Accurate and adaptive dynamic models are critical for underwater vehicle-manipulator systems where hydrodynamic effects induce time-varying parameters. This paper introduces a novel uncertainty-aware adaptive dynamics model framework that remains linear in lumped vehicle and manipulator parameters, and embeds convex physical consistency constraints during online estimation. Moving horizon estimation is used to stack horizon regressors, enforce realizable inertia, damping, friction, and hydrostatics, and quantify uncertainty from parameter evolution. Experiments on a BlueROV2 Heavy with a 4-DOF manipulator demonstrate rapid convergence and calibrated predictions. Manipulator fits achieve R2 = 0.88 to 0.98 with slopes near unity, while vehicle surge, heave, and roll are reproduced with good fidelity under stronger coupling and noise. Median solver time is approximately 0.023 s per update, confirming online feasibility. A comparison against a fixed parameter model shows consistent reductions in MAE and RMSE across degrees of freedom. Results indicate physically plausible parameters and confidence intervals with near 100% coverage, enabling reliable feedforward control and simulation in underwater environments.
Figures & tables
Fig. 1 : Adaptive dynamics in UVMS: prior knowledge of system parameters is updated using new experimental data, resulting in an updated belief consistent with observed dynamics.
Fig. 2 : Framework overview of the Uncertainty-Aware Adaptive Dynamics scheme for UVMS, combining regressor models, horizon stacking, moving horizon estimation, and physical consistency constraints to produce adaptive parameter estimates with uncertainty for control and planning.
Fig. 3 : Identified fit for excited and recorded vehicle (a) surge force, (b) heave force and (c) roll moment DOF .
Fig. 4 : Identified fit for excited and recorded torque profile of manipulator: (a) joint 0 and (b) joint 1.
Fig. 5 : Identified fit for excited and recorded torque profile of manipulator: (a) joint 2 and (b) joint 3.
Fig. 6 : UVMS experiment platform.
Fig. 7 : Online parameter adaptation results for manipulator and vehicle subsystems.
Fig. 8 : (a) Joint 0 parity analysis, excited torque versus model computed torque. (b) Eigenvalue trajectory of the pseudo inertia for joint 2, showing positive definiteness.
DOF / Joint
R2
slope
MSE
MAE
RMSE
surge (N)
0.58
0.62
16.081
2.939
4.010
sway (N)
0.46
1.08
20.072
3.378
4.480
heave (N)
0.68
1.02
42.658
3.397
6.531
roll (N m)
0.72
1.13
1.085
0.730
1.041
pitch (N m)
0.43
0.51
1.206
0.879
1.098
yaw (N m)
0.68
1.06
0.392
0.439
0.626
TABLE I : Average identification metrics for vehicle DOFs and manipulator joints, based on recorded excited profiles.
Fig. 9 : Solver time during online identification.
Fig. 10 : Comparison of excitation torque versus model torques computed with prior fixed parameters (blue plots) and with the adaptive converged parameters (red plots), for vehicle DOFs.
Accurate trajectory tracking is essential for autonomous underwater vehicles operating with uncertain hydrodynamics and limited thruster authority. This paper develops a low-complexity adaptive prescribed performance controller for uncertain underwater vehicle dynamics with coupled and saturated inputs. The proposed method adapts the performance functions directly through the mismatch between the requested and saturated control inputs, enlarging the performance funnels only when the available actuation cannot meet the nominal specifications. A coupled invariant-set analysis establishes boundedness of all closed-loop signals, prescribed bounds on the filtered tracking errors, and explicit feasibility conditions. Comparative simulations on a BlueROV2 underwater vehicle show that the adaptive design maintains prescribed performance during a figure-eight maneuver, whereas conventional prescribed performance control loses feasibility under input limits. A real-time pool experiment further demonstrates stable trajectory tracking and the practical implementation of the proposed method on an underwater robotic platform.
Athanasios K. Gkesoulis, Christos Vlachos, George K. Fourlas +2
The authors are with the Robotics Institute, Athena Research Center, Marousi, Greece · The authors are with the Division of Systems and Automatic Control, Department of Electrical and Computer Engineering, University of Patras, Patras, Greece · The authors are with the Department of Informatics and Telecommunications, School of Sciences, University of Thessaly, Lamia, Greece
Model-based control of an aquatic robotic platform depends on a hydrodynamic model that is costly to identify and specific to the hull, payload, and conditions it was measured in. Here, we present MOSAIC-SV, a deployable real-time adaptive dynamics identification and control system that identifies a control-sufficient dynamics model from a spec-sheet engineering prior, without dedicated identification trials, and re-estimates it at every control step of a closed-loop mission while the controller plans on it. A physically admissible unscented Kalman filter re-estimates hydrodynamic, disturbance, and actuator parameters at every control step of the closed-loop mission; while a command-dependent consider projection withholds corrections the current command cannot attribute between actuator effectiveness and external force; and a model predictive path integral controller plans on the current estimate. In simulation on a CyberShip II plant, MOSAIC-SV recovers the transit performance of the calibrated model under static mismatch and transient changes, and stays within 20% of its own transit time at the unscaled prior when its inertia or damping prior is wrong by an order of magnitude. In on-water field trials on the Blue Robotics BlueBoat, a twin-thruster catamaran, MOSAIC-SV transits at least 25% faster and predicts its own motion with at least 56% less error than its frozen engineering prior, including under an unmodeled payload. The same MOSAIC-SV system concept was also feasibly deployed on a 6.3-tonne dual outboard monohull.
Wensen Liu, Jerry Peng, Shravani Vedagiri +1
Mechanical Engineering Department, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Accurate models of underwater vehicle motion are needed for autonomous execution of marine tasks like infrastructure inspection and scientific sampling. However, such motion is challenging to characterize using traditional physics-based methods. This paper presents a novel data-driven framework for learning stochastic underwater vehicle dynamics. Using Euler-Poincaré dynamics and the geometry of Lie groups, we develop a stochastic physics-informed neural network architecture that respects the physical and geometric constraints of underwater vehicles. Our approach leverages structure-preserving stochastic integration and builds upon moment matching and finite dimensional matching to ensure geometrically-consistent training. We evaluate our approach in simulation and on an underwater vehicle navigating dock pylons in a harbor environment. The results demonstrate that our method learns accurate and robust dynamics models, enabling safe model-based control in challenging marine environments.
Evan F. Palmer, Ross L. Hatton, Geoffrey A. Hollinger
Collaborative Robotics and Intelligent Systems (CoRIS) Institute, Oregon State University, Corvallis OR 97331, USA