arXiv subjects

Richard Linares

Publications and source records attributed to Richard Linares.

At least 19 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

Agentic AutoResearch forSpace Autonomy: An Auditable, LLM-Driven Research Agent for Aerospace Control Problems

Spacecraft guidance, navigation, and control functions are increasingly realized as learned policies distilled from expert solvers. Developing such a policy is itself a research process: an investigator selects an architecture and hyperparameters, runs experiments, and must determine whether an apparent improvement is genuine or merely seed noise. This paper presents AutoResearch, a framework in which a large language model autonomously drives that loop for aerospace control problems, coupled with a credibility layer, built into the loop, that certifies each reported result against the problem's own measured seed noise. The language model serves only as the offline research agent that develops the control policy; the trained policy it produces is then deployed onboard the spacecraft, while the model itself never operates the vehicle. At each iteration the agent reads a plain-language problem description and the run history, proposes a single edit to the training script, executes it, and logs the outcome. No reported result is credited until it passes the same three checks: measured per-problem seed noise, reseeded verification of the best configuration, and leave-one-out pruning of the agent's edits. The same loop is applied, unchanged, to two aerospace control problems: a Clohessy-Wiltshire relative rendezvous and a safety-constrained collision-avoidance docking past a keep-out zone, each calibrated against a known optimal control benchmark. In both, the audited policy clears the measured seed noise by many standard deviations; an undirected search over the same parameters does not. On the docking problem the gap becomes categorical: undirected search yields no feasible policy, while the learned policy stays outside the keep-out zone on every seed.

cs.RO↗

arXiv2026

Memory-Efficient Meta-Reinforcement Learning for Adaptive Safety-Critical Control in Adversarial Spacecraft Proximity Operations

Autonomous spacecraft rendezvous and proximity operations (RPO) require controllers that guarantee safety under thrust constraints while minimizing fuel expenditure. Input-constrained control barrier functions (ICCBFs) provide a control method for nonlinear systems with actuation constraints that construct a forward-invariant safe set. Previous work has shown that learning class-$\mathcal{K}$ functions defining the ICCBF recursion via meta reinforcement learning (meta-RL) yields a robust, non-greedy approach to safety-critical control in RPO. This paper extends that framework further by investigating the performance of three recurrent network architectures (Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), Selective State Space Model (Mamba)) and two training algorithms (Proximal Policy Optimization (PPO) and Soft Actor Critic (SAC)) to identify the best setup for tuning ICCBF class-K functions via meta-RL. In addition to cooperative test cases, performance is evaluated in the presence of adversarial behavior where the target spacecraft behaves in a way that worsens the safety of the chaser spacecraft. Results indicate that state space models such as Mamba when used with PPO achieve superior task completion, safety, and fuel-savings compared to other architectures, across all cooperative and uncooperative scenarios tested.

cs.LG↗

arXiv2026

Preparing for the Next Carrington: Spatiotemporal Agent-Based Modeling for Safeguarding Satellite Infrastructure Under Extreme Space Weather Disturbances

Extreme space weather poses an existential threat to modern satellite infrastructure, with a Carrington-class solar storm projected to cause economic losses of billions of dollars per day. Due to the rapid proliferation of satellites (with over 70,000 expected to be deployed in the next 5 years), understanding extreme space weather impacts has become essential for global economic stability and national security, and consequently, the lives of millions. However, our current vulnerability to such events remains largely unknown, and existing models rely primarily on statistical populations instead of individual satellite behavior. Through the development of a novel spatiotemporal agent-based model (ABM), this study addresses two critical research challenges: (1) predicting the impacts of extreme space weather disturbances and (2) enabling real-time maneuver guidance for satellites during such events. Utilizing 41,644 satellite records, historical records from 5 recent space weather events, and atmospheric density models, we built individual satellite agents with physics-driven behaviors that make independent decisions by dynamically responding to constraints such as propellant requirements and collision avoidance thresholds. Scenario analysis suggests that 95% of satellites in Low Earth Orbit altitudes would experience enhanced atmospheric drag of 8x baseline levels, increasing collision risks by 2-3x. Monte Carlo simulations also predict direct economic impact per affected satellite on the order of $40M. Furthermore, the model successfully uses real-time conditions to provide maneuver recommendations, with 92% accuracy. This study is thus the first to provide a prototype framework for real-time adaptive decision systems to safeguard satellites against the next Carrington-class disruption.

physics.geo-ph↗

arXiv2026

The Dyson Minds 2025 Workshop: SETI around Black Holes

The Dyson Minds 2025 Workshop, held at the Center for Brains, Minds & Machines at MIT and organized by Penn State, MIT, and The Ultraintelligence Foundation, brought together researchers in astrophysics, engineering, artificial intelligence, computer science, and philosophy to examine "Dyson Minds" -- large-scale post-biological intelligences powered by energy harvested from supermassive black holes (SMBHs). Building on the ideas of F. J. Dyson (1960, 1966) and I. J. Good (1966), participants explored the physical, engineering, behavioral, and observational consequences of civilizations embodied as machinery operating near the universe's most powerful energy sources. The workshop aimed to develop new observational strategies capable of detecting signatures of such systems. Despite the highly cross-disciplinary scope, discussions centered on how a Dyson Mind might be constructed, how it might behave, and how those factors would shape strategies for the search for extraterrestrial intelligence. Key themes included the thermodynamic, mechanical, and stability limits of Dyson swarms; the trade-offs between power availability and communication latency in distributed minds; and how observability changes depending on whether Dyson Minds act as coherent entities or as loosely coordinated collectives. Across these topics, the consensus was that details of architecture and behavior strongly influence observational signatures. A major recommendation was to apply anomaly-detection methods to archival datasets, including those from WISE, JWST, and the Event Horizon Telescope, to identify unusual sources potentially overlooked by standard reduction pipelines. By integrating insights from multiple disciplines, the meeting advanced concrete, observation-focused strategies for future technosignature searches around SMBHs.

astro-ph.GA↗

arXiv2026

GUIDE: Guided Updates for In-context Decision Evolution in LLM-Driven Spacecraft Operations

Large language models (LLMs) have been proposed as supervisory agents for spacecraft operations, but existing approaches rely on static prompting and do not improve across repeated executions. We introduce \textsc{GUIDE}, a non-parametric policy improvement framework that enables cross-episode adaptation without weight updates by evolving a structured, state-conditioned playbook of natural-language decision rules. A lightweight acting model performs real-time control, while offline reflection updates the playbook from prior trajectories. Evaluated on an adversarial orbital interception task in the Kerbal Space Program Differential Games environment, GUIDE's evolution consistently outperforms static baselines. Results indicate that context evolution in LLM agents functions as policy search over structured decision rules in real-time closed-loop spacecraft interaction.

cs.MA↗

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↗

arXiv2026

Autonomous Reasoning for Spacecraft Control: A Large Language Model Framework with Group Relative Policy Optimization

This paper presents a learning-based guidance-and-control approach that couples a reasoning-enabled Large Language Model (LLM) with Group Relative Policy Optimization (GRPO). A two-stage procedure consisting of Supervised Fine-Tuning (SFT) to learn formatting and control primitives, followed by GRPO for interaction-driven policy improvement, trains controllers for each environment. The framework is demonstrated on four control problems spanning a gradient of dynamical complexity, from canonical linear systems through nonlinear oscillatory dynamics to three-dimensional spacecraft attitude control with gyroscopic coupling and thrust constraints. Results demonstrate that an LLM with explicit reasoning, optimized via GRPO, can synthesize feasible stabilizing policies under consistent training settings across both linear and nonlinear systems. The two-stage training methodology enables models to generate control sequences while providing human-readable explanations of their decision-making process. This work establishes a foundation for applying GRPO-based reasoning to autonomous control systems, with potential applications in aerospace and other safety-critical domains.

cs.RO↗

arXiv2025

Tiny Recursive Control: Iterative Reasoning for Efficient Optimal Control

Neural network controllers increasingly demand millions of parameters, and language model approaches push into the billions. For embedded aerospace systems with strict power and latency constraints, this scaling is prohibitive. We present Tiny Recursive Control (TRC), a neural architecture based on a counterintuitive principle: capacity can emerge from iteration depth rather than parameter count. TRC applies compact networks (approximately 1.5M parameters) repeatedly through a two-level hierarchical latent structure, refining control sequences by simulating trajectories and correcting based on tracking error. Because the same weights process every refinement step, adding iterations increases computation without increasing memory. We evaluate TRC on nonlinear control problems including oscillator stabilization and powered descent with fuel constraints. Across these domains, TRC achieves near-optimal control costs while requiring only millisecond-scale inference on GPU and under 10~MB memory, two orders of magnitude smaller than language model baselines. These results demonstrate that recursive reasoning, previously confined to discrete tasks, transfers effectively to continuous control synthesis.

cs.LG↗

arXiv2025

Multi-Phase Spacecraft Trajectory Optimization via Transformer-Based Reinforcement Learning

Autonomous spacecraft control for mission phases such as launch, ascent, stage separation, and orbit insertion remains a critical challenge due to the need for adaptive policies that generalize across dynamically distinct regimes. While reinforcement learning (RL) has shown promise in individual astrodynamics tasks, existing approaches often require separate policies for distinct mission phases, limiting adaptability and increasing operational complexity. This work introduces a transformer-based RL framework that unifies multi-phase trajectory optimization through a single policy architecture, leveraging the transformer's inherent capacity to model extended temporal contexts. Building on proximal policy optimization (PPO), our framework replaces conventional recurrent networks with a transformer encoder-decoder structure, enabling the agent to maintain coherent memory across mission phases spanning seconds to minutes during critical operations. By integrating a Gated Transformer-XL (GTrXL) architecture, the framework eliminates manual phase transitions while maintaining stability in control decisions. We validate our approach progressively: first demonstrating near-optimal performance on single-phase benchmarks (double integrator and Van der Pol oscillator), then extending to multiphase waypoint navigation variants, and finally tackling a complex multiphase rocket ascent problem that includes atmospheric flight, stage separation, and vacuum operations. Results demonstrate that the transformer-based framework not only matches analytical solutions in simple cases but also effectively learns coherent control policies across dynamically distinct regimes, establishing a foundation for scalable autonomous mission planning that reduces reliance on phase-specific controllers while maintaining compatibility with safety-critical verification protocols.

cs.LG↗

arXiv2025

Advancing AI Challenges for the United States Department of the Air Force

The DAF-MIT AI Accelerator is a collaboration between the United States Department of the Air Force (DAF) and the Massachusetts Institute of Technology (MIT). This program pioneers fundamental advances in artificial intelligence (AI) to expand the competitive advantage of the United States in the defense and civilian sectors. In recent years, AI Accelerator projects have developed and launched public challenge problems aimed at advancing AI research in priority areas. Hallmarks of AI Accelerator challenges include large, publicly available, and AI-ready datasets to stimulate open-source solutions and engage the wider academic and private sector AI ecosystem. This article supplements our previous publication, which introduced AI Accelerator challenges. We provide an update on how ongoing and new challenges have successfully contributed to AI research and applications of AI technologies.

cs.AI↗

arXiv2025

Action Chunking with Transformers for Image-Based Spacecraft Guidance and Control

We present an imitation learning approach for spacecraft guidance, navigation, and control(GNC) that achieves high performance from limited data. Using only 100 expert demonstrations, equivalent to 6,300 environment interactions, our method, which implements Action Chunking with Transformers (ACT), learns a control policy that maps visual and state observations to thrust and torque commands. ACT generates smoother, more consistent trajectories than a meta-reinforcement learning (meta-RL) baseline trained with 40 million interactions. We evaluate ACT on a rendezvous task: in-orbit docking with the International Space Station (ISS). We show that our approach achieves greater accuracy, smoother control, and greater sample efficiency.

cs.RO↗

arXiv2025

BEAVR: Bimanual, multi-Embodiment, Accessible, Virtual Reality Teleoperation System for Robots

\textbf{BEAVR} is an open-source, bimanual, multi-embodiment Virtual Reality (VR) teleoperation system for robots, designed to unify real-time control, data recording, and policy learning across heterogeneous robotic platforms. BEAVR enables real-time, dexterous teleoperation using commodity VR hardware, supports modular integration with robots ranging from 7-DoF manipulators to full-body humanoids, and records synchronized multi-modal demonstrations directly in the LeRobot dataset schema. Our system features a zero-copy streaming architecture achieving $\leq$35\,ms latency, an asynchronous ``think--act'' control loop for scalable inference, and a flexible network API optimized for real-time, multi-robot operation. We benchmark BEAVR across diverse manipulation tasks and demonstrate its compatibility with leading visuomotor policies such as ACT, DiffusionPolicy, and SmolVLA. All code is publicly available, and datasets are released on Hugging Face\footnote{Code, datasets, and VR app available at https://github.com/ARCLab-MIT/BEAVR-Bot.

cs.RO↗

arXiv2025

DreamSat-2.0: Towards a General Single-View Asteroid 3D Reconstruction

To enhance asteroid exploration and autonomous spacecraft navigation, we introduce DreamSat-2.0, a pipeline that benchmarks three state-of-the-art 3D reconstruction models-Hunyuan-3D, Trellis-3D, and Ouroboros-3D-on custom spacecraft and asteroid datasets. Our systematic analysis, using 2D perceptual (image quality) and 3D geometric (shape accuracy) metrics, reveals that model performance is domain-dependent. While models produce higher-quality images of complex spacecraft, they achieve better geometric reconstructions for the simpler forms of asteroids. New benchmarks are established, with Hunyuan-3D achieving top perceptual scores on spacecraft but its best geometric accuracy on asteroids, marking a significant advance over our prior work.

cs.CV↗

arXiv2025

Large Language Models as Autonomous Spacecraft Operators in Kerbal Space Program

Recent trends are emerging in the use of Large Language Models (LLMs) as autonomous agents that take actions based on the content of the user text prompts. We intend to apply these concepts to the field of Control in space, enabling LLMs to play a significant role in the decision-making process for autonomous satellite operations. As a first step towards this goal, we have developed a pure LLM-based solution for the Kerbal Space Program Differential Games (KSPDG) challenge, a public software design competition where participants create autonomous agents for maneuvering satellites involved in non-cooperative space operations, running on the KSP game engine. Our approach leverages prompt engineering, few-shot prompting, and fine-tuning techniques to create an effective LLM-based agent that ranked 2nd in the competition. To the best of our knowledge, this work pioneers the integration of LLM agents into space research. The project comprises several open repositories to facilitate replication and further research. The codebase is accessible on \href{https://github.com/ARCLab-MIT/kspdg}{GitHub}, while the trained models and datasets are available on \href{https://huggingface.co/OhhTuRnz}{Hugging Face}. Additionally, experiment tracking and detailed results can be reviewed on \href{https://wandb.ai/carrusk/huggingface}{Weights \& Biases

cs.AI↗

arXiv2025

Greenhouse Gas (GHG) Emissions Poised to Rocket: Modeling the Environmental Impact of LEO Satellite Constellations

The proliferation of satellite megaconstellations in low Earth orbit (LEO) represents a significant advancement in global broadband connectivity. However, we urgently need to understand the potential environmental impacts, particularly greenhouse gas (GHG) emissions associated with these constellations. This study addresses a critical gap in modeling current and future GHG emissions by developing a comprehensive open-source life cycle assessment (LCA) methodology, applied to 10 launch vehicles and 15 megaconstellations. Our analysis reveals that the production of launch vehicles and propellant combustion during launch events contribute most significantly to overall GHG emissions, accounting for 72.6% of life cycle emissions. Among the rockets analyzed, reusable vehicles like Falcon-9 and Starship demonstrate 95.4% lower production emissions compared to non-reusable alternatives, highlighting the environmental benefits of reusability in space technology. The findings underscore the importance of launch vehicle and satellite design choices to minimize potential environmental impacts. The Open-source Rocket and Constellation Lifecycle Emissions (ORACLE) repository is freely available and aims to facilitate further research in this field. This study provides a critical baseline for policymakers and industry stakeholders to develop strategies for reducing the carbon footprint of the space industry, especially satellite megaconstellations.

physics.geo-ph↗

arXiv2025

Increasing Determinism of All-vs-all Orbital Evolution Simulators

All-vs-all orbital evolutionary simulations for the low Earth orbit (LEO) simulate the long term evolution of the LEO environment. Although these simulations typically offer the highest fidelity, they are also highly computationally intensive. One factor that effectively reduces the efficiency of the approach is that all-vs-all approaches are stochastic and the distribution of the output has large variance. This paper introduces a new, quasi-deterministic all-vs-all simulator, whose variance is greatly reduced compared to traditional methods. The proposed approach virtually simulates collisions happening everywhere and all the time; however, their effect is appropriately reduced to maintain an unbiased estimate of the mean. Additional techniques are used to augment the proposed approach and obtain very precise estimates of any number of standard deviations from the mean, for the evaluation of the Value at Risk (VaR) with a single, low-variance run. Depending on the settings, results show that the variance in total number of debris generated can be reduced by a factor that averages 1,500, while increasing the computational cost by a factor of less than 1.5. Variance can be reduced even more when computing the VaR, albeit a no longer negligible bias is introduced. Low-variance results enable several key applications, such as sensitivity analysis, sustainability assessment of small missions, and fast evaluation of collision risk induced by existing debris. Additionally, rapid computations of the VaR can improve the evaluation of policy robustness, and include confidence intervals in risk assessment.

astro-ph.EP↗