WasserMan: Benchmark for Underwater Manipulation Policy Learning

Danil Belov; Artem Erkhov; Sergei Parsegov; Pavel Osinenko

cs.ROOct 3, 2026

WasserMan: Benchmark for Underwater Manipulation Policy Learning

Authors: Danil Belov, Artem Erkhov, Sergei Parsegov, Pavel Osinenko

Organizations: Central University, Moscow, Russia · Center for Engineering Systems and Sciences, Moscow, Russia · Sirius University of Science and Technology, Sirius Federal Territory, Russia · V. A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences, Moscow, Russia

Abstract

Underwater manipulation couples visual decisions, contact forces and a thruster-controlled floating base. We introduce WasserMan, to our knowledge the first multi-task simulation benchmark for visuomotor learning of floating-base underwater contact manipulation. It provides ten expert-solvable tasks, two vehicle-arm platforms, a bimanual configuration and underwater dynamics. Nine tasks have learned-policy evaluations. We compare ACT, diffusion policies (DP) and behavioral cloning on six tasks, with three training runs and equal sampled-window budgets. Pretrained SmolVLA adds evaluations on three tasks. In the tested settings, removing integral action can prevent completion, while changing action interfaces can reduce learned-policy success despite successful expert replay. Currents produce task-dependent changes in completion and actuation effort. Versioned tasks, demonstrations and per-episode evidence support a protocol separating expert feasibility, learned completion and execution effort.

Figures & tables

Fig. 2: System diagram. Wrist RGB and proprioception feed a policy (shown schematically). Inverse kinematics converts EE targets to joint commands. Native base/joint targets bypass this step. Vehicle feedback control and joint servos drive separate force and torque paths. Allocation and motor response bound thruster forces. Hydrodynamic loads act on the coupled simulation, and simulated contact provides physical measurements for evaluation.

Fig. 3: Six tasks in the learning protocol. The external view (large), base camera (upper right) and gripper camera (lower right) show the same expert state. These CAD-profile views illustrate the tasks. Policy learning uses procedural geometry, wrist RGB and proprioception.

Task	Interface	$d_{u}$	$f_{\pi}$ (Hz)	$H$
PressButton	Actuator	10	30	470
RotateValve	EE pose/jaw	8	30	2240
OpenHatch	Actuator	8	20	1790
CollectShell	Actuator	8	30	7190
PushSlider	Actuator	8	30	1790
PullLever	Actuator	8	30	1790

TABLE I: Decoded command size

d_{u}

, policy target rate

f_{\pi}

, and horizon

H

in 30 Hz control steps. All families predict 16 targets and execute 8.

Fig. 4: Visual water presets on CabinRecovery (top) and CargoRelease (bottom). Within each row, the camera and physical expert state are identical. The presets combine refraction, attenuation, backscatter and suspended particles. These are optical replays, not learned-policy robustness scores.

Task	ACT	DP	BC	SmolVLA
PressButton	45.6 $\pm$ 5.1	60.0 $\pm$ 12.0	40.0 $\pm$ 5.8	54.4 $\pm$ 5.1
RotateValve	84.4 $\pm$ 24.1	84.4 $\pm$ 6.9	74.4 $\pm$ 5.1	—
OpenHatch	81.1 $\pm$ 16.8	100.0 $\pm$ 0.0	16.7 $\pm$ 17.6	—
CollectShell	0.0 $\pm$ 0.0	33.3 $\pm$ 12.0	0.0 $\pm$ 0.0	—
PushSlider	10.0 $\pm$ 12.0	42.2 $\pm$ 10.2	2.2 $\pm$ 1.9	8.9 $\pm$ 6.9
PullLever	40.0 $\pm$ 38.4	51.1 $\pm$ 6.9	24.4 $\pm$ 15.0	7.8 $\pm$ 5.1

TABLE II: Success (%), mean

\pm

sample SD over three training runs and 30 resets each. ACT, DP and BC cover six tasks. Pretrained SmolVLA covers three of these tasks. Each run uses 320,000 demonstration windows.

Fig. 5: Each point is a separately trained checkpoint evaluated on 30 resets. Within a family, points from left to right are seeds 17, 43 and 101. Horizontal marks show training-run means. Families use the same reset states but independent training draws. SmolVLA is shown for its three-task extension.

$k_{I}$	Base coefficients	OpenHatch	RotateValve
1	Nominal	30/30/30	25/30/28
0.5	Nominal	17/15/25	21/27/25
0	Nominal	0/0/0	9/9/9
1	Published damping	30/30/30	24/27/27
1	Published added mass	30/30/30	25/28/28
1	Published both	30/30/30	25/28/26

TABLE III: Success counts per 30 research resets, ordered by training seeds 17/43/101.

k_{I}

multiplies the original integral gain. Published conditions replace only the stated base coefficients. All unlisted settings are unchanged.

Fig. 6: Nominal-model integral intervention. Left: each line is one frozen DP checkpoint’s full-horizon success on 30 research resets. Other panels: change from

k_{I}=1

in opposing-grasp occupancy and world-identity attitude RMS over the predeclared 20-s window, fully observed in every pair. Colored markers show mean changes for each training run. Black diamonds and bars show aggregate changes and descriptive 95% intervals from the paired crossed bootstrap. Contact changes have opposite signs across tasks. Interval conventions follow Section IV.

Fig. 7: Complete interface comparison. Each point is one independently trained DP model on 30 research resets. Within each interface, points from left to right are training seeds 17/43/101. Horizontal marks show means. Descriptive crossed intervals use independent training draws between interfaces and paired reset draws. Interface effects differ by task.

Fig. 8: Frozen-policy current intervention. Lines identify training seeds. upper panels report full-horizon completion and lower panels 20 s motor-force RMS. Each task/checkpoint uses the same 30 resets across currents. The three OpenHatch success curves coincide at 100%. Completion and actuator effort respond differently across tasks.

Explore similar work

ULOHA: An Underwater Bimanual Robot System for Robot Learning
Sep 16, 2026Masato Kobayashi, Takeru TsunooriBimanual Robotic Manipulation Visuomotor Policy Learning
The University of Osaka · Kobe University
AquaCap: A Training-Free Underwater Embodied Agent with Code-as-Policy
Sep 19, 2026Xiaoshi Li, Yule Xu, Chunghiu Kong +5Underwater Robotics Autonomous Underwater Navigation
Sun Yat-sen University · Dalian University of Technology · Southern Marine Science and Engineering Guangdong Laboratory
UMI-Underwater: Learning Underwater Manipulation without Underwater Teleoperation
Mar 27, 2026Hao Li, Long Yin Chung, Jack Goler +5Robotic Grasping Robotic Manipulation
All authors are with Stanford University.

Sep 16, 2026J/K move · Enter open · S save

ULOHA: An Underwater Bimanual Robot System for Robot Learning

Masato Kobayashi, Takeru Tsunoori

The University of Osaka · Kobe University

Bimanual Robotic Manipulation Visuomotor Policy Learning Underwater Robotics Robot Imitation Learning

Open paper AskPDF arXiv

Underwater visuomotor policy learning has focused primarily on single manipulators, while bimanual imitation learning has been studied largely in air. We present ULOHA, an underwater bimanual robot learning platform that combines custom-designed leader--follower hardware with software extensions to LeRobot, integrating teleoperation, multi-view sensing, demonstration collection, policy training, and autonomous deployment. Real-robot experiments demonstrate a range of coordinated underwater bimanual behaviors, including inter-arm transfer, shared-object manipulation, and buoyancy-driven interception. We evaluate ACT, Diffusion Policy, and the vision--language--action model SmolVLA on the platform. We investigate how learning methods and execution strategies developed for manipulation in air perform underwater, examining bubble disturbances, buoyancy-driven object motion, action-execution horizons, and real-time chunking. A separate single-arm study examines policy transfer between air and water and shows that demonstrations spanning both media support execution in both under the tested conditions. ULOHA provides a unified experimental platform for studying underwater bimanual robot learning under the coupled perceptual and physical effects of underwater environments. Additional material: https://mertcookimg.github.io/uloha/

Abstract

Explore similar work

ULOHA: An Underwater Bimanual Robot System for Robot Learning

AquaCap: A Training-Free Underwater Embodied Agent with Code-as-Policy

UMI-Underwater: Learning Underwater Manipulation without Underwater Teleoperation