arXiv subjects

Qinglei Hu

Publications and source records attributed to Qinglei Hu.

7 recordsLinked to original sources

arXiv2026

AstroMind: A High-Fidelity Benchmark for Spacecraft Behavior Reasoning Based on Large Language Models

Understanding why a spacecraft maneuvers -- rather than simply that it did -- is an increasingly important problem for space domain awareness as Earth orbits grow crowded and contested. Current analysis pipelines are built for detection: they are good at picking up that something happened, less good at reasoning about what it means. AstroMind is a physics-grounded benchmark designed to close that gap. It draws on high-fidelity astrodynamics simulations and real observational constraints, converting them into verifiable reasoning problems across three task types: intent inference, maneuver parameter estimation, and threat assessment. Each scenario includes realistic sensing noise and multi-source textual intelligence at varying reliability levels. Evaluation metrics capture both semantic correctness and quantitative consistency under physical constraints. Benchmarking a suite of open-weight models shows no single model dominates every axis: Qwen3 (32B) leads on intent inference accuracy; QwQ (32B) leads on threat assessment and achieves the lowest median relative error on parsed items; GPT-OSS (20B) produces the strongest judged reasoning quality and extracts the most scalar values for parameter estimation (136 of 241 parsed items). Training data composition and reasoning style matter as much as model size. Structured reasoning prompts help consistently across tested 8B models, with larger gains for those that can already track physical constraints. AstroMind gives the field a shared test for a problem where getting the physics right and reading the tactical situation correctly are both required -- neither is sufficient on its own.

cs.CL↗

arXiv2025

Safety Meets Speed: Accelerated Neural MPC with Safety Guarantees and No Retraining

While Model Predictive Control (MPC) enforces safety via constraints, its real-time execution can exceed embedded compute budgets. We propose a Barrier-integrated Adaptive Neural Model Predictive Control (BAN-MPC) framework that synergizes neural networks' fast computation with MPC's constraint-handling capability. To ensure strict safety, we replace traditional Euclidean distance with Control Barrier Functions (CBFs) for collision avoidance. We integrate an offline-learned neural value function into the optimization objective of a Short-horizon MPC, substantially reducing online computational complexity. Additionally, we use a second neural network to learn the sensitivity of the value function to system parameters, and adaptively adjust the neural value function based on this neural sensitivity when model parameters change, eliminating the need for retraining and reducing offline computation costs. The hardware in-the-loop (HIL) experiments on Jetson Nano show that BAN-MPC solves 200 times faster than traditional MPC, enabling collision-free navigation with control error below 5\% under model parameter variations within 15\%, making it an effective embedded MPC alternative.

cs.RO↗

arXiv2025

Prescribed-Time Boresight Control of Spacecraft Under Pointing Constraints

This article proposes an integrated boresight guidance and control (IBGC) scheme to address the boresight reorientation problem of spacecraft under temporal and pointing constraints. A $C^1$ continuous, saturated prescribed-time adjustment (PPTA) function is presented, along with the establishment of a practical prescribed-time stability criterion. Utilizing the time scale transformation technique and the PPTA function, we propose a prescribed-time guidance law that guides the boresight vector from almost any initial orientation in free space to a small neighborhood of the goal orientation within a preassigned time, while avoiding all forbidden zones augmented with safety margins. Subsequently, a prescribed-time disturbance observer (PTDO) is derived to reconstruct the external disturbances. By leveraging barrier and PPTA functions, a PTDO-based reduced-attitude tracking controller is developed, which ensures prescribed-time boresight tracking within a ``safe tube''. By judiciously setting the safety margins, settling times, and safe tube for the guidance and control laws, the proposed IBGC scheme achieves pointing-constrained boresight reorientation within a required task completion time. Simulation and experimental results demonstrate the efficacy of the proposed IBGC scheme.

eess.SY↗

arXiv2025

SpaceSeg: A High-Precision Intelligent Perception Segmentation Method for Multi-Spacecraft On-Orbit Targets

With the continuous advancement of human exploration into deep space, intelligent perception and high-precision segmentation technology for on-orbit multi-spacecraft targets have become critical factors for ensuring the success of modern space missions. However, the complex deep space environment, diverse imaging conditions, and high variability in spacecraft morphology pose significant challenges to traditional segmentation methods. This paper proposes SpaceSeg, an innovative vision foundation model-based segmentation framework with four core technical innovations: First, the Multi-Scale Hierarchical Attention Refinement Decoder (MSHARD) achieves high-precision feature decoding through cross-resolution feature fusion via hierarchical attention. Second, the Multi-spacecraft Connected Component Analysis (MS-CCA) effectively resolves topological structure confusion in dense targets. Third, the Spatial Domain Adaptation Transform framework (SDAT) eliminates cross-domain disparities and resist spatial sensor perturbations through composite enhancement strategies. Finally, a custom Multi-Spacecraft Segmentation Task Loss Function is created to significantly improve segmentation robustness in deep space scenarios. To support algorithm validation, we construct the first multi-scale on-orbit multi-spacecraft semantic segmentation dataset SpaceES, which covers four types of spatial backgrounds and 17 typical spacecraft targets. In testing, SpaceSeg achieves state-of-the-art performance with 89.87$\%$ mIoU and 99.98$\%$ mAcc, surpassing existing best methods by 5.71 percentage points. The dataset and code are open-sourced at https://github.com/Akibaru/SpaceSeg to provide critical technical support for next-generation space situational awareness systems.

cs.CV↗

arXiv2024

InPTC: Integrated Planning and Tube-Following Control for Prescribed-Time Collision-Free Navigation of Wheeled Mobile Robots

In this article, we propose a novel approach, called InPTC (Integrated Planning and Tube-Following Control), for prescribed-time collision-free navigation of wheeled mobile robots in a compact convex workspace cluttered with static, sufficiently separated, and convex obstacles. A path planner with prescribed-time convergence is presented based upon Bouligand's tangent cones and time scale transformation (TST) techniques, yielding a continuous vector field that can guide the robot from almost all initial positions in the free space to the designated goal at a prescribed time, while avoiding entering the obstacle regions augmented with safety margin. By leveraging barrier functions and TST, we further derive a tube-following controller to achieve robot trajectory tracking within a prescribed time less than the planner's settling time. This controller ensures the robot moves inside a predefined ``safe tube'' around the reference trajectory, where the tube radius is set to be less than the safety margin. Consequently, the robot will reach the goal location within a prescribed time while avoiding collision with any obstacles along the way. The proposed InPTC is implemented on a Mona robot operating in an arena cluttered with obstacles of various shapes. Experimental results demonstrate that InPTC not only generates smooth collision-free reference trajectories that converge to the goal location at the preassigned time of $250\,\rm s$ (i.e., the required task completion time), but also achieves tube-following trajectory tracking with tracking accuracy higher than $0.01\rm m$ after the preassigned time of $150\,\rm s$. This enables the robot to accomplish the navigation task within the required time of $250\,\rm s$.

cs.RO↗

arXiv2021

Coordinate-free Circumnavigation of a Moving Target via a PD-like Controller

This paper proposes a coordinate-free controller for a nonholonomic vehicle to circumnavigate a fully-actuated moving target by using range-only measurements. If the range rate is available, our Proportional Derivative (PD)-like controller has a simple structure as the standard PD controller, except the design of an additive constant bias and a saturation function in the error feedback. We show that if the target is stationary, the vehicle asymptotically encloses the target with a predefined radius at an exponential convergence rate, i.e., an exact circumnavigation pattern can be completed. For a moving target, the circumnavigation error converges to a small region whose size is shown proportional to the maneuverability of the target, e.g., the maximum linear speed and acceleration. Moreover, we design a second-order sliding mode (SOSM) filter to estimate the range rate and show that the SOSM filter can recover the range rate in a finite time. Finally, the effectiveness and advantages of our controller are validated via both numerical simulations and real experiments.

eess.SY↗

arXiv2021

Composite Adaptive Control for Anti-Unwinding Attitude Maneuvers: An Exponential Stability Result Without Persistent Excitation

This paper provides an exponential stability result for the adaptive anti-unwinding attitude tracking control problem of a rigid body with uncertain but constant inertia parameters, without requiring the satisfaction of persistent excitation (PE) condition. Specifically, a composite immersion and invariance (I&I) adaptive controller is derived by integrating a prediction-error-driven learning law into the dynamically scaled I&I adaptive control framework, wherein we modify the scaling factor so that the algorithm design does not involve any dynamic gains. To avoid the unwinding problem, a barrier function is introduced as the attitude error function, along with the tactful establishment of two crucial algebra properties for exponential stability analysis. The regressor filtering method is adopted in combination with the dynamic regressor extension and mixing (DREM) procedure to acquire the prediction error using only easily obtainable signals. In particular, aiding by a constructive liner time-varying filter, the scalar regressor of DREM is extended to generate a new exciting counterpart. In this way, the derived controller is shown to permit closed-loop exponential stability without PE, in the sense that both output-tracking and parameter estimation errors exponentially converge to zero. Further, the composite learning law is augmented with a power term to achieve synchronized finite/fixed-time parameter convergence. Numerical simulations are performed to verify the theoretical findings.

eess.SY↗