WorksComputer Science
Disturbance-Aware Informative Planning in Spatiotemporal Environments
Abstract
Autonomous robots are widely used for persistent monitoring of spatiotemporal environments, where quantities of interest (QoI) change across space and time and require repeated measurements. In practice, robot motion can be affected by external disturbances that vary across the environment. When such external disturbances are not considered in trajectory optimization, it can lead to inaccurate predictions of robot motion and, consequently, the information acquired about the QoI during execution. However, estimating disturbances throughout the environment can be inefficient, as disturbances in regions with little overlap with monitoring trajectories have limited impact on monitoring performance. We therefore propose a two-stage informative planning framework for unknown, spatially varying but time-invariant disturbances, combining informed disturbance sampling with disturbance-aware trajectory optimization. First, we identify where QoI measurements are needed and generate alternative paths to these locations using the environment geometry. We then prioritize disturbance measurements based on their expected reduction of disturbance uncertainty along these paths. Second, rather than optimizing information acquisition based on nominal robot motion, we incorporate the learned disturbance belief into trajectory optimization to account for its effects on robot motion and information acquisition. Across four simulation scenarios, the proposed method reduces disturbance-learning time by 25.0–52.3 percent compared with environment-wide estimation and identifies paths that appear costly under nominal dynamics but become preferable when disturbances are considered.
Introduction
Autonomous robots are widely used for environmental monitoring, collecting measurements of quantities of interest such as temperature, water quality, and terrain characteristics [6, 3, 18]. In spatiotemporal environments, these quantities of interest 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.
Addressing these challenges requires accounting for uncertainty about the quantities of interest being monitored and uncertainty about the external disturbances affecting robot motion. Informative planning methods quantify uncertainty in the quantities of interest using measures such as posterior variance, entropy, mutual information, and clarity [9, 19, 1]. These measures guide the selection of sensing locations and trajectories through sampling-based planning under travel budgets [19, 7] or optimization of expected information gain [6, 18, 12]. In spatiotemporal environments, informative planning must account for evolving quantities of interest. Existing approaches use spatiotemporal Gaussian processes [3], update sparse spatial GP models online [11], or explicitly model information acquisition and decay in ergodic exploration and trajectory optimization [14, 15]. However, they do not jointly address disturbance learning and its effects on robot motion during informative planning.
Beyond uncertainty in the quantities of interest, other approaches account for the effects of disturbances on robot motion. Popovic et al. [17] consider localization and mapping uncertainty in informative planning, while Cho et al. [5] incorporate known wind through direction-dependent travel costs. For unknown disturbances, Sun et al. [20] use Gaussian processes to learn state-dependent disturbances for safe exploration. Other approaches combine online wind estimation with wind-aware routing [13] or use learned wind maps in quadrotor planning and control to reduce attitude effort [21]. While these methods address disturbance estimation or its effects on robot motion, they do not jointly consider monitoring-driven disturbance learning and the incorporation of learned disturbance beliefs into informative trajectory optimization.
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 [2, 10], and task-optimal exploration, which prioritizes learning according to its effect on task performance [23, 22]. 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.
To address these challenges, we propose a two-stage disturbance-aware informative planning framework. (i) The first stage predicts where QoI measurements are needed as information decays and generates alternative paths to these locations using environment geometry. We then prioritize disturbance measurements by their expected reduction of disturbance uncertainty along these paths, weighted by monitoring relevance and accounting for travel cost. (ii) The second stage incorporates the learned disturbance belief into Model-Based Diffusion (MBD) trajectory optimization, so that the trajectory cost reflects information acquisition and decay along predicted robot motion under disturbances rather than nominal motion. We compare against nominal planning, disturbance-aware monitoring without dedicated learning, and environment-wide disturbance estimation, evaluating monitoring performance over both stages.
Preliminaries
Notation
Let and ; , , and denote the real, nonnegative, and positive real numbers. For , , , and denote the identity matrix and the sets of symmetric positive-semidefinite and positive-definite matrices in , respectively. We write for a Gaussian distribution with mean and covariance , for the trace, for , and for the indicator of .
Dynamics Model
Consider the continuous-time robot dynamics
where and denote the robot state and control input. The robot’s position is given by , where is the workspace and . The unknown disturbance field is , with , and is the known dynamics model. The field can vary with position, but its value at any fixed does not change with time. Let denote the prescribed set of admissible states, including obstacle avoidance.
Definition 1 (Trajectory). Let , where . A trajectory starting from is a pair of functions satisfying , , with .
Quantity of Interest Model and Clarity
Let be the number of free-space monitoring cells and their index set. Cell has center and a scalar quantity of interest . The cell quantities have independent Gaussian initial beliefs. Their process and observation models are
where and are process- and measurement-noise intensities. The scalar processes are mutually independent standard Wiener processes, and is the integrated observation. The function specifies the measurement sensitivity to cell and is zero when that cell is not observed. Different values of allow the quantities at different cells to evolve with different process uncertainty.
Estimating each with a continuous-time Kalman filter gives posterior mean and variance , with . Clarity [1] is a normalized representation of differential entropy; for this scalar Gaussian belief, . Substitution of the variance equation yields
The first term represents information acquisition and the second represents information decay. Let be the target clarity in cell . With , the cellwise deficits and mean-deficit function are
Thus, measures the difference between target and current clarity.
Disturbance Belief
To estimate the unknown disturbance field , the robot collects noisy measurements along its trajectory. Let denote the time of the -th disturbance measurement, where indexes successive measurements. At position , the measurement is given by
where is the measurement noise with covariance . The measurement noises are independent across and independent of the noises in (2). The dataset contains all disturbance measurements collected up to time .
To represent uncertainty about the unknown field , we consider a random field . Let denote its posterior belief conditioned on , and let be the space of such disturbance beliefs. For any , the posterior mean and cross-covariance are
The marginal covariance is . Although the physical disturbance field is time-invariant, its posterior belief is updated as new measurements are collected.
Probabilistic Online Attentive Mapping (POAM) for Estimating Disturbance
We estimate the unknown disturbance field using Probabilistic Online Attentive Mapping (POAM) [4], an online sparse Gaussian-process (GP) method. Its attentive kernel combines base kernels of different lengthscales using location-dependent weights, allowing spatially varying correlations. We approximate by independent sparse GP posteriors for the disturbance components and assume diagonal observation-noise covariance .
For component , , we use a zero-mean GP prior with kernel , whose parameters are updated as new measurements become available. Let and denote the number and locations of inducing points. The corresponding inducing values have variational posterior , where and . Define the nonsingular kernel matrix and , where contains the kernel values between the inducing points and . For any , the predictive mean and covariance are
The vector mean consists of the component means , while the cross-covariance has diagonal entries and zero cross-component entries. POAM updates inducing locations using pivoted Cholesky decomposition (PCD), incorporates new measurements through analytic variational updates, and adapts kernel hyperparameters through mini-batch optimization. For further details, see Chen et al. [4].
Model-Based Diffusion
Model-Based Diffusion (MBD) [16] is a zeroth-order, sampling-based optimization method that iteratively refines candidate solutions through score-based reverse diffusion using samples, without requiring objective gradients.
Let , with , denote the decision vector and its cost. MBD defines on and outside , with temperature . For diffusion steps, indexed by , define and . At each step, denotes a noisy version of the decision vector , generated by the forward diffusion process:
During reverse diffusion, proposals are sampled and weighted by their costs:
For a positive denominator, estimates the clean decision conditioned on . Let be the marginal density of for . Its score is approximated by in the reverse update:
Repeating this update for progressively refines the candidates toward lower-cost solutions. Further details are provided by Pan et al. [16].
Problem Statement
Consider a robot governed by (1) monitoring (2), with initial state , clarity , and disturbance belief at . A feedback policy selects without access to the true field or future measurements. We seek to minimize the expected long-run mean clarity deficit subject to state and input constraints:
Here is the averaging duration, not a terminal mission time. The expectation includes the initial disturbance uncertainty and observation noise; constraints are required almost surely for all . The belief is updated from observations (5).
Directly solving (11) is computationally intractable, as it requires optimizing robot trajectories while accounting for future disturbance measurements and belief updates over an infinite horizon. We therefore consider the following problem and propose a safety-aware approximate solution to it.
Problem 1 (Disturbance-aware informative planning). Given the robot and monitoring models, environment geometry, and local disturbance measurements (5), develop an online method to approximate the constrained monitoring problem (11) by (i) learning the unknown disturbance field in regions relevant to the monitoring task and (ii) incorporating the learned disturbance belief into informative trajectory optimization while accounting for state and input constraints.
Methodology
Overview
We develop the two-stage online approach to Problem 1 illustrated in Figure 1. 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.
Figure 1. Overview of monitoring-informed disturbance estimation and disturbance-aware informative planning.
Let , , denote successive planning times, with and . We define , , and as the current robot state, clarity vector, and disturbance belief, respectively. The clarity targets are . Trajectories are planned over a horizon and executed in a receding-horizon manner. The planning index continues across both stages.
Geometric Path Initialization
We first generate geometric paths toward informative sensing locations using the current clarity map and known obstacle geometry. These paths identify regions where disturbance estimation can benefit the monitoring task and provide distinct initial trajectories for subsequent optimization.
Since the quantities of interest evolve over time, selecting sensing locations based only on the current clarity may overlook regions with significant future clarity deficits. We therefore predict clarity over , assuming no additional measurements are collected. Setting in (3), the predicted clarity of cell at time , for , and its corresponding deficit are
We evaluate these deficits at selected times , , forming . This accounts for how clarity deficits develop throughout the prediction horizon.
Using these predictions and known obstacle geometry, we generate a fixed number of alternative collision-free paths. Let denote the collision-free workspace and the generated paths, where indexes individual paths. Each path starts at and reaches a candidate sensing location, with denoting normalized arc length. Alternative paths through different passages are retained to provide geometrically distinct routes.
To prioritize paths according to their monitoring relevance, we evaluate the predicted clarity deficits of cells observable along each path. Let be a sensing configuration at , satisfying . The score of the -th path is defined as
The integral can be approximated numerically by evaluating the integrand at discrete points along each path. A larger score indicates that the path passes through locations from which cells with greater predicted clarity deficits can be observed. These scores form and are subsequently used to prioritize disturbance estimation along the geometric paths. The generated paths are also used to initialize the subsequent MBD trajectory optimization.
Disturbance Estimation
We use the geometric paths and their monitoring relevance scores from § 4.2 to determine where disturbance measurements should be prioritized.
Monitoring-informed spatial weighting. Disturbances along geometric paths can affect the robot’s motion and its ability to collect measurements of the quantities of interest. We therefore construct spatial weights that assign greater importance to regions near paths with higher monitoring relevance. Let be a prescribed spatial weighting function that assigns greater weight to locations near the geometric path , where and is a tunable parameter. For each cell , define an unnormalized weight and, when their sum is positive, its normalized value by
where is the normalization factor. For , the weights sum to one.
Disturbance measurement selection. Using the spatial weights, we quantify the disturbance uncertainty in regions relevant to the monitoring task as
We aim to select measurements that reduce this uncertainty. Since the disturbance belief captures spatial correlations, a measurement at one location can reduce uncertainty at other locations. For a candidate measurement location , let denote the expected reduction in from a disturbance measurement at . Using Gaussian conditioning, this reduction is given by
This one-measurement reduction is evaluated with the current spatial weights, GP kernel parameters, and inducing representation held fixed; subsequent POAM retraining is not predicted. To account for travel cost, we consider a finite set of candidate measurement locations . Let give the collision-free travel distance from to each candidate, and let control the travel-distance penalty. When candidates remain after route checks, we select
We exclude candidate routes that intersect obstacles.
Stopping criterion for disturbance estimation. At each planning iteration, is updated using the current clarity and disturbance belief. Dedicated disturbance estimation terminates when , where is a prescribed uncertainty tolerance. Throughout this stage, clarity continues to evolve, and the monitoring cost incurred during disturbance estimation is included in the evaluation.
Disturbance-Aware Model-Based Diffusion
In the second stage, we incorporate the learned disturbance belief into Model-Based Diffusion (MBD) to optimize informative trajectories. At each planning time , geometric paths from § 4.2 initialize candidate trajectories, which are refined through MBD. Each candidate is evaluated by predicting the robot’s motion under sampled disturbance fields and the resulting information acquisition, allowing the optimizer to account for disturbance effects directly.
Disturbance-aware trajectory prediction. Let parameterize candidate state and input curves over . To evaluate each candidate, we draw spatial disturbance fields from , indexed by . Each sampled field remains fixed throughout its rollout, preserving spatial correlations.
Let denote the set of candidate trajectories. For each sample, the tracking controller computes a nominal control input to follow using the current predicted state and disturbance belief. This input is modified by an approximate safety filter , based on the approach described in the following paragraph. The resulting predicted state and input satisfy
with . The clarity vector is propagated using (3), initialized at . Thus, disturbances and filter interventions affect the predicted information acquisition.
Safety-aware filtering during planning. We now describe the approximate safety filter used in (18), based on the robust policy control barrier function (RPCBF) approach [8]. Let encode the admissible state set as , and let denote a prescribed design policy satisfying the input constraints. At each predicted state along a candidate trajectory, the RPCBF estimates the maximum future constraint violation by simulating under the sampled disturbance fields . The sampled finite-horizon value function is
where denotes the auxiliary state under and field , initialized at . The inner index ranges over all fields while the outer rollout index is fixed. The sample set is held fixed when estimating the gradient with respect to . Using and its estimated gradient, the filter modifies the nominal tracking input by minimizing its deviation subject to the RPCBF constraint and input bounds . For control-affine dynamics and polyhedral input bounds, imposing the sampled barrier conditions yields a quadratic program (QP) [8]. The filtered input is used to propagate the predicted robot motion in (18), with applied throughout each candidate rollout. The purpose of this filter is to account for how potential safety interventions affect the predicted motion and information acquisition, rather than to guarantee safety during planning.
Trajectory cost and optimization. Each candidate is evaluated using the accumulated clarity deficit along its predicted motion, with a soft penalty for state-constraint violations. Using the constraint function defined above and a penalty coefficient , the finite-horizon cost is
The cost accounts for disturbance effects and safety-filter interventions through the predicted state and clarity trajectories. The geometric paths from § 4.2 initialize separate MBD optimizations using (8)–(10), with . Each optimization refines its candidate, and the lowest-cost evaluated candidate with a finite cost is selected, with parameters .
Execution and belief updates. The robot executes an initial segment of the selected candidate using the tracking controller and runtime filter , which has the same argument and output spaces as , then replans from the updated state and clarity. Actual disturbance measurements continue updating through POAM during both stages.
Results and Discussion
We evaluate four environments with spatially varying, time-invariant wind, using double-integrator nominal dynamics and a relative-air-velocity force model. Methods share each scenario’s geometry, initial state and clarity, and MBD budget. The planning horizon is 15 s, with 5 s execution intervals and no initial wind measurements. Appendix § 8 provides simulation details.
Baselines and evaluation: We compare B1, zero-wind MBD without filtering; B2, zero-wind MBD with the learned wind belief used in tracking and runtime RPCBF; B3, disturbance-aware MBD with RPCBF during planning and execution, learning only from measurements collected while monitoring; and B4, global wind learning followed by disturbance-aware MBD. The proposed method targets learning along monitoring-relevant paths before using the same planner as B4.
Figure 2 compares monitoring histories, while Table 1 in Appendix § 8 reports the final mean clarity deficit and its time average , with and elapsed time measured from the start of each run. Contact terminates a run, and monitoring deficits are not extrapolated beyond that point.
Figure 2. Monitoring across four scenarios. Top: environments and proposed trajectories; bottom: mean clarity-deficit histories for all methods. Comparison durations are 532, 560, 544, and 514 s for Scenarios 1–4, respectively.
| Method | Scenario 1 | Scenario 2 | Scenario 3 | Scenario 4 |
| s | s | s | s | |
| B1 | Contact: 4.4 s | Contact: 15.6 s | Contact: 4.8 s | 0.181 (0.161) |
| B2 | 0.293 (0.366) | 0.301 (0.367) | 0.078 (0.081) | 0.180 (0.180) |
| B3 | 0.224 (0.280) | 0.221 (0.267) | 0.047 (0.035) | 0.186 (0.184) |
| B4 | Contact: 399.0 s | 0.190 (0.156) | 0.054 (0.040) | 0.221 (0.177) |
| Proposed | 0.166 (0.146) | 0.177 (0.171) | 0.042 (0.027) | 0.189 (0.189) |
Table 1. Monitoring performance: , with final deficit in parentheses. Bold indicates the lowest among completed runs; contact times are reported for terminated runs.
Route-dependent disturbances: In Scenario 1, wind opposes travel from region B to A through the central passage, while a sheltered lower bypass is available. B2 and B3 do not enter A within the comparison window, whereas the proposed method does, reducing from B3’s 0.224 to 0.166. B4 also reaches A but contacts an obstacle at 399.0 s. In Scenario 2, wind also opposes travel through the lower passage, making the upper bypass important. Again, B2 and B3 do not enter A. Targeted learning ends at 200 s versus B4’s 370 s and yields lower , although B4 has the lower final deficit. The improvement therefore concerns accumulated monitoring performance, not every instantaneous deficit.
Spatial allocation of learning: In Scenario 3, the proposed method learns disturbances along paths connecting the two monitoring regions rather than throughout the workspace. By focusing learning on monitoring-relevant paths, the proposed method reduces estimation time from 244 to 124 s and lowers from 0.0540 to 0.0418 (22.6%) relative to B4. In Scenario 4, the monitoring region is largely calm. Although the proposed method reduces learning time from 214 to 102 s relative to B4, B2 achieves a lower , showing that dedicated learning may be unnecessary when disturbances have little effect on monitoring.
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 25.0–52.3% 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.
Algorithmic Details
This appendix details Algorithm 1, which switches from disturbance estimation to persistent informative planning when the weighted disturbance uncertainty satisfies .
Planning state and geometric initialization
At planning time , the available quantities are , , the disturbance data , and their belief . The geometry, target clarity , horizon , uncertainty tolerance , and remaining design parameters are fixed inputs. The index counts planning iterations and is not reset between stages. The retained waypoint is , or when none is available. The symbol denotes the candidate selected for execution at , or when no candidate is available.
The operation GeoPaths predicts clarity deficits using (12) and constructs geometrically distinct paths , scored over their entire length by (13). Numerical quadrature approximates the path integrals. These paths guide disturbance learning and initialize separate MBD optimizations; neither their construction nor scoring requires the disturbance belief.
The operation PathWeights uses in (14) to distribute path scores to nearby cells and normalize the weights . It also returns their unnormalized sum . If , the algorithm sets and , preventing an undefined normalization or premature transition to monitoring.
Disturbance measurement selection
For positive total weight, the algorithm evaluates using (15). If , it leaves the first loop before selecting another disturbance-measurement waypoint. Otherwise, SelectWaypoint retains a usable current waypoint or applies (17) to the candidate set . A new waypoint is needed after arrival, rejection of the connecting route, or lack of progress. Candidates are excluded when their routes intersect obstacles or are predicted to require inputs outside . If or no usable candidate remains, the routine returns .
The acquisition value in (16) predicts the reduction in weighted disturbance variance from one measurement, holding spatial weights and GP parameters fixed; subsequent POAM updates are not predicted. The travel penalty in (17) accounts for distance, not the full downstream monitoring benefit. Measurements acquired during execution update the disturbance belief.
Given a waypoint, MeasurementPath constructs a candidate trajectory toward it using the known geometry and current disturbance belief. It returns if or no usable trajectory is available. A prescribed recovery policy is then used during execution. The specific recovery controller is an implementation choice, not an additional safety guarantee.
Disturbance-aware MBD optimization
After the transition, Initialize time-parameterizes the geometric paths to form a finite set of candidate parameter vectors. Available hold and shifted previous candidates may also be retained. Each initialization is refined independently using the MBD equations in § 2.6; candidate parameters from different chains are not averaged together.
The operation MBD evaluates each candidate using the sampled fields , the filtered dynamics (18), and the cost (20). A sampled field is held fixed along its complete rollout. At each predicted state, the tracking input is modified by , whose RPCBF value estimate is constructed under the design policy as in (19). These design-policy predictions are auxiliary calculations for the filter; the candidate itself is propagated using the filtered tracking input. Clarity is propagated along the resulting state trajectory, and the disturbance belief remains fixed within the planning call.
The cost is averaged over disturbance samples before computing the MBD proposal weights. Initial candidates, sampled proposals, and refined means are evaluated before selection. If all proposal weights vanish, no weighted update is defined and that chain retains its previously evaluated candidates. Among candidates with defined, finite evaluations, the routine selects the lowest-cost trajectory and returns its parameters ; if none is available, it returns . A finite set of predicted trajectories does not certify physical safety. No hypothetical measurement is added to during this optimization.
Execution and actual-data updates
The operation Execute follows an initial segment of the candidate using the tracking controller and runtime filter . If , the prescribed recovery controller supplies an input in . In the first stage the candidate leads toward a disturbance-measurement waypoint; in the second it is selected by MBD. The routine returns the next planning time , state , clarity , and new disturbance observations
The operation incorporates the accumulated observations into the POAM model, including its online variational and kernel updates. The dataset union in Algorithm 1 records this assimilation and does not imply that the model must be retrained from scratch. Measurements of the quantities of interest also remain active, so clarity evolves throughout both stages. The planning clock, clarity, and disturbance belief are carried across the transition without resetting. If the uncertainty threshold is never met, the first stage continues; the algorithm assumes no terminal mission time.
Algorithm 1: Persistent disturbance-aware informative planning. The estimation stage ends only when weighted posterior uncertainty meets its tolerance.
Input: ; models, geometry, , and design parameters
// Stage 1: Disturbance estimation
while true do
if then
if then break
// Stage 2: Disturbance-aware informative planning
while true do
if then
Environments, Baselines, and Detailed Results
Four scenarios assess disturbance-aware trajectory prediction, alternative-route discovery, and monitoring-informed disturbance learning. Wind affects robot motion while the QoI dynamics remain separate. Figure 3, Figure 2, and Figure 4 show the environments and trajectory comparisons. Simulations were performed on an Apple M3 MacBook Air with 16 GB of unified memory.
Figure 3. The four evaluation environments. Scenarios 1 and 2 test alternative passages under opposing wind; Scenario 3 has two monitoring regions within a larger workspace; Scenario 4 has a largely calm monitoring region. The lower-left and lower-right panels correspond to Scenarios 3 and 4 in the main text; their embedded labels are reversed.
Figure 4. Trajectories of the proposed method and baselines, with rows corresponding to Scenarios 1–4 in the main text. The embedded labels in the final two rows are reversed. Runs ending in contact are terminated, not completed comparisons; Table 1 reports the numerical results.
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 15 s, with 5 s 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 in (15) falls below m/s. 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.
Scenarios 1–4 are evaluated over 532, 560, 544, and 514 s, respectively, measured from mission start and including dedicated learning. QoI sensing remains active during learning. These evaluation windows do not impose a terminal time on the persistent planner. Runs end upon contact, and monitoring deficits are not extrapolated thereafter.
Comparison methods
B1: MBD without RPCBF. B1 assumes zero wind in planning and executes MBD trajectories without safety filtering.
B2: MBD with runtime RPCBF. B2 uses zero-wind planning, while tracking and runtime RPCBF use the learned wind belief. The planner therefore does not account for disturbance-induced motion or filter corrections when choosing trajectories.
B3: Disturbance-aware MBD without dedicated learning. B3 begins informative monitoring immediately, evaluating candidate trajectories using the learned wind belief and RPCBF during planning and execution. POAM learns from measurements collected during monitoring, without a dedicated disturbance-learning stage.
B4: Global learning followed by disturbance-aware MBD. B4 reduces wind uncertainty throughout the free workspace, including regions irrelevant to monitoring, before using the same disturbance-aware MBD planner as the proposed method.
Proposed: Monitoring-informed learning followed by disturbance-aware MBD. The proposed method prioritizes disturbance measurements near monitoring-relevant geometric paths, including transit passages, before using the same disturbance-aware MBD planner as B4. Learning allocation is handled in the first stage rather than by adding a disturbance-information reward to the monitoring cost.
Metrics and learning durations
For each simulation, define the mean clarity deficit and its time average as
The final deficit depends on the revisit cycle, whereas captures monitoring loss over the full comparison window. Table 1 reports both; bold denotes the lowest among completed runs, not a statistically significant difference.
Table 2 reports simulated disturbance-learning times and percentage reductions , where and are the respective durations. These are mission times, not computation times; QoI sensing remains active throughout learning.
| Scenario | B4 (s) | Proposed (s) | Reduction |
| 1 | 240 | 180 | 25.0% |
| 2 | 370 | 200 | 45.9% |
| 3 | 244 | 124 | 49.2% |
| 4 | 214 | 102 | 52.3% |
Table 2. Dedicated wind-estimation time.
Scenario 1: Central opposing wind and a lower bypass
Wind opposes travel from region B to A through the central passage, while a sheltered lower bypass remains available. B2 and B3 do not reach A within 532 s, although B3 achieves a lower mean deficit than B2. The proposed method reaches A and reduces to 0.166 versus 0.224 for B3. B4 also reaches A but contacts an obstacle at 399.0 s; it therefore has no full-window monitoring score.
Scenario 2: Opposing wind in the central and lower passages
Wind also opposes the lower passage, making the upper bypass important. B2 and B3 again fail to reach A within the 560 s comparison window. Both dedicated-learning methods reach A. Targeted learning takes 200 s versus 370 s for B4. The proposed method reduces from 0.190 to 0.177, although B4 has the lower final deficit (0.156 versus 0.171).
Scenario 3: Monitoring concentrated in two regions
Two monitoring regions are embedded in an obstacle-filled workspace with additional wind outside monitoring-relevant routes. B2 never reaches A, while B3 reaches it only at 351.55 s, illustrating the delay in discovering an alternative without dedicated disturbance learning. Compared with B4, targeted learning ends after 124 rather than 244 s, leaving more time for monitoring. The proposed method reduces from 0.0540 to 0.0418 (22.6%) and from 0.0396 to 0.0269 (about 32%). B4 reaches A earlier during learning (54.10 versus 74.65 s), so the proposed method’s improvement reflects a shorter learning stage rather than an earlier first arrival.
Scenario 4: Calm monitoring region and remote wind
The monitoring region is largely calm, with stronger wind elsewhere. Targeted learning takes 102 s versus B4’s 214 s and lowers from 0.221 to 0.189, although its final deficit is higher (0.189 versus 0.177). However, B2 attains the lowest (B1: 0.181; B3: 0.186). Dedicated learning may therefore be unnecessary when disturbances have little effect on monitoring, and the fixed switching threshold still incurs learning cost in this scenario.
Planning time and interpretation
In Scenario 3, median planning times after compilation are 1.64 s (proposed) and 1.60 s (B4), with 95th percentiles of 1.93 and 1.73 s, respectively. Both methods use the same MBD budget. Timings include posterior and field preparation, geometric initialization, optimization, and safety-belief refresh. The baselines distinguish execution-time compensation (B2), disturbance-aware monitoring without dedicated learning (B3), and spatial allocation of learning with a common monitoring planner (B4 versus proposed). These comparisons do not separately isolate geometric initialization, weighting, or the switching rule. Each scenario reports one run. The proposed method completes all four comparison windows without contact, but infeasible RPCBF steps occur, and B4 contacts an obstacle in Scenario 1 despite filtering. The results do not establish guaranteed collision avoidance or statistical robustness. The path weights approximate task relevance rather than the exact long-term value of disturbance information.
References
- [1]Devansh R. Agrawal and Dimitra Panagou. Sensor-based planning and control for robotic systems: Introducing clarity and perceivability. IEEE Control Systems Letters, 7:2623–2628, 2023. doi: 10.1109/LCSYS.2023.3288493. URL https://arxiv.org/abs/2304.02578.
- [2]Elena Arcari, Lukas Hewing, Max Schlichting, and Melanie Zeilinger. Dual stochastic MPC for systems with parametric and structural uncertainty. In Proceedings of the 2nd Conference on Learning for Dynamics and Control, volume 120 of Proceedings of Machine Learning Research, pages 894–903, 2020. URL https://proceedings.mlr.press/v120/arcari20a.html.
- [3]Jonathan Binney, Andreas Krause, and Gaurav S. Sukhatme. Optimizing waypoints for monitoring spatiotemporal phenomena. The International Journal of Robotics Research, 32(8):873–888, 2013. doi: 10.1177/0278364913488427.DOI
- [4]Weizhe Chen, Lantao Liu, and Roni Khardon. POAM: Probabilistic online attentive mapping for efficient robotic information gathering. In Robotics: Science and Systems, 2024. doi: 10.15607/RSS.2024.XX.019.DOI
- [5]Doo-Hyun Cho, Jung-Su Ha, Sujin Lee, Sunghyun Moon, and Han-Lim Choi. Informative path planning and mapping with multiple UAVs in wind fields. In Distributed Autonomous Robotic Systems, volume 6 of Springer Proceedings in Advanced Robotics, pages 269–283. Springer, 2018. doi: 10.1007/978-3-319-73008-0_19.DOI
- [6]Gregory Hitz, Enric Galceran, Marie-Ève Garneau, François Pomerleau, and Roland Siegwart. Adaptive continuous-space informative path planning for online environmental monitoring. Journal of Field Robotics, 34(8):1427–1449, 2017. doi: 10.1002/rob.21722.DOI
- [7]Geoffrey A. Hollinger and Gaurav S. Sukhatme. Sampling-based robotic information gathering algorithms. The International Journal of Robotics Research, 33(9):1271–1287, 2014. doi: 10.1177/0278364914533443.DOI
- [8]Luzia Knoedler, Oswin So, Ji Yin, Mitchell Black, Zachary Serlin, Panagiotis Tsiotras, Javier Alonso-Mora, and Chuchu Fan. Safety on the fly: Constructing robust safety filters via policy control barrier functions at runtime. IEEE Robotics and Automation Letters, 10(10):10058–10065, 2025. doi: 10.1109/LRA.2025.3597847.DOI
- [9]Andreas Krause, Ajit Singh, and Carlos Guestrin. Near-optimal sensor placements in gaussian processes: Theory, efficient algorithms and empirical studies. Journal of Machine Learning Research, 9:235–284, 2008. URL https://jmlr.org/papers/v9/krause08a.html.
- [10]Zhongguo Li, Wen-Hua Chen, Jun Yang, and Cunjia Liu. Cooperative active learning-based dual control for exploration and exploitation in autonomous search. IEEE Transactions on Neural Networks and Learning Systems, 36(2):2221–2233, 2025. doi: 10.1109/TNNLS.2024.3349467.DOI
- [11]Kai-Chieh Ma, Lantao Liu, and Gaurav S. Sukhatme. Informative planning and online learning with sparse Gaussian processes. In 2017 IEEE International Conference on Robotics and Automation (ICRA), pages 4292–4298, 2017. URL https://arxiv.org/abs/1609.07560.
- [12]Roman Marchant and Fabio Ramos. Bayesian optimisation for informative continuous path planning. In 2014 IEEE International Conference on Robotics and Automation (ICRA), 2014. doi: 10.1109/ICRA.2014.6907763.DOI
- [13]Brady Moon. Informative Path Planning Toward Autonomous Real-World Applications. Ph.d. thesis, Carnegie Mellon University, Pittsburgh, PA, 2025. URL https://publications.ri.cmu.edu/informative-path-planning-toward-autonomous-real-world-applications.DOI
- [16]Chaoyi Pan, Zeji Yi, Guanya Shi, and Guannan Qu. Model-based diffusion for trajectory optimization. In Advances in Neural Information Processing Systems, volume 37, 2024. URL https://arxiv.org/abs/2407.01573.
- [17]Marija Popović, Teresa Vidal-Calleja, Jen Jen Chung, Juan Nieto, and Roland Siegwart. Informative path planning for active field mapping under localization uncertainty. In 2020 IEEE International Conference on Robotics and Automation (ICRA), pages 10751–10757, 2020a. doi: 10.1109/ICRA40945.2020.9197034.DOI
- [18]Marija Popović, Teresa Vidal-Calleja, Gregory Hitz, Jen Jen Chung, Inkyu Sa, Roland Siegwart, and Juan Nieto. An informative path planning framework for UAV-based terrain monitoring. Autonomous Robots, 44:889–911, 2020b. doi: 10.1007/s10514-020-09903-2.DOI
- [19]Amarjeet Singh, Andreas Krause, Carlos Guestrin, William J. Kaiser, and Maxim A. Batalin. Efficient planning of informative paths for multiple robots. In Proceedings of the Twentieth International Joint Conference on Artificial Intelligence, pages 2204–2210, 2007. URL https://ijcai.org/proceedings/2007/355.
- [20]Dawei Sun, Mohammad Javad Khojasteh, Shubhanshu Shekhar, and Chuchu Fan. Uncertain-aware safe exploratory planning using gaussian process and neural control contraction metric. In Proceedings of the 3rd Conference on Learning for Dynamics and Control, volume 144 of Proceedings of Machine Learning Research, pages 728–741, 2021. URL https://proceedings.mlr.press/v144/sun21a.html.
- [21]Mitchell Torok, Man Ching Melvin Chan, Donglin Sui, and Mohammad Deghat. Online wind mapping for coupled path planning and contouring control of quadrotors. Sensors, 26(16):5250, 2026. doi: 10.3390/s26165250.DOI
- [22]Andrew Wagenmaker, Guanya Shi, and Kevin G. Jamieson. Optimal exploration for model-based RL in nonlinear systems. In Advances in Neural Information Processing Systems, volume 36, 2023. URL https://papers.nips.cc/paper_files/paper/2023/hash/31e018f43ab9c7065c058cc2c5848128-Abstract-Conference.html.arxiv.org/abs/2306.09210
- [23]Andrew J. Wagenmaker, Max Simchowitz, and Kevin Jamieson. Task-optimal exploration in linear dynamical systems. In Proceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learning Research, pages 10461–10652, 2021. URL https://proceedings.mlr.press/v139/wagenmaker21a.html.arxiv.org/abs/2102.05214



