Adapting Neural Robot Dynamics on the Fly for Predictive Control

Abdullah Altawaitan; Nikolay Atanasov

cs.ROApr 5, 2026

Adapting Neural Robot Dynamics on the Fly for Predictive Control

Authors: Abdullah Altawaitan, Nikolay Atanasov

Organizations: Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA 92093, USA · Kuwait University

Abstract

Accurate dynamics models are critical for the design of predictive controllers for autonomous mobile robots. Physics-based models are often too simple to capture relevant real-world effects, while data-driven models are data-intensive and slow to train. We introduce an approach for fast adaptation of neural robot dynamic models that combines offline training with efficient online updates. Our approach learns an incremental neural dynamics model offline and performs low-rank second-order parameter adaptation online, enabling rapid updates without full retraining. We demonstrate the approach on a real quadrotor robot, achieving robust predictive tracking control in novel operational conditions.

Figures & tables

Figure 1: Quadrotor robot adapting to a payload equal to $35\%$ of its weight on the fly while tracking a reference trajectory.

Figure 2: Overview of our approach for on-the-fly neural dynamics learning and predictive control.

Figure 3: Range of values and their densities in the collected dataset of quadrotor positions, orientations, linear velocities, and angular velocities. The top row corresponds to the training set, and the bottom row to the validation set.

Panel of Figure 4 — Figure 4: Quadrotor tracking lemniscate and circular reference trajectories with an added $350\,\mathrm{g}$ payload ( $35\%$ increase). (a–b) lemniscate without/with adaptation, (c–d) circle without/with adaptation. In (e-f), the transparent quadrotors denote the starting states while the bold ones denote the end states.

Control		Adaptation
$\mathbf{Q}_{\mathbf{p}}$	$\mathrm{diag}(200,\,200,\,200)$	$\mathbf{Q}_{\mathbf{p}}$	$\mathrm{diag}(10,\,10,\,10)$
$\mathbf{Q}_{\mathbf{q}}$	$\mathrm{diag}(1.25,\,1.25,\,50)$	$\mathbf{Q}_{\mathbf{q}}$	$\mathrm{diag}(5,\,5,\,2)$
$\mathbf{Q}_{\mathbf{v}}$	$\mathrm{diag}(1,\,1,\,1)$	$\mathbf{Q}_{\mathbf{v}}$	$\mathrm{diag}(1,\,1,\,1)$
$\mathbf{Q}_{\bm{\omega}}$	$\mathrm{diag}(1,\,1,\,1)$	$\mathbf{Q}_{\bm{\omega}}$	$\mathrm{diag}(0.1,\,0.1,\,0.1)$
$\mathbf{Q}_{\mathbf{u}}$	$2\times\mathbf{I}_{4}$	$\mathbf{Q}_{\bm{\eta}}$	$0.1\times\mathbf{I}_{p}$
$T$	$50$	$T$	$50$

Table I : Cost Weights

Trajectory	Method	Position [ $\mathrm{m}$ ]	Heading [ $\mathrm{rad}$ ]	Overall
Lemniscate	No Adaptation	$0.136$	$0.059$	$0.196$
Lemniscate	With Adaptation	${\bf 0.107}$	${\bf 0.058}$	${\bf 0.166}$
Circle	No Adaptation	$0.134$	$0.063$	$0.198$
Circle	With Adaptation	${\bf 0.099}$	${\bf 0.060}$	${\bf 0.159}$

Table II : Tracking performance reported in RMSE.

Robot Dynamics Learning

Robot dynamics learning builds models that predict how robots and objects move under actions, enabling control, planning, and adaptation.

See all 83 papers

Learning Context-Aware Neural ODE Dynamics for Adaptive Robotic Control
Jun 13, 2026Shao-Yi Yu, Jen-Wei Wang, Maya Horii +2Robot Dynamics Identification Robot Dynamics Learning
Department of Mechanical Engineering, University of California, Berkeley, CA, USA · Aalto University and YaiYai Ltd, Finland
Physics-Aware Sparse Learning and Selective Online Adaptation for Euler-Lagrange Robot Dynamics
Jun 8, 2026Rishabh Dev Yadav, Samaksh Ujjawal, Sihao Sun +2Robotic Control Robot Dynamics Identification
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
Continual Robot Policy Learning via Variational Neural Dynamics
Jun 25, 2026Jiaxu Xing, Zhiyuan Zhu, Yunfan Ren +4Robot Policy Learning Robot Policy Adaptation
Robotics and Perception Group, University of Zurich

Jun 13, 2026J/K move · Enter open · S save

Learning Context-Aware Neural ODE Dynamics for Adaptive Robotic Control

Shao-Yi Yu, Jen-Wei Wang, Maya Horii, Masayoshi Tomizuka+1

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

Open paper AskPDF arXiv

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 .

Abstract

Robot Dynamics Learning

Explore similar work

Learning Context-Aware Neural ODE Dynamics for Adaptive Robotic Control

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

Continual Robot Policy Learning via Variational Neural Dynamics