arXiv subjects

Adam Abdin

Publications and source records attributed to Adam Abdin.

14 recordsLinked to original sources

arXiv2026

Offline Approximate Value Iteration: A Reinforcement Learning Approach for Satellite Constellation Deployment

This paper introduces a reinforcement learning-based approximate dynamic programming approach to optimize the deployment of Walker-type satellite constellations under uncertainties, including launch failures and satellite malfunctions. We formulate the problem as a Markov Decision Process that incorporates low-injection orbit launches, continuous low-thrust orbit raising, and variable satellite loads. We adopt the offline approximate value iteration solution method, using linear function approximation with basis functions and action pruning strategies to substantially reduce the computational and memory requirements for finding optimal decision policies. Preliminary results demonstrate convergence to policies with low expected costs and deployment times, both of which are lower than those of a rolling-horizon baseline, showcasing a novel application of approximate dynamic programming in space logistics.

cs.AI↗

arXiv2026

Chance-Constrained Inspection Viewpoint Sequencing for On-Orbit Servicing via Safe Reinforcement Learning

Autonomous inspection of a target spacecraft is typically the initial step in on-orbit servicing. Planning close-proximity observation viewpoints involves a complex combinatorial problem constrained by coverage, fuel, and safety considerations. This paper models the viewpoint selection as a Constrained Markov Decision Process (CMDP) and applies Proximal Policy Optimization with Lagrangian relaxation to solve it. The system combines a high-level planner, which sequences camera viewpoints on an observation sphere around the target, with a low-level model that assesses each transfer using the Clohessy--Wiltshire (CW) equations for relative motion. The deterministic constraints on single-impulse reachability and $Δv$ cap are enforced directly on the action set. Safety margins are affected by navigation and manoeuvre errors, making the actual clearance stochastic. To address this, a chance constraint on the realised trajectory is implemented, with a Lagrangian multiplier governed by PID control to adapt the penalty during training. The approach is tested on a Galileo-class navigation satellite in medium Earth orbit, modelled as a point cloud where visibility from each viewpoint considers field-of-view and line-of-sight occlusion. Across various risk budgets, the trained policy maintains the keep-out violation rate within the specified limit, achieving coverage close to its maximum and staying within the mission $Δv$ budget. Compared to the usual practice of applying a fixed margin to the keep-out radius and planning deterministically, the chance-constrained policy attains less than half the violation rate at comparable coverage. This makes the collision risk an explicit design parameter, eliminating the need for re-tuning per case. The learned policy selects a viewpoint without the repeated Monte Carlo risk estimates required by a greedy, chance-constrained planner at every decision point.

cs.AI↗

arXiv2026

Risk-Sensitive Mission Planning for Multi-Target On-Orbit Inspection via Distributional Reinforcement Learning

Multi-target on-orbit servicing missions require planning tools that can adapt to evolving operational conditions while accounting for the outcome variability inherent to safety-critical spaceflight. This paper presents an adaptive planning approach for multi-target servicing campaigns in low Earth orbit and applies it to inspection missions flown by a low-thrust servicer. The approach is based on Distributional Reinforcement Learning, which learns the full distribution of mission returns and thereby supports explicit risk-sensitive decision-making at each planning step. Specifically, a Quantile-Regression Deep Q-Network (QR-DQN) agent selects which target to inspect next by jointly considering the expectation and the variance of the predicted return through a mean-variance criterion. The mission environment models circular orbits with a spread in inclination and uses Edelbaum's combined-manoeuvre low-thrust transfer estimates. The observation comprises the orbital elements, the visit history, the observed risk state of each target and the remaining mission-time budget. The risk state of each target changes stochastically during the campaign, making the outcome of an inspection uncertain and creating operationally meaningful distinctions between risk-neutral and risk-averse planning strategies. Because the mission-time budget generally admits only a subset of the candidate targets, the planner must also select which targets to inspect. Numerical experiments on scenarios with five target satellites show that one risk-aversion weight moves the policy across a range of mean return and return variance, over an unchanged environment and reward. Risk-averse agents reduce the variance of the episodic return by approximately one half relative to risk-neutral agents and lower the probability of a mission loss, at a cost in mean return. To validate the learned policies, the efficient frontier, which gives the highest mean return attainable at each level of return variance, is computed exactly by enumerating the admissible visit orders. At equal variance, the learned policies lie close to this frontier in mean return, and the risk-averse policies have a lower probability of a mission loss than the frontier policies.

cs.AI↗

arXiv2026

Integrating Low-Thrust Transfer Dynamics into POMDP Planning for On-Orbit Servicing

Recent developments in both high-thrust (HT) and low-thrust (LT) propulsion technologies broaden design options for on-orbit servicing (OOS) missions. However, incorporating LT transfers into OOS mission planning requires accounting for the trade-off between prescribed transfer duration and propellant consumption. Multi-servicing, multi-transfer OOS mission planning is inherently sequential and requires adaptive planning tools that account for propulsion-dependent transfer durations and mass-dependent propellant consumption. Thus, transfer dynamics must be integrated into mission planning and scheduling to increase flexibility and adaptability. In addition, the planning is often done with imperfect information about the system's state and stochastic service demands. This paper focuses on modeling orbital transfers, particularly LT transfers, within a Partially Observable Markov Decision Process (POMDP) framework for OOS mission planning. To enable offline policy computation, the transfer model must provide explicit state transitions and rewards for all admissible actions. The state space is therefore augmented with the servicing vehicle's remaining propellant to enable consistent mass updates. HT transfers are modeled using a precomputed transfer matrix that maps each transfer to the time of flight and propellant consumed. LT transfers are represented using an analytical GEO phasing model with prescribed transfer-duration alternatives. For each alternative, the model calculates propellant consumption and maneuver feasibility as functions of the required phase change and the current servicing-vehicle mass. The proposed modeling approach is evaluated on simplified OOS planning scenarios using circular phasing with HT and LT propulsion. The resulting POMDPs are solved using the Successive Approximations of the Reachable Space under Optimal Policies (SARSOP) algorithm, and the policies obtained under HT and LT are compared. This comparison provides a quantitative assessment of the feasibility and operational impact of LT options, particularly regarding the potential role of advanced electric propulsion in future servicing architectures.

cs.RO↗

arXiv2026

Data-Driven Maintenance Optimization: Aligning Prognostic Learning with Decision Objective

Estimation error in machine learning prognostic models can propagate into poor maintenance decisions. We study a data-driven predictive maintenance problem coupling health-condition estimation with a joint ordering-replacement model. We show that the conventional Estimate-Then-Optimize (ETO) approach yields inconsistent, suboptimal decisions for a broad class of such problems. To bridge the gap, we propose an Integrated Estimate-Optimize (IEO) framework that directly targets maintenance cost as the prognostic learning objective, bypassing surrogate statistical accuracy metrics such as Kullback--Leibler divergence or mean squared error. Theoretically, we prove out-of-sample performance guarantees of the IEO framework under certain conditions, including i.i.d. and sliding-window data-generating processes. Computationally, we develop a training procedure combining Monte Carlo dropout, central-difference gradient approximation, and an ETO warm-start to handle discrete maintenance decisions and nonlinear costs. Experiments on the four CMAPSS subsets demonstrate that, under the nominal setting, IEO reduces mean maintenance cost by 14.8--22.7% relative to ETO and by 7.2--11.8% relative to a decision-oriented baseline, while also reducing failure rates and cost variation. These improvements are obtained despite higher prediction errors. Increasing the ratio of unplanned-downtime costs to planned-downtime costs makes this tradeoff more pronounced: IEO shifts predictions further toward RUL underestimation, accompanied by greater cost savings and fewer failures. These findings support aligning prognostic learning with maintenance objectives when imperfect predictions must guide decisions under costly unplanned downtime.

cs.AI↗

arXiv2026

Structure of Exposure Modeling of Systems to Climate Change Related Hazards

Physical infrastructures designed for stable climate conditions support a significant portion of daily human life activities. However, climate change reshapes the distributions of extreme climate intensities. As a result, physical infrastructures that may face extreme events exceeding their design thresholds risk damage and require adaptation. A preliminary step to adaptation is to identify exposed infrastructures to climate hazards. This paper aims to structure the exposure modeling to climate change hazards by providing an overall methodology. This paper instantiates a framework using the Boolean Exposure Model to assess how physical systems may be exposed to climate hazards. The framework combines a Boolean System Model for infrastructures and a Boolean Hazard Model informed by extreme value statistics. An illustrative case study quantifies the exposure of road bridges in French administrative units to extreme temperatures. Results indicate increasing exposure across future climate scenarios and time periods, with spatial non-uniformity. This framework supports multi-level analysis and integrates non-stationary climate extremes, providing a structured exposure model to facilitate the adaptation of physical systems to climate change.

physics.soc-ph↗

arXiv2026

BOCO: Bayesian Online Contextual Optimization for Decision-Focused Online Learning

\emph{Decision-focused learning} (DFL) trains predictive models to optimize downstream decisions rather than prediction accuracy alone. While recent studies have extended this paradigm to online settings with streaming data, existing online DFL methods generally maintain a point estimate, while their gradient-based updates require either a differentiable optimization layer or a problem-specific surrogate loss. Consequently, they can be unstable under limited data and difficult to apply across heterogeneous optimization problems. We introduce Bayesian Online Contextual Optimization (\texttt{BOCO}), a framework that maintains a decision-focused posterior over model parameters. \texttt{BOCO} aggregates the resulting predictions when prescribing decisions, thereby accounting for parameter uncertainty. To track this posterior in evolving environments, we develop two particle-based inference algorithms: a sequential Monte Carlo sampler for nondifferentiable problems and a function-space Stein variational gradient descent algorithm for differentiable problems. Across both real-world tasks, \texttt{BOCO} reduces running mean regret and temporal regret variability relative to two frequentist online DFL baselines. At the full horizon, relative to the best frequentist baseline, BOCO reduces running mean regret and temporal regret variability by 6.9\% and 6.3\% on knapsack and by 49.3\% and 38.1\% on energy scheduling, respectively. The gains are larger early in the data stream, a pattern consistent with a benefit from accounting for parameter uncertainty when data are limited.

math.OC↗

arXiv2026

From Frequentist to Bayesian Contextual Optimization

In data-driven contextual stochastic optimization, existing approaches are predominantly frequentist: they commit to a single predictive model and treat it as ground truth, yielding prescriptions that are fragile to model uncertainty and sampling variability in small- and moderate-sample regimes. We propose Bayesian contextual optimization (BCO), a framework that maintains a Gibbs posterior over the parameter space. This decision-focused posterior weights candidate models by their empirical decision quality rather than statistical fit, thereby avoiding commitment to a potentially misspecified likelihood while encoding the full distribution of plausible models consistent with the data. A Bayesian contextual policy is then derived by minimizing the expected decision cost under the posterior predictive distribution, hedging prescriptions against model uncertainty by aggregating over the posterior. We establish three theoretical guarantees: (i) the Gibbs posterior concentrates exponentially fast around the frequentist best-in-class parameter set; (ii) BCO can strictly improve over the frequentist best-in-class policy when model uncertainty is non-negligible; and (iii) BCO attains an $O(n^{-1/2})$ excess risk rate against the oracle over all probability measures up to a misspecification term and an oracle aggregate gap. Computationally, we tailor a variational inference scheme that has the same per-iteration cost as frequentist alternatives and a gradient-free Metropolis-Hastings algorithm that handles nondifferentiable problems. Numerical experiments on two-stage shipment planning, contextual newsvendor, and return-constrained portfolio problems confirm that BCO consistently reduces out-of-sample cost and variance relative to kernel estimators and decision-focused baselines, with the most pronounced gains in small- and moderate-sample regimes under substantial model uncertainty.

math.OC↗

arXiv2026

New Formulations and Discretization Insights for the Electric Autonomous Dial-a-Ride Problem

The Electric Autonomous Dial-a-Ride Problem (E-ADARP) involves routing and scheduling electric autonomous vehicles under battery capacity and partial recharging constraints, aiming to minimize total travel cost and excess ride time. In practice, operational data for time and state-of-charge (SoC) are often available only at a coarse granularity. This raises a natural question: can discretization be exploited to improve computational performance by enabling alternative formulation structures? To investigate this question, we develop three formulations reflecting different levels of discretization. The first is an improved event-based formulation (IEBF) with arc-flow SoC variables for the continuous-parameter E-ADARP, serving as a strengthened baseline. The latter two are fragment-based formulations designed for discretized inputs. The second is a time-space fragment-based formulation with continuous SoC arc-flow variables (TSFFCS), which discretizes time while keeping SoC continuous. The third is a battery-time-space fragment-based formulation (BTSFF), which discretizes both time and SoC. Here, an event denotes a tuple consisting of a location and a set of onboard customers, while a fragment denotes a partial path. Computational results show that IEBF improves upon the existing event-based formulation for the original E-ADARP. Under discretized settings, TSFFCS tends to outperform IEBF, particularly when recharging is frequent and time discretization is relatively coarse, indicating that time discretization can improve computational performance across a wide range of settings. In contrast, BTSFF rarely outperforms TSFFCS unless the number of reachable SoC levels is limited, suggesting that explicit SoC discretization is beneficial only in relatively restricted settings.

eess.SY↗

arXiv2026

Improving critical buildings energy resilience via shared autonomous electric vehicles -- A sequential optimization framework

The interdependence between electric power systems and transportation systems is rapidly increasing due to the high adoption of Electric Vehicles (EVs) and their charging infrastructures. Electric vehicles can represent additional load for the power system, but can also bring new opportunities for contributing to the efficient and resilient operations of the power grid. This is mainly because of their ability to provide back power to the system when it is not used for transportation, essentially serving as a moving battery source for the power grid. This so-called Vehicle-to-Grid (V2G), Vehicle-to-Building (V2B), or, generally, Vehicle-to-X (V2X) capability of EVs has been extensively studied in the literature. However, the upcoming development of autonomous driving systems and their integration within sharing mobility services can significantly add to the possibilities of interaction between the transportation system and the power grid. This paradigm is studied to a much lesser extent in the existing literature. Shared Autonomous Electric Vehicles (SAEVs) could allow for more control of the actions of the fleet allowing for large-scale coordinated responses both to mobility and energy demands. This coordinated response can be particularly useful for providing emergency power services in case of power loss while maintaining a high level of transportation service. Thus, improving the overall resilience of the system. In this work, we develop a dynamic optimization framework to evaluate the potential contribution of the SAEV fleet for improving critical buildings' energy resilience via V2B services. The model considers passengers' pick-up and transportation, relocation of vehicles, and battery charging and discharging. Power outage scenarios for critical buildings are considered and the potential of the SAEV fleet to fully or partially respond to the emergency power outage is studied. In addition, sensitivity analysis for key parameters such as the outage parameters is introduced. The results of the case study for the Ile-de-France region in France shows that the SAEV fleet has the potential to provide V2B service for critical building at an acceptable loss of passenger total waiting time on the transportation side. Furthermore, it is shown that it is capable of satisfying the emergency power load at a lower cost compared to investing in extra backup generators unless the outage occurs at significantly high frequencie

math.OC↗

arXiv2026

New electric vehicle charging rate design : an MPEC assessment

A high penetration of electric vehicles (EVs) will deeply impact the management of electric power systems. To avoid costly grid reinforcements and the risk of load curtailment due to EV charging, indirect load control via adapted economic signals is a solution proposed by many utilities. Charging costs can be reduced with a domestic tariff applied only to EV charging using a dedicated load measurement method while enhancing the flexibility offered by EVs. We develop a game-theoretical model expressed and treated as a mathematical programme with equilibrium constraints (MPEC) to capture the interaction between a national regulatory authority (NRA) designing these tariffs and heterogeneous agents. First, we analyse the conditions in which EV-only tariffs can be applied for domestic slow charging sessions by comparing different energy profiles. Second, we study the impact of EV charging on different tariff structures to identify the most efficient way of recovering network costs. Submetering with a pure volumetric tariff can bring yearly gains varying from $64 to $110 compared to a flat rate. This depends on the share of investment in grid reinforcement that remains to be made. Finally, we derive policy implications from the results and earmark more sophisticated tariff designs for further investigation.

math.OC↗

arXiv2026

Transformer-Based Reinforcement Learning for Autonomous Orbital Collision Avoidance in Partially Observable Environments

We introduce a Transformer-based Reinforcement Learning framework for autonomous orbital collision avoidance that explicitly models the effects of partial observability and imperfect monitoring in space operations. The framework combines a configurable encounter simulator, a distance-dependent observation model, and a sequential state estimator to represent uncertainty in relative motion. A central contribution of this work is the use of transformer-based Partially Observable Markov Decision Process (POMDP) architecture, which leverage long-range temporal attention to interpret noisy and intermittent observations more effectively than traditional architectures. This integration provides a foundation for training collision avoidance agents that can operate more reliably under imperfect monitoring environments.

cs.LG↗

arXiv2024

AI-Driven Risk-Aware Scheduling for Active Debris Removal Missions

The proliferation of debris in Low Earth Orbit (LEO) represents a significant threat to space sustainability and spacecraft safety. Active Debris Removal (ADR) has emerged as a promising approach to address this issue, utilising Orbital Transfer Vehicles (OTVs) to facilitate debris deorbiting, thereby reducing future collision risks. However, ADR missions are substantially complex, necessitating accurate planning to make the missions economically viable and technically effective. Moreover, these servicing missions require a high level of autonomous capability to plan under evolving orbital conditions and changing mission requirements. In this paper, an autonomous decision-planning model based on Deep Reinforcement Learning (DRL) is developed to train an OTV to plan optimal debris removal sequencing. It is shown that using the proposed framework, the agent can find optimal mission plans and learn to update the planning autonomously to include risk handling of debris with high collision risk.

cs.AI↗

arXiv2024

On-orbit Servicing for Spacecraft Collision Avoidance With Autonomous Decision Making

This study develops an AI-based implementation of autonomous On-Orbit Servicing (OOS) mission to assist with spacecraft collision avoidance maneuvers (CAMs). We propose an autonomous `servicer' trained with Reinforcement Learning (RL) to autonomously detect potential collisions between a target satellite and space debris, rendezvous and dock with endangered satellites, and execute optimal CAM. The RL model integrates collision risk estimates, satellite specifications, and debris data to generate an optimal maneuver matrix for OOS rendezvous and collision prevention. We employ the Cross-Entropy algorithm to find optimal decision policies efficiently. Initial results demonstrate the feasibility of autonomous robotic OOS for collision avoidance services, focusing on one servicer spacecraft to one endangered satellite scenario. However, merging spacecraft rendezvous and optimal CAM presents significant complexities. We discuss design challenges and critical parameters for the successful implementation of the framework presented through a case study.

cs.AI↗