A Browser-Native Digital Test Range for Benchmarking 4D Ocean-Glider Planning Algorithms

Summary

Repeated in-situ evaluation of ocean-glider planners requires scarce vehicles, operators, deployment and recovery resources, and ocean conditions that cannot be reset for competing algorithms.

Abstract Summary

Repeated in-situ evaluation of ocean-glider planners requires scarce vehicles, operators, deployment and recovery resources, and ocean conditions that cannot be reset for competing algorithms. We present a guided, installation-free browser-native digital test range that transforms a selected region into a reproducible four-dimensional experiment. The system leads users from regional domain selection through mission-scoped bathymetry, time/depth forcing, science objectives, optional task decomposition, route specification, current-advected execution, observation generation, and scoring. Its primary contribution is a common plan-to-observation contract unifying vehicle, sensing, and evaluator assumptions across manual routes, transparent built-in algorithms, and imported classical or learned-planner outputs, while exported artifacts form dataset-ready records. A controlled Observing System Simulation Experiment (OSSE) evaluates five classical planners in two episodes, three deterministic seeds, and a calibrated 60-hour horizon. All 54 missions completed and recovered without hard violations, while planner rankings and dive-policy effects revealed operational-scientific tradeoffs. An authentic public deployment supplied a field-referenced audit to scope current kinematic boundaries. Separately, source-locked GliderFlight 1.2.0 achieved native-to-browser parity through Pyodide/WebAssembly, establishing a pathway for high-fidelity multi-tier simulation. The resulting operational space is scientifically traceable and component-qualified for mission-scale pre-deployment experimentation.

Key Points

Repeated in-situ evaluation of ocean-glider planners requires scarce vehicles, operators, deployment and recovery resources, and ocean conditions that cannot be reset for competing algorithms.
We present a guided, installation-free browser-native digital test range that transforms a selected region into a reproducible four-dimensional experiment.
The system leads users from regional domain selection through mission-scoped bathymetry, time/depth forcing, science objectives, optional task decomposition, route specification, current-advected execution, observation generation, and scoring.
Its primary contribution is a common plan-to-observation contract unifying vehicle, sensing, and evaluator assumptions across manual routes, transparent built-in algorithms, and imported classical or learned-planner outputs, while exported artifacts form dataset-ready records.
A controlled Observing System Simulation Experiment (OSSE) evaluates five classical planners in two episodes, three deterministic seeds, and a calibrated 60-hour horizon.

Guided Digital Test-Range Workflow

Figure 1 summarizes the information boundary. The interface guides a user through Bathymetry $\rightarrow$ Currents $\rightarrow$ Science $\rightarrow$ Segments $\rightarrow$ Routes $\rightarrow$ Mission $\rightarrow$ Simulate $\rightarrow$ Validate . Table I identifies the principal choices and persisted object at each stage. A geographic bounding box defines the broad analysis domain.

Mission Execution and Evaluation

The mission contract fixes deployment and recovery, clock, fleet, vehicle speed, dive policy, waypoint acceptance, dwell, clearance, observation schedule, and evaluation.

The active benchmark engine advances the vehicle using mission-scale current-advection kinematics, where $\mathbf{v}_{g}$ is ground-relative velocity, $\mathbf{v}_{w}$ is commanded through-water velocity, and $\mathbf{v}_{c}$ is current sampled at the executed state.

Mission Execution and Evaluation — A Browser-Native Digital Test Range for Benchmarking 4D Ocean-Glider Planning Algorithms — Fig. 3 : Planned guidance and executed 4D motion for the representative cross-shelf-front science-aware A* run (fixed dive, seed 1). The current-advected trajectory, dive/climb cycle, observations, deployment, and recovery correspond to checksum fnv1a32:2f0262b7 . Depth is exaggerated $20\times$ for display only.

Controlled Benchmark Design and Results

Two deterministic episodes represent a cross-shelf front (CSF) and a depth-shear eddy (DSE). Each contains georeferenced bathymetry, masks, three current times and depths, a hidden scalar reference, prior, uncertainty, and sampling value. The one-glider mission uses through-water speed $0.42\text{\,}\mathrm{m}\,\mathrm{s}^{-1}$, a 30-minute step, and 121 states over 60 hours.

Scientific Qualification and Reproducibility

The operational space is scientifically traceable and component-qualified for simulation. Here, component-qualified means that individual data, computation, information-boundary, and browser-execution contracts have supporting evidence; this confirms bounded execution within the idealized simulator.

Table IV separates verification, calibration, field-referenced auditing, reference-model portability, and benchmark inference.

Sources and Demonstrations

Figures are reproduced from Holmberg et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.