compared with a baseline discrete Jacobian learning approach. For long-horizon prediction, trajectories recovered via ODE integration achieve higher fidelity under sparse sampling (Stride = 8), reducing the RMSE median by 14.43% and the error variance by 24.87%. These results demonstrate that the learned flow-based Jacobian field provides an effective local model for offline multi-step trajectory optimization in rigid-soft coupled nonlinear systems.

Tianyou Liang, Haisen Zeng, Shanjun Chen +3

College of Intelligence Science and Technology, National University of Defense Technology,, Changsha, 410073, China · National Key Laboratory of Equipment State Sensing and Smart Support, National University of Defense Technology,, Changsha, 410073, China

Robot Dynamics Learning Soft Robotics Robot Learning

Oct 1, 2026cs.RO

EIDA: Execution-Interface Dynamics Adaptation for Real-to-Sim-to-Real Robot Navigation

Simulation-to-robot transfer can fail when velocity commands produce motion and feedback that differ from those modeled during policy training. We present execution-interface dynamics adaptation (EIDA), which fits these responses from target-platform execution data without reconstructing actuator dynamics. A model of body-frame pose increments updates simulator geometry, while a separate model predicts the velocity feedback observed by the policy; a short history of velocity feedback is included in the policy input. The fitted models are used within a lightweight GPU-parallel simulator. On the full Jackal and Go2 validation sets, the fitted models reduced position and yaw prediction errors relative to the simulator's predefined motion model. Across 100 benchmark navigation environments evaluated in a separate physics-based simulator, EIDA achieved the highest success rate and navigation score among the compared learned policies, both with and without global guidance. Feedback ablations further supported the need to match policy-facing velocity estimates. On a physical Unitree Go2, EIDA reached the goal without collision in all 20 static-scene trials, compared with 4 of 20 for the baseline. These results show that execution-interface adaptation can improve navigation transfer without detailed actuator simulation.

Yiwei Qian, Shanze Wang, Qingyuan Hu +2

Eastern Institute of Technology, Ningbo, China · National University of Singapore, Singapore · Department of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University, Hong Kong +1

Robot Dynamics Identification Robotics Simulation Robot Navigation Sim-to-Real Transfer Robot Dynamics Learning

Sep 29, 2026cs.RO

WorldLine: Action-Driven Visual Simulation for Robotic Manipulation

Real-world robot learning is constrained by the cost of collecting experience and evaluating candidate behaviors. Video generation models offer a scalable foundation for visual simulators that predict action outcomes before physical execution. Yet they often favor visual plausibility over accurate action following and coherent robot--object dynamics, while action-conditioned simulators depend on scarce, embodiment-specific data that are difficult to share across incompatible control spaces. We introduce WorldLine, an action-driven visual simulator that decouples transferable dynamics learning from heterogeneous action grounding. WorldLine learns manipulation dynamics from more than 10,000 hours of action-free robot videos and grounds them using over 2,000 hours of action trajectories across more than ten embodiments. An image-space action representation provides a shared control interface across embodiments, while multi-view and failure-enriched training with relational regularization improves interaction-sensitive prediction. Robot-focused few-step distillation enables efficient causal rollout while preserving action-critical motion. Across held-out and out-of-domain settings, WorldLine maintains strong visual quality and robot-motion agreement; on failed trajectories, it improves robot-mask IoU by 0.1626 over the strongest baseline. It predicts trajectory success with 74% mean accuracy across RoboTwin and AgiBot, one percentage point above the strongest baseline. Without RoboTwin training or adaptation, its rollouts improve task success by up to 21.4 percentage points over direct policy execution. Together, these capabilities make WorldLine a scalable and efficient visual simulator for policy evaluation and embodied planning. More results are available at project page.

Shenghe Zheng, Wenbo Li, Jiyao Zhang +4

The Hong Kong University of Science and Technology · Joy Future Academy · Peking University +1

Action-Conditioned Video Generation World Models for Robotics Robotics Simulation Robot Dynamics Learning Robotic Policy Evaluation Cross-Embodiment Robot Learning

Sep 28, 2026cs.RO

Scouting the Dynamics Gap: Test-Time Policy Adaptation via Action-Outcome Feedback

While pretrained robotic policies exhibit impressive capabilities in controlled environments, unobserved physical properties and dynamics require these policies to rapidly adapt during deployment. Existing test-time adaptation methods typically rely on sparse scalar rewards, failing to exploit the rich geometric and dynamic feedback from the environment during physical interaction. To address this challenge, we propose SCOUT, a dynamics-aware meta-learning framework that enables manipulation policies to rapidly adapt by continuously revising their internal beliefs about environment dynamics. Our approach couples an action-prediction policy with a forward dynamics model via a shared belief latent space. During meta-training, an inner loop updates this shared belief latent by minimizing the dynamics prediction error against the observed action outcome, while the outer loop optimizes the network for action selection. At deployment, this structure allows the agent to infer and adapt to unknown physical dynamics on the fly. By updating its latent belief based on action-outcome mismatches, the policy automatically adapts without risking catastrophic forgetting. We demonstrate that SCOUT significantly accelerates online adaptation across simulated manipulation benchmarks and achieves robust sim-to-real transfer in the real world. Project webiste can be found here: https://liy1shu.github.io/SCOUT/

Yishu Li, Liyuan Geng, Xinyi Mao +2

Robotics Institute, Carnegie Mellon University · Computer Science and Technology, Tsinghua University

Robot Policy Learning Test-Time Adaptation Robot Policy Adaptation Robot Dynamics Learning Robotic Manipulation Robot Learning

Sep 28, 2026cs.RO

EMPIRIC: Experiment-Driven Learning of Residual World Models for Robot Planning

A robot should be able to learn through experiments how unfamiliar objects behave and interact, then plan with that knowledge. It need not start from scratch: physics engines supply knowledge of motion and contact, but can omit entire mechanisms, such as glue curing, water heating, or wind. We present EMPIRIC, an agent that learns a residual world model: a physics engine extended with code for the missing mechanisms. The learned programs can introduce new forces, constraints, and hidden state, and Bayesian inference estimates their parameters and states from noisy observations. The resulting model lets the agent predict the outcomes of actions, choose informative experiments, and revise its hypotheses when predictions fail. Across five simulated domains, EMPIRIC learns interpretable, reusable models, and solves more tasks with fewer environment interactions than all three baselines. On a physical robot, it learns wind forces and domino masses to solve a manipulation task. Website and code: https://yichao-liang.github.io/empiric

Yichao Liang, Amber Li, Dat Nguyen +13

Basis Research Institute · University of Cambridge · Carnegie Mellon University +6

World Models for Robotics Residual Dynamics Learning World Models World Model-Based Planning Robot Dynamics Learning Data-Efficient Robot Learning+1

Sep 28, 2026cs.RO

From World Models to World Action Models: Rethinking Next-State Prediction

Predicting the next state is a core paradigm of World Models for modeling physical dynamics, emphasizing prediction fidelity. As World Models evolve into World-Action Models (WAMs), existing methods still fix the next state before training as RGB, a single latent feature, or a static combination of predefined targets, thereby constraining action learning to the inductive biases preserved by a particular representation. To address this limitation, we propose CF-WAM, a dynamic next-state prediction framework that samples visual, semantic, geometric, and interaction projections of the same future, standardizes them into a common video form, and supervises a unified WAM across these projections. The action-relevant constraints exposed by these projections accumulate across training steps, forcing WAM to capture the underlying state-transition structure that supports multiple projections of the same action-conditioned future. This dynamic mechanism also provides a natural cross-embodiment dynamics reference frame for Human and Robot learning. By jointly learning across different next-state parameterizations, heterogeneous Human and Robot experience can bypass appearance differences and directly contribute to shared state-transition learning, improving cross-embodiment generalization. Experiments show that CF-WAM improves both training efficiency and final control performance, while translating Human experience effectively into policy gains. CF-WAM achieves state-of-the-art performance on RoboCasa-GR1 with an average success rate of 82.50%, while reaching 82.65% on LIBERO-Plus and up to 84.00% in real-world evaluations.

Tingyu Yuan, Ziming Ji, Biaoliang Guan +9

CASIA · UCAS · BUPT +4

Robot Dynamics Learning Action-Conditioned World Models Cross-Embodiment Robot Learning World Action Models

Sep 27, 2026cs.RO

AquaWAM: A Dynamics-aware World Action Model for Underwater Embodied Agents

World Action Models (WAMs) are becoming increasingly important and useful for embodied intelligence, as they enable robots to anticipate the consequences of candidate actions before interacting with the physical environment. However, underwater robots are usually subject to passive dynamics, such as inertia, buoyancy, hydrodynamic drag, and persistent drift, which can continue to affect the vehicle even after an action is completed. Existing WAMs, which primarily predict action-conditioned visual observations, are not explicitly designed to capture such passive motion dynamics. In this paper, we present AquaWAM, the first World Action Model designed for underwater embodied agents. Instead of predicting future images, AquaWAM models both action-conditioned and passive physical dynamics, including the thruster dead band, the inertial glide that outlasts each command, and ambient currents. Specifically, it senses through the DVL, IMU, pressure sensor and joint encoders, while cameras supply only semantics for understanding goals and target pose. By modeling compact navigation states rather than high-dimensional visual observations, AquaWAM substantially reduces the model size and computational cost compared with conventional WAMs. Experimentally, AquaWAM achieves a 72.6% task success rate across 20 underwater tasks on the USIM benchmark, outperforming existing methods while making action decisions 2.7x faster than U0 on an NVIDIA Jetson AGX Orin. Our model also remains effective when some onboard sensor measurements are unavailable. For example, without DVL velocity measurements, our method still achieves a 61.6% success rate, compared with 39.4% for U0.

Cunhao Zhu, Yifeng Wang, Dongliang Xu +3

Shandong University (sdu.edu.cn) · Beijing Institute of Technology (bit.edu.cn)

Robot Dynamics Learning Action-Conditioned World Models Underwater Robotics World Action Models Autonomous Underwater Navigation

Sep 22, 2026cs.RO

Manipulation of Deformable Linear Objects Using Model Predictive Path Integral Control with Bidirectional Long Short-Term Memory Learning

The manipulation of Deformable Linear Objects (DLOs) such as cables poses a significant challenge for automation due to their infinite degrees of freedom and non-linear dynamics. In this paper we present a machine learning based optimal control approach for the manipulation of DLOs. This approach is divided into two main components: modeling and control. For modeling the dynamics of the DLO, we propose a learning based approach using a bidirectional Long Short-Term Memory (biLSTM) network. The biLSTM network is trained on synthetic data generated by the MuJoCo physics engine. For manipulating the DLO, a model predictive control strategy that employs Model Predictive Path Integral (MPPI) control is selected. The proposed approach is evaluated through simulation and experiments. The results demonstrate the effectiveness of the proposed method in achieving accurate and efficient manipulation of DLOs.

Lukas Zeh, Johannes Meiwaldt, Zexu Zhou +2

Institute for Control Engineering of Machine Tools and Manufacturing Units, University of Stuttgart, Stuttgart, Germany

Deformable Object Manipulation Robot Dynamics Learning Robotic Manipulation

Sep 22, 2026cs.RO

History-Conditioned Flow Matching for Probabilistic Dynamics of Tendon-Driven Continuum Robots

Deterministic dynamics modeling of tendon-driven continuum robots remains challenging owing to uncertainties in material behavior, tendon transmission, friction, and contact. Measured joint configurations and nominal tendon commands do not fully characterize these internal mechanical factors, leaving uncertainty in the subsequent motion. We therefore develop a history-conditioned, physics-informed flow-matching framework for probabilistic dynamics prediction, using motion and actuation histories to predict the distribution of the next complete joint configuration. By recursively sampling next-step configurations under prescribed commands, the model predicts distributions of future whole-body motions. In simulation, scenario-specific models achieve five-second trajectory Energy Scores (lower is better) of 12.05 mm under internal friction variation and 9.29 mm under unobserved actuation disturbances. Relative to the conditional variational autoencoder and diffusion baselines, Flow attains lower Energy Scores and coverage closer to the nominal level in both scenarios. Ablations support history and structural conditioning in both scenarios. On the physical robot, predictions under two tendon-command profiles excluded from training capture the principal motion sequences, with five-second Energy Scores of 11.91 and 11.42 mm, lower than the compared baselines. The predicted-to-measured spread ratios are 1.65 and 1.22 (closer to 1 is better). These results support history-conditioned probabilistic dynamics prediction under incomplete mechanical observations.

Hang Yang, Tingcong Liu, Junjie Xiong +2

Flow Matching Robot Dynamics Learning Tendon-Driven Actuation Soft Robotics

Sep 16, 2026cs.RO

ForwardDLO: Model-Based Bimanual Shape Matching of Unconstrained Deformable Linear Objects

Ropes, cables, and other deformable linear objects appear in tasks from untangling to cable routing and suturing, yet controlling their shape remains a challenge in robot manipulation. We study model-based shape control in a general setting: the object lies unfixated on a support surface and two arms may grasp and move it anywhere along its length. Because each arm chooses a grasp point, direction, and magnitude, the joint action space is combinatorially large, and the dynamics model's per-prediction cost bounds how much of it a planner can search. We present ForwardDLO, a recurrent latent dynamics model for this unfixated bimanual setting that predicts per-segment displacements grounded in the observed rope state at every step. Our model reaches accuracy comparable to more expensive baselines while containing no explicit segment-to-segment operations, which makes batched evaluation of candidate actions cheap. On open-loop prediction of real rope motion it reaches the lowest error of the learned models we evaluate, 13% below the strongest baseline. Within a fixed time budget it scores 8 to 22 times more candidate actions than models of comparable accuracy while matching them in real-world shape matching; and on a simulated routing task at a 30Hz control rate, this throughput converts into 98% task success versus at most 30% for the baselines at their own budgets. We release the model, code, and a dataset of 2.42 million simulated and 14,107 real rope transitions at https://anonymous.4open.science/r/ForwardDLO/

Tim Missal, Berk Guler, Lucas Domingues +3

Technical University of Darmstadt · Honda Research Institute Europe GmbH · School of Electrical and Computer Engineering, Universidade Estadual de Campinas (UNICAMP), Brazil +4

Bimanual Robotic Manipulation Deformable Object Manipulation Robot Dynamics Learning Dynamic Robotic Manipulation Robot Learning Deformable Object Simulation

Jul 13, 2026cs.RO

SKooP: Symmetric Koopman Predictions for Faster and More Generalizable Legged Robot Locomotion with Reinforcement Learning

Reinforcement learning (RL) algorithms classically suffer from poor sample efficiency. In robotics, a recent line of work has emerged addressing this problem by encoding physics priors in the learning process. However, most of these approaches are validated on well-defined, low-dimensional benchmark systems rather than high-dimensional robots with complex nonlinear dynamics. In this paper, we introduce \textit{SKooP (Symmetric Koopman Predictions)}, an approach combining the advantages of morphological symmetries with those of a Koopman model learned via autoencoder to enhance policy learning. SKooP learns a Koopman model of the system dynamics alongside the policy. The resulting Koopman predictions are used as privileged observations for the critic, allowing the agent to learn based on smoother, more informative features. We also incorporate group symmetries into the actor, critic, encoder and decoder networks to produce a highly equivariant policy. The SKooP approach is validated via in-depth analysis of the learned Koopman models and symmetric policies to showcase how each of these influences the agent's performance. We also show that the learned policies are transferable to different simulation environments. Our results show that SKooP consistently reduces convergence time and increases the learned reward for multiple challenging bipedal locomotion tasks on a quadruped robot. Project page: https://evelyd.github.io/SymmetricKoopmanPredictions

Evelyn D'Elia, Weishu Zhan, Giulio Turrisi +5

Machine Learning and Optimisation, University of Manchester, M13 9PL Manchester, U.K. · Dynamic Legged Systems Lab, IIT, 16163 Genoa, Italy · Generative Bionics S.R.L, 16163 Genoa, Italy +3

Reinforcement Learning Koopman Operator Learning Robot Dynamics Learning RL for Legged Locomotion Robot Policy Generalization

Jun 30, 2026cs.RO

3D Point World Models: Point Completion Enables More Accurate Dynamics Learning

Learning predictive models of the world enables robotic control through planning, potentially allowing robots to improvise solutions on new tasks. However, large video-based dynamics models lack explicit 3D spatial structure and suffer from geometrically inconsistent long-term rollouts with compounding errors. Emerging 3D dynamics models based on partial point clouds improve geometric consistency but remain sensitive to occlusions and accumulated prediction drift. To address these challenges, we present 3D Point World Models (3DPWM) - a task-agnostic world model that operates entirely in 3D space by first completing partial point clouds and then learning action-conditioned dynamics in this completed 3D scene. By operating on completed geometry, 3DPWM enables reliable long-horizon rollouts and more accurate cost evaluation for model-based planning while supporting adaptation to new tasks. Experiments across different robotic embodiments and tabletop manipulation benchmarks demonstrate that 3DPWM achieves significantly more reliable long-horizon rollouts (100-300+ steps), supports both open-loop and closed-loop planning, and enables successful sim-to-real transfer.

Skand Peri, Hung Nguyen, Chanho Kim +2

Oregon State University

World Model Learning World Models for Robotics World Model-Based Planning Robot Dynamics Learning Action-Conditioned World Models Robotic Manipulation+1

Jun 25, 2026cs.RO

Continual Robot Policy Learning via Variational Neural Dynamics

Robots deployed in the real world rarely operate under a single fixed dynamics model: wind changes, payloads vary, batteries drain, contacts shift, and hardware wears. Yet most learning-based controllers are trained once and deployed as if learning were complete. This prevents the robot from using deployment experience to further improve task performance. In this work, we propose a continual learning framework that uses real-world experience to improve robot policies under hidden and recurring dynamics. Our method learns a condition-aware dynamics model from real state-action trajectories by combining an analytical physics prior with a neural residual for unmodeled effects. A recurrent encoder infers the current hidden condition from recent interaction, and this estimate conditions both the residual model and the policy. Policy learning is performed via differentiable simulation using diverse learned dynamics sampled from the latent model. At deployment, these sampled conditions are replaced by conditions inferred online from recent real interaction, allowing the policy to recover recurring dynamics by recognition rather than residual re-fitting. Through extensive simulation studies and real-world experiments, we demonstrate that the framework improves policy performance under diverse unobserved disturbances. On real quadrotor trajectory tracking under changing wind, the policy recovers from recurring disturbances in roughly 1s, about 5x faster than online residual re-fitting. It also reduces large-disturbance hover and tracking errors by 65.7% and 53.3% over the state-of-the-art online adaptation approaches

Jiaxu Xing, Zhiyuan Zhu, Yunfan Ren +4

Robotics and Perception Group, University of Zurich

Robot Policy Learning Robot Policy Adaptation Continual Robot Learning Residual Dynamics Learning Robot Dynamics Learning Robust RL+3

Jun 15, 2026cs.RO

Unified Motion-Action Modeling for Heterogeneous Robot Learning

We present Unified Motion-Action (UMA) Model, an approach that uses 3D object motion trajectories as a shared interface to bridge visuomotor control and dynamics modeling. UMA treats object motion and robot actions as co-evolving variables under a masked generative objective, in which the mask pattern determines both the supervision regime during pretraining and the inference mode at deployment. Using hindsight-relabeled motion contexts and a contrastive objective that disentangles task intent from scene geometry, UMA enables multi-task pretraining across heterogeneous data sources without requiring manually annotated task instructions. At deployment, the same pretrained parameters support motion-conditioned visuomotor control, motion-based dynamics modeling, and task adaptation from few-shot demonstrations. Pretrained on a mixture of robot demonstrations, human videos, and simulated data, UMA consistently outperforms state-of-the-art baselines specialized for each inference mode.

Yunhao Cao, Shitong Liu, Chao Feng +4

Cornell University

Robotic Control Robot Dynamics Learning Visuomotor Policy Learning Cross-Embodiment Robot Learning Conditional Generative Modeling Robot Learning

Jun 13, 2026cs.RO

Learning Context-Aware Neural ODE Dynamics for Adaptive Robotic Control

Robotic systems deployed in uncertain and dynamically changing environments often face variations in contact conditions, aerodynamic effects, and external disturbances that challenge reliable control. To remain effective under model-based control, these systems require dynamics models that can adapt to such changes, especially when direct access to complete environmental information is limited. To enable adaptability and facilitate integration with model predictive control, we propose a context-aware dynamics model based on neural ordinary differential equations, which infers environmental factors from state-action histories using a two-phase training procedure. 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. The results demonstrate that our method effectively adapts to temporally and spatially varying environmental changes across different tasks. Videos are available at https://youtu.be/PY0sNyF2rqE , and the source code is available at https://github.com/syyu410-yu/context-aware-neural-ode-control.git .

Shao-Yi Yu, Jen-Wei Wang, Maya Horii +2

Department of Mechanical Engineering, University of California, Berkeley, CA, USA · Aalto University and YaiYai Ltd, Finland

Robot Dynamics Identification Robot Dynamics Learning Robotics Neural ODEs Adaptive Control

Jun 8, 2026cs.RO

Physics-Aware Sparse Learning and Selective Online Adaptation for Euler-Lagrange Robot Dynamics

Accurate dynamics models are essential for model-based robotic control, yet nominal Euler--Lagrange models often become inaccurate in the presence of payload variation, unmodeled coupling, friction, aerodynamic effects, and changing operating conditions. Most learning-based correction methods improve prediction accuracy by introducing a single additive residual, but do not preserve the internal mechanical structure of Euler--Lagrange systems. This leads to models that do not preserve symmetry, positive-definiteness, or the coupling between inertia and velocity-dependent terms, which can result in physically inconsistent predictions and reduced reliability when embedded in model-based controllers. We propose a structure-preserving residual learning framework that decomposes model mismatch into an inertia correction, the corresponding induced Coriolis term, and a generalized-force residual. The mechanical component is learned under physical constraints, while the disturbance-sensitive component is represented through a sparse history-dependent latent interaction model and adapted online using Bayesian linear regression. This separation preserves key mechanical structure while restricting adaptation to the part of the dynamics most affected by changing conditions. Experiments across multiple robotic platforms, including mobile, aerial, and manipulator systems, show that the proposed method improves dynamics prediction and trajectory tracking under coupled and time-varying dynamics. These results highlight the value of combining structured residual modeling, compact latent interaction selection, and selective online adaptation for real-world model-based control.

Rishabh Dev Yadav, Samaksh Ujjawal, Sihao Sun +2

Department of Computer Science, The University of Manchaster, U.K. · Department of Cognitive Robotics, Delft University of Technology, Netherlands · International Institute of Information Technology Hyderabad. +1

Robotic Control Robot Dynamics Identification Online System Identification Residual Learning Residual Dynamics Learning Robot Dynamics Learning+2

Jun 1, 2026cs.RO

Dynamics Are Learned, Not Told: Semi-Supervised Discovery of Latent Dynamics Geometries For Zero-Shot Policy Adaptation

Real-world dynamics shifts pose a critical challenge for reinforcement learning in robotics, as policies tightly coupled to nominal environments often fail catastrophically when physical conditions change. Most existing methods rely on encoding explicitly identified physical parameters into a latent context, a parameter-centric paradigm that depends on pre-specified axes of variation and becomes brittle under unmodeled or compound dynamics changes. We revisit dynamics adaptation from an outcome-centric perspective: rather than telling policies what the dynamics are, we enable them to learn how dynamics affect interaction outcomes. Theoretically, this is grounded in a monotonic relationship between target-domain regret and the Lipschitz constant of a trajectory dynamics encoder. Practically, this constant can be upper-bounded through contrastive learning, yielding a smooth, task-relevant latent topology without privileged dynamics information. On MuJoCo benchmarks, our method consistently outperforms parameter-centric baselines under severe dynamics shifts, including unmodeled and time-varying parameters, while also improving in-distribution stability and latent interpretability. Overall, these results validate that controlling latent geometry is a principled mechanism for robust adaptation.

Zhiming Xu, Weitao Zhou, Xianghui Pan +4

School of Computer Science and Engineering, Tongji University, Shanghai, China · School of Vehicle and Mobility, Tsinghua University, Beijing, China · Simple AI, Beijing, China +1

Robot Policy Adaptation Latent Dynamics Modeling Robot Dynamics Learning Robotic RL Robust RL

May 29, 2026cs.RO

Batched Differentiable Rigid Body Dynamics in PyTorch for GPU-Accelerated Robot Learning

As robot control shifts toward large-scale reinforcement learning with in-loop dynamics computation, the community's reliance on CPU-bound libraries such as Pinocchio creates a throughput bottleneck in GPU-based training pipelines. We present BARD (Batched Articulated Rigid-body Dynamics), a self-contained PyTorch implementation of Featherstone's rigid-body dynamics algorithms, optimized for batched GPU evaluation and automatic differentiation. Three design choices make this efficient: a tiered lazy-evaluation cache that avoids redundant tree traversals, matmul-free joint transforms via pre-computed Rodrigues constants, and level-parallel propagation that reduces sequential operations to tree-depth batched steps. On five robot models (7-23 DOFs), BARD matches Pinocchio numerically while reaching up to 64x higher throughput for Forward Kinematics and 63x for Jacobians at batch size 4096 on an NVIDIA H200. We validate differentiability through gradient-based system identification on a 7-DOF manipulator, recovering link masses to 1.24% mean error under 5% torque noise, and integrate BARD into an Isaac Lab AMP training pipeline for an 11-DOF spined quadruped with 4096 parallel environments, where it is 8.5x faster than Pinocchio and 2.0x faster than ADAM for in-loop dynamics. BARD is open-sourced at: https://github.com/YueWang996/bard-pytorch-dynamics.

Yue Wang, Yanran Xu, Wenbo Wu +2

University of Southampton, Southampton, SO17 1BJ, UK

Multibody Dynamics Robot Dynamics Learning Differentiable Programming Differentiable Physics Robot Learning

May 2, 2026cs.RO

Dynamics Aware Quadrupedal Locomotion via Intrinsic Dynamics Head

Quadrupedal locomotion plays a critical role in enabling agile, versatile movement across complex terrains. Understanding and estimating the underlying physical dynamics are essential for achieving efficient and stable quadrupedal locomotion. We propose a novel training framework for quadrupedal locomotion that enables the Control Policy to understand and reason about physical dynamics. In simulation, we concurrently train an Intrinsic Dynamics (ID) Head that learns state-to-torque dynamics alongside the Control Policy, and we define a dynamics reward enabled by the ID Head that encourages the Policy toward more predictable dynamical behavior. We also provide a mechanism to tune the learned dynamics in the resulting Policy by controlling the training coefficients of the ID Head. Our simulation experiments show that this mechanism drives convergence to better optima across a wide range of standard quadrupedal locomotion rewards, yielding more efficient and smoother policies. Our real-robot experiments demonstrate sim-to-real transfer of these improvements, with significant gains in torque efficiency (16.8%), action rate (18.6%), and mechanical power (12.8%), while improving safe torque occupancy by 6.4%.

Aman Arora, Nalini Ratha

Department of Computer Science, University at Buffalo, The State University of New York, Buffalo, USA

Robot Dynamics Learning RL for Legged Locomotion Inverse Dynamics Quadruped Locomotion Robot Learning

Apr 28, 2026cs.RO

Learning-Based Dynamics Modeling and Robust Control for Tendon-Driven Continuum Robots

Tendon-Driven Continuum Robots (TDCRs) pose significant modeling and control challenges due to complex nonlinearities, such as frictional hysteresis and transmission compliance. This paper proposes a differentiable learning framework that integrates high-fidelity dynamics modeling with robust neural control. We develop a GRU-based dynamics model featuring bidirectional multi-channel connectivity and residual prediction to effectively suppress compounding errors during long-horizon auto-regressive prediction. By treating this model as a gradient bridge, an end-to-end neural control policy is optimized through backpropagation, allowing it to implicitly internalize compensation for intricate nonlinearities. Experimental validation on a physical three-section TDCR demonstrates that our framework achieves accurate tracking and superior robustness against unseen payloads, outperforming Jacobian-based methods by eliminating self-excited oscillations. For implementation details and source code, please refer to https://github.com/ZiqingZou/ContinuumControl.

Ziqing Zou, Ke Qiu, Fei Wang +3

Department of Control Science and Engineering, Zhejiang University, Hangzhou, China

Robot Trajectory Tracking Robot Dynamics Learning Recurrent Neural Networks Robust Control Continuum Robot Control Tendon-Driven Actuation+1

Apr 21, 2026cs.RO

Efficient Reinforcement Learning using Linear Koopman Dynamics for Nonlinear Robotic Systems

This paper presents a model-based reinforcement learning (RL) framework for optimal closed-loop control of nonlinear robotic systems. The proposed approach learns linear lifted dynamics through Koopman operator theory and integrates the resulting model into an actor-critic architecture for policy optimization, where the policy represents a parameterized closed-loop controller. To reduce computational cost and mitigate model rollout errors, policy gradients are estimated using one-step predictions of the learned dynamics rather than multi-step propagation. This leads to an online mini-batch policy gradient framework that enables policy improvement from streamed interaction data. The proposed framework is evaluated on several simulated nonlinear control benchmarks and two real-world hardware platforms, including a Kinova Gen3 robotic arm and a Unitree Go1 quadruped. Experimental results demonstrate improved sample efficiency over model-free RL baselines, superior control performance relative to model-based RL baselines, and control performance comparable to classical model-based methods that rely on exact system dynamics.

Wenjian Hao, Yuxuan Fang, Zehui Lu +1

School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN 47907, USA · independent researcher

Robotic Control Reinforcement Learning Koopman Operator Learning Robot Dynamics Learning Actor-Critic Methods Optimal Control+1

Oct 4, 2025cs.RO

Model-Based Adaptive Precision Control for Tabletop Planar Pushing Under Uncertain Dynamics

Data-driven planar pushing methods have recently gained attention as they reduce manual engineering effort and improve generalization compared to analytical approaches. However, most prior work targets narrow capabilities (e.g., side switching, precision, or single-task training), limiting broader applicability. We present a model-based framework for non-prehensile tabletop pushing that uses a single learned model to address multiple tasks without retraining. Our approach employs a recurrent GRU-based architecture with additional non-linear layers to capture object-environment dynamics while ensuring stability. A tailored state-action representation enables the model to generalize across uncertain dynamics, variable push lengths, and diverse tasks. For control, we integrate the learned dynamics with a sampling-based Model Predictive Path Integral (MPPI) controller, which generates adaptive, task-oriented actions. This framework supports side switching, variable-length pushes, and objectives such as precise positioning, trajectory following, and obstacle avoidance. Training is performed in simulation with domain randomization to support sim-to-real transfer. We first evaluate the architecture through ablation studies, showing improved prediction accuracy and stable rollouts. We then validate the full system in simulation and real-world experiments using a Franka Panda robot with markerless tracking. Results demonstrate high success rates in precise positioning under strict thresholds and strong performance in trajectory tracking and obstacle avoidance. Moreover, multiple tasks are solved simply by changing the controller's objective function, without retraining. While our current focus is on a single object type, we extend the framework by training on wider push lengths and designing a balanced controller that reduces the number of steps for longer-horizon goals.

Aydin Ahmadi, Baris Akgun

Computer Engineering Department, Ko¸c University, Rumelifeneri Yolu, Istanbul, 34450, Istanbul, Turkey.

Contact-Rich Manipulation Non-Prehensile Manipulation Robot Dynamics Learning Robotic Manipulation Robot Learning

Sep 15, 2025cs.RO

Learning Contact Dynamics through Touching: Action-conditional Graph Neural Networks for Robotic Peg Insertion

We present a learnable physics-based model that predicts motion of the robot end effector and reaction force-torque in contact-rich manipulation. The model represents the end effector and the environment as interacting meshes in a graph structure, and conditions its prediction explicitly on the applied control input. It predicts object-level pose update directly, while the reaction torque emerges from a per-vertex force field. Training is self-supervised using only joint encoder and force-torque data while the robot is randomly touching the environment without task context. In simulation, our model transfers to peg insertion with unseen concave geometry, where an MPC agent using it reaches up to 98% success rate, and after fine-tuning on self-collected data matches an agent planning with the ground truth dynamics at the tightest 1 mm clearance. In the real world, it outperforms the system-identified MuJoCo model by 45% in position and by 74% and 63% in force and torque error.

Zongyao Yi, Joachim Hertzberg, Martin Atzmueller

German Research Center for Artificial Intelligence, DFKI Niedersachsen, Osnabrück, Germany · Osnabrück University, Institute of Computer Science, Osnabrück, Germany

Graph Neural Networks Contact-Rich Robotic Manipulation Robot Dynamics Learning Robotic Insertion Robot Learning