arXiv subjects

Minduli C. Wijayatunga

Publications and source records attributed to Minduli C. Wijayatunga.

6 recordsLinked to original sources

arXiv2026

DreamSat-Bench: Development and Initial Testing of a Testbed for AI-Based Pose Estimation from 3D Reconstruction

This paper presents the development and initial testing of DreamSat-Bench, a modular rendezvous and proximity operation testbed designed to benchmark AI-based relative navigation techniques. By integrating a software- and hardware-in-the-loop robotic pipeline, the platform enables a seamless transition from digital simulation to physical reality. DreamSat-Bench unifies state-of-the-art robotic learning tools such as MuJoCo, Isaac Lab, and LeRobot into a single benchmarking platform, utilizing robotic arms to trace 3D trajectories. The platform allows for extensive customization of orbital environments and lighting to evaluate the simulation-to-reality gap. We demonstrate the testbed's utility by evaluating an end-to-end vision-based navigation pipeline that pairs DreamSat, a generative AI framework for single-view 3D reconstruction, with FoundationPose for zero-shot 6-DoF tracking of unseen spacecraft. Initial testing explores mission-representative orbital segments, including fixed-point station-keeping and fly-around characterization. Through a series of parametric studies, we quantify the impacts of reconstruction latency, mesh resolution, orbital range, and illumination geometry on pose estimation accuracy. Finally, a preliminary hardware-in-the-loop campaign qualitatively validates the physical deployment of the pipeline, identifying target symmetry and accumulated tracking drift as critical factors for robust navigation. DreamSat-Bench provides a rigorous framework for maturing autonomous navigation with unprepared space assets in the absence of prior geometric models.

cs.RO↗

arXiv2026

DreamSat-Pose: Spacecraft Pose Estimation from Single-View 3D Reconstructions and Learned 2D-3D Feature Matching

6-DoF pose estimation is a critical task in autonomous rendezvous and proximity operations. In the case of an unknown target, this task becomes challenging as it shall be paired with the reconstruction of the target shape model. In this article, we propose a novel framework for single-shot shape and pose estimation of unknown spacecraft objects. Given a single image, we first reconstruct a 3D shape model of the target, then estimate the relative six-degrees-of-freedom pose by learning dense 2D-3D correspondences. The image features are extracted using a frozen DINOv3 vision transformer, while the geometric features are computed from the reconstructed point cloud using a trainable dynamic graph convolutional neural network encoder. A dual-stream transformer matcher refines descriptors through alternating self- and cross-attention, producing soft correspondences that are passed to a Perspective-$n$-Point solver for pose recovery. We evaluate the method on the SPE3R dataset and consider FoundationPose as a representative baseline for current state-of-the-art capabilities. Results show reliable pose estimates achieving 0.157 degrees mean pointing error using only a single image and reconstructed geometry, demonstrating strong generalization to unseen spacecraft.

cs.CV↗

arXiv2026

An Autonomous, End-to-End, Convex-Based Framework for Close-Range Rendezvous Trajectory Design and Guidance with Hardware Testbed Validation

Autonomous satellite servicing missions must execute close-range rendezvous under stringent safety and operational constraints while remaining computationally tractable for onboard use and robust to uncertainty in sensing, actuation, and dynamics. This paper presents CORTEX (Convex Optimization for Rendezvous Trajectory Execution), an autonomous, perception-enabled, real-time trajectory design and guidance framework for close-range rendezvous. CORTEX integrates a deep-learning perception pipeline with convex-optimisation-based trajectory design and guidance, including reference regeneration and abort-to-safe-orbit logic to recover from large deviations caused by sensor faults and engine failures. CORTEX is validated in high-fidelity software simulation and hardware-in-the-loop experiments. The software pipeline (Basilisk) models high-fidelity relative dynamics, realistic thruster execution, perception, and attitude control. Hardware testing uses (i) an optical navigation testbed to assess perception-to-estimation performance and (ii) a planar air-bearing testbed to evaluate the end-to-end guidance loop under representative actuation and subsystem effects. A Monte-Carlo campaign in simulation includes initial-state uncertainty, thrust-magnitude errors, and missed-thrust events; under the strongest case investigated, CORTEX achieves terminal docking errors of $36.85 \pm 44.46$ mm in relative position and $1.25 \pm 2.26$ mm/s in relative velocity. On the planar air-bearing testbed, 18 cases are executed (10 nominal; 8 off-nominal requiring recomputation and/or abort due to simulated engine failure and sensor malfunctions), yielding terminal errors of $8.09 \pm 5.29$ mm in position and $2.23 \pm 1.72$ mm/s in velocity.

cs.RO↗

arXiv2026

Meta-Reinforcement Learning for Robust and Non-greedy Control Barrier Functions in Spacecraft Proximity Operations

Autonomous spacecraft inspection and docking missions require controllers that can guarantee safety under thrust constraints and uncertainty. Input-constrained control barrier functions (ICCBFs) provide a framework for safety certification under bounded actuation; however, conventional ICCBF formulations can be overly conservative and exhibit limited robustness to uncertainty, leading to high fuel consumption and reduced mission feasibility. This paper proposes a framework in which the full hierarchy of class-$\mathcal{K}$ functions defining the ICCBF recursion is parameterized and learned, enabling localized shaping of the safe set and reduced conservatism. A control margin is computed efficiently using differential algebra to enable the learned continuous-time ICCBFs to be implemented on time-sampled dynamical systems typical of spacecraft proximity operations. A meta-reinforcement learning scheme is developed to train a policy that generates ICCBF parameters over a distribution of hidden physical parameters and uncertainties, using both multilayer perceptron (MLP) and recurrent neural network (RNN) architectures. Simulation results on cruise control, spacecraft inspection, and docking scenarios demonstrate that the proposed approach maintains safety while reducing fuel consumption and improving feasibility relative to fixed class-$\mathcal{K}$ ICCBFs, with the RNN showing a particularly strong advantage in the more complex inspection case.

eess.SY↗

arXiv2024

Trajectory Design and Guidance for Far-range Proximity Operations of Active Debris Removal Missions with Angles-only Navigation and Safety Considerations

Observability of the target, safety, and robustness are often recognized as critical factors in ensuring successful far-range proximity operations. The application of angles-only (AO) navigation for proximity operations is often met with hesitancy due to its inherent limitations in determining range, leading to issues in target observability and consequently, mission safety. However, this form of navigation remains highly appealing due to its low cost. This work employs Particle Swarm Optimization (PSO) and Reinforcement Learning (RL) for the design and guidance of such far-range trajectories, assuring observability, safety and robustness under angles-only navigation. Firstly, PSO is used to design a nominal trajectory that is observable, robust and safe. Subsequently, Proximal Policy Optimization (PPO), a cutting-edge RL algorithm, is utilized to develop a guidance controller capable of maintaining observability while steering the spacecraft from an initial perturbed state to a target state. The fidelity of the guidance controller is then tested in a Monte-Carlo (MC) manner by varying the initial relative spacecraft state. The observability of the nominal trajectory and the perturbed trajectories with guidance are validated using an Extended Kalman Filter (EKF). The perturbed trajectories are also shown to adhere to the safety requirements satisfied by the nominal trajectory. Results demonstrate that the trained controller successfully determines maneuvers that maintain observability and safety and reaches the target end state.

math.OC↗

arXiv2022

Exploiting Scaling Constants to Facilitate the Convergence of Indirect Trajectory Optimization Methods

This note develops easily applicable techniques that improve the convergence and reduce the computational time of indirect low thrust trajectory optimization when solving fuel- and time-optimal problems. For solving fuel optimal (FO) problems, a positive scaling factor -- $Γ_{TR}$ -- is introduced based on the energy optimal (EO) solution to establish a convenient profile for the switching function of the FO problem. This negates the need for random guesses to initialize the indirect optimization process. Similarly, another scaling factor-$β$-, is introduced when solving the time-optimal (TO) problem to connect the EO problem to the TO. The developed methodology for the TO problem was crucial for the GTOC11 competition. Case studies are conducted to validate the solution process in both TO and FO problems. For geocentric cases, the effect of eclipses and $J_2$ perturbations were also considered. The examples show that EO can provide a good guess for TO and FO problems and that introducing the constants can reduce the initial residuals and improve convergence. It is also shown that the equation for the Lagrangian multiplier of mass and the associated boundary condition can be ignored for both FO and TO cases without affecting optimality. This simplification reduces the problem dimensions and improves efficiency.

math.OC↗