Autonomous robots are widely used for environmental monitoring, collecting measurements of quantities of interest such as temperature, water quality, and terrain characteristics. In spatiotemporal environments, these quantities evolve over time, causing information decay. Informative planning must therefore account for both information acquisition and decay when optimizing robot trajectories. A separate challenge is uncertainty about external disturbances, which can affect robot motion and the locations where measurements are collected. Consequently, trajectories optimized using nominal dynamics may acquire less information than predicted during execution.
Selecting disturbance measurements to improve subsequent monitoring requires considering how reducing disturbance uncertainty affects future planning decisions. This is closely related to dual control, which balances immediate performance and learning, and task-optimal exploration, which prioritizes learning according to its effect on task performance. However, directly evaluating this benefit is computationally challenging, as it requires considering possible measurement outcomes, their effects on the disturbance belief, and the resulting changes in subsequent informative trajectories.
Two-Stage Approach
We develop a two-stage online approach to the problem. The first stage collects disturbance measurements in regions relevant to the monitoring task. Once the uncertainty in these regions is sufficiently reduced, the second stage uses the learned disturbance belief to optimize informative trajectories. Measurements of both the quantities of interest and the disturbance continue throughout both stages.

Disturbance Estimation
Geometric paths and their monitoring relevance scores are used to determine where disturbance measurements should be prioritized.
Conclusion
We presented a two-stage framework combining monitoring-informed disturbance learning with disturbance-aware trajectory optimization. In the four reported runs, monitoring-informed sampling reduces dedicated learning time by an unspecified lower-to-upper percentage range relative to global estimation and improves monitoring when disturbances restrict access to sensing locations. The largely calm scenario also exposes the cost of unnecessary learning.
Simulation and Comparison Protocol
Simulations use double-integrator nominal dynamics with wind entering through a relative-air-velocity force model. Wind varies spatially but remains fixed in time. Methods share each scenario’s geometry, initial state and clarity, and MBD budget. The planning horizon is an unspecified duration, with an unspecified number of execution intervals. Wind estimation begins without measurements, and POAM is updated online from observations collected during execution.
Dedicated learning terminates when the path-weighted disturbance uncertainty falls below an unspecified threshold. B4 instead evaluates disturbance uncertainty throughout the free workspace. This posterior uncertainty criterion is model-dependent and does not bound the true wind-estimation error.
Comparison Methods
B1 assumes zero wind in planning and executes MBD trajectories without safety filtering.

Frequently Asked Questions
What problem does the framework address? It addresses informative robot planning when environmental quantities change over time and external disturbances can affect motion and measurement locations.
How does the two-stage approach work? It first collects disturbance measurements in task-relevant regions, then uses the learned disturbance belief to optimize informative trajectories.
Where does the approach prioritize disturbance measurements? It uses geometric paths and monitoring relevance scores to identify where disturbance measurements should be prioritized.
What limitation applies to the disturbance uncertainty criterion? The posterior uncertainty criterion is model-dependent and does not bound the true wind-estimation error.
