This paper addresses the finite-budget exposure-aware informative path planning (IPP) problem for a fleet of mobile sensing agents. The agents map an unknown scalar field while limiting exposure to high field intensity. Existing IPP methods optimize informativeness under motion or resource constraints, but do not address field exposure constraints. We formulate exposure-aware IPP (EA-IPP) as a scalarized bi-objective belief-state Markov decision process that trades the normalized Gaussian-process (GP) information gain against a normalized measurement-derived fleet exposure index. A parameter-shared proximal policy optimization (PPO) framework with decentralized actors and a centralized fleet critic is trained offline and evaluated on unseen fields. Across the radar, plume, and wildfire field families, the EA-IPP agent achieves the lowest GP reconstruction RMSE among the evaluated baselines while retaining D-optimal information within 10% of the non-learning information baseline. The minimum field exposure is approximately 34.6%, 20.1%, and 27% below the non-exposure-aware baseline for radar, plume, and wildfire, respectively.
Figures & tables
Fig. 2: From left to right: radar, plume, and wildfire-field realizations.
Category
Parameter
Value
Environment
Grid / navigable cells
40×40 / 1444
N / H
3 / 50
σn / ∣A∣
1 / 9
Global GP
μ0 (radar/fire/plume)
36.31/18.86/6.34
ℓ (radar/fire/plume)
4.1891/2.0738/2.1928
σf (radar/fire/plume)
13.335/19.806/9.6393
TABLE I: Experimental parameters.
Fig. 3: Effect of λ on D-optimal PPO across the three field families. Top: IepA , IepD , and Cep . Bottom: terminal RMSE, NLPD, and Cov95 .
Fig. 4: Mission-horizon comparison of PPO at λ=0.5 with non-learning baselines under D-optimal sensing. Columns show cumulative D-optimal information, normalized cumulative exposure, GP reconstruction RMSE, and NLPD for the radar, chemical-plume, and wildfire field families.
Field
Method
IepA
IepD
Cep
RMSE
NLPD
Radar
PPO ( λ=0 )
0.61
0.321
0.347
8.374
2.943
PPO ( λ=0.25 )
0.56
0.29
0.323
8.995
2.997
PPO ( λ=0.5 )
0.382
0.214
0.265
11.012
3.298
PPO ( λ=0.75 )
0.145
0.113
0.208
13.354
3.727
PPO ( λ=1 )
0.109
0.085
0.206
13.695
3.826
Greedy-D [ 4 ]
0.561
0.346
0.315
8.586
2.907
TABLE II: PPO at λ∈{0,0.25,0.5,0.75,1} compared with non-learning baselines under D-optimal sensing. Bold denotes the best value within each field.
Fig. 5: D-optimal information–exposure trade-off for PPO and the non-learning baselines across the three field families. PPO markers indicate λ∈{0,0.25,0.5,0.75,1} .
Fig. 6: PPO evaluation return during training under D-optimal sensing for λ∈{0,0.25,0.5,0.75,1} . Curves assess convergence within each configuration; return magnitudes are not compared across λ because the scalarized reward changes with λ .
Informative path planning chooses robot routes and sensing actions that gather useful information while respecting travel, energy, time, and safety constraints.
Accurate environmental monitoring relies on Informative Path Planning (IPP) to deploy autonomous systems that maximize information gain. While Gaussian Processes (GPs) provide a robust mathematical foundation for modeling the environment, contemporary IPP approaches remain hindered by heuristic operational constraints and the lack of simultaneous theoretical guarantees for worst-case estimation error and approximation quality. Rather than introducing yet another heuristic, this paper presents a rigorous theoretical analysis of existing error bounds and algorithms to further develop the mathematical foundation for IPP. By evaluating probabilistic and deterministic bounds on reconstruction error, we establish that predictive variance is the theoretically ideal optimization objective for GP-based IPP. Furthermore, we analyze GreedyCover, a recent approach for optimizing predictive variance, and demonstrate that its near-optimal approximation guarantee matches the fundamental hardness-of-approximation limit for the problem. Comprehensive benchmarking confirms that this approach delivers superior estimation accuracy and computational efficiency compared to prominent information-theoretic objectives and optimization methods used in IPP. Finally, this theoretical analysis establishes a rigorous, near-optimal foundation for discrete offline IPP under bounded uncertainty constraints, offering clear and principled guidance for future work in continuous-space and online formulations.
Kalvik Jakkala, Jennifer Wakulicz, Donald G. Dansereau +3
Department of Computer Science and Engineering, Texas A&M University, College Station, TX 77843 USA · Australian Centre for Robotics, School of Aerospace, Mechanical and Mechatronic Engineering, University of Sydney, NSW 2006, Australia · University of North Carolina at Charlotte, Charlotte, NC 28223 USA +1
Informative Path Planning for scalar field reconstruction uses predictive uncertainty to direct sensing vehicles toward maximally informative locations. Gaussian Processes provide this signal but their stationary isotropic kernels are misspecified for non-homogeneous phenomena such as oil spills, producing miscalibrated estimates that degrade planning. We investigate whether replacing the Gaussian Process with a well-calibrated Deep Ensemble improves path planning outcomes, and whether uncertainty quality interacts with the choice of planning algorithm. Five strategies (ε-Greedy, Value Greedy, Uncertainty Greedy, Monte Carlo Tree Search, and Receding Horizon Orienteering) share a common Deep Ensemble backbone trained on physics-based oil spill simulations. On held-out stochastic spill scenarios, the Deep Ensemble reduces normalised reconstruction error by 83% relative to the Gaussian Process baseline. Crucially, well-calibrated uncertainty amplifies the importance of the planning strategy: the performance gap between algorithms is negligible under miscalibrated models but becomes substantial under the ensemble, where multi-step lookahead planners outperform greedy selection by up to 32% in reconstruction error and achieve IoU above 0.85. Monte Carlo Tree Search is the recommended planner, matching Orienteering in reconstruction quality at an order-of-magnitude lower computational cost.
Samuel Yanes Luis, Alejandro Casado Pérez, Alejandro Mendoza Barrionuevo +3
Department of Electronic Technology, University of Sevilla, Sevilla, Spain · Department of Electronic Engineering, University of Sevilla, Sevilla, Spain
An autonomous robot efficiently exploring an unknown environment, such as looking for water sources on Mars, faces two simultaneous demands: building an accurate information map while quickly finding the regions of greatest value, and paying for every meter of travel and the cost of every measurement it takes. Classical information-seeking and reward-seeking criteria address only one of these objectives at a time. Here, we propose Expected Free Energy (EFE), the principled action-selection objective from active inference, as a unifying criterion for budgeted robotic informative path planning. Maintaining a Gaussian-process belief over the information field, our agent plans continuous trajectories that minimize expected free energy under hard path-length constraints. The results from multiple realizations show that EFE-based planning yields accurate posterior maps and locates the highest-value regions simultaneously, outperforming information-theoretic baselines under the same settings. In robotic exploration, these unified, easy-to-tune principled information-gathering strategies facilitate autonomous deployment while enforcing efficiency and resource constraints.
Ajith Anil Meera, Pablo Lanillos, Wouter Kouw
TU Eindhoven, The Netherlands · Cajal Centre for Neuroscience, Spanish National Research Council, Madrid, Spain