aiqbench analysis
This research applies Proximal Policy Optimization to optimize sensor selection in maritime networks, achieving tracking performance comparable to always-on systems while significantly reducing computational costs and energy consumption. By leveraging belief-state representations from a Bayesian tracker, the learned policy efficiently manages heterogeneous sensors without relying on expensive online entropy calculations. The work demonstrates practical efficiency gains for resource-constrained edge deployments in complex sensing environments.
Reinforcement Learning for Heterogeneous Sensor Selection in Maritime Surveillance
arXiv:2607.22667v1 Announce Type: new Abstract: This paper presents an information-gain-guided reinforcement-learning sensor-selection framework for single-vessel tracking in heterogeneous maritime sensor networks. The proposed approach is motivated by information-theoretic sensor management: instead of activating all sensors or repeatedly performing computationally expensive online expected-information-gain evaluation, a learned policy selects one tracking-relevant sensor at each decision epoch. A Bayesian sequential Monte Carlo tracker estimates the vessel state from noisy measurements and provides a belief representation for scheduling under nonlinear and non-Gaussian conditions. A Proximal Policy Optimization agent selects one of five sensors deployed in a georeferenced simulation of the CMMI Smart Marina testbed at Ayia Napa Marina, Cyprus. The agent observes belief-state, detection-history, coverage, sensor-geometry, and realized-information-gain features. The reward is defined as a realized-information-gain term gated by an observability mask. Final-test simulations compare the proposed framework with random single-sensor selection, always-on sensing using all sensors simultaneously, and the expected-information-gain sensor-selection baseline proposed in our previous work. Results show that the learned policy achieves tracking performance close to always-on sensing while activating only one sensor per decision time step and avoiding the computationally expensive online entropy search required by expected-information-gain selection.
Abstract:This paper presents an information-gain-guided reinforcement-learning sensor-selection framework for single-vessel tracking in heterogeneous maritime sensor networks. The proposed approach is motivated by information-theoretic sensor management: instead of activating all sensors or repeatedly performing computationally expensive online expected-information-gain evaluation, a learned policy selects one tracking-relevant sensor at each decision epoch. A Bayesian sequential Monte Carlo tracker estimates the vessel state from noisy measurements and provides a belief representation for scheduling under nonlinear and non-Gaussian conditions. A Proximal Policy Optimization agent selects one of five sensors deployed in a georeferenced simulation of the CMMI Smart Marina testbed at Ayia Napa Marina, Cyprus. The agent observes belief-state, detection-history, coverage, sensor-geometry, and realized-information-gain features. The reward is defined as a realized-information-gain term gated by an observability mask. Final-test simulations compare the proposed framework with random single-sensor selection, always-on sensing using all sensors simultaneously, and the expected-information-gain sensor-selection baseline proposed in our previous work. Results show that the learned policy achieves tracking performance close to always-on sensing while activating only one sensor per decision time step and avoiding the computationally expensive online entropy search required by expected-information-gain selection.
Artificial Intelligence (cs.AI); Information Theory (cs.IT); Machine Learning (cs.LG); Robotics (cs.RO); Signal Processing (eess.SP); Systems and Control (eess.SY)
I.2.6; I.2.8; I.4.8; G.3
arXiv:2607.22667 [cs.AI]
(or arXiv:2607.22667v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2607.22667 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 220 words
Related coverage
News
Quantum Computing Report · Jul 25, 2026
Temperament Engineering: Designing Strategic Behavioural Diversity in Robot Swarms
arXiv · Sep 25, 2026
Skydio CEO Adam Bry on why Silicon Valley shouldn’t draw red lines for drone use
The Verge · Jun 15, 2026
Reinforcement Learning-Guided Evolutionary Policy Optimization for Preference-Adjustable Heterogeneous Agile Earth Observation Satellite Scheduling
arXiv · Aug 27, 2026