arXiv subjects

Fei Gao

Publications and source records attributed to Fei Gao.

At least 109 records · Page 6Linked to original sources

arXiv2025

FAR-AVIO: Fast and Robust Schur-Complement Based Acoustic-Visual-Inertial Fusion Odometry with Sensor Calibration

Underwater environments impose severe challenges to visual-inertial odometry systems, as strong light attenuation, marine snow and turbidity, together with weakly exciting motions, degrade inertial observability and cause frequent tracking failures over long-term operation. While tightly coupled acoustic-visual-inertial fusion, typically implemented through an acoustic Doppler Velocity Log (DVL) integrated with visual-inertial measurements, can provide accurate state estimation, the associated graph-based optimization is often computationally prohibitive for real-time deployment on resource-constrained platforms. Here we present FAR-AVIO, a Schur-Complement based, tightly coupled acoustic-visual-inertial odometry framework tailored for underwater robots. FAR-AVIO embeds a Schur complement formulation into an Extended Kalman Filter(EKF), enabling joint pose-landmark optimization for accuracy while maintaining constant-time updates by efficiently marginalizing landmark states. On top of this backbone, we introduce Adaptive Weight Adjustment and Reliability Evaluation(AWARE), an online sensor health module that continuously assesses the reliability of visual, inertial and DVL measurements and adaptively regulates their sigma weights, and we develop an efficient online calibration scheme that jointly estimates DVL-IMU extrinsics, without dedicated calibration manoeuvres. Numerical simulations and real-world underwater experiments consistently show that FAR-AVIO outperforms state-of-the-art underwater SLAM baselines in both localization accuracy and computational efficiency, enabling robust operation on low-power embedded platforms. Our implementation has been released as open source software at https://far-vido.gitbook.io/far-vido-docs.

cs.RO↗

arXiv2025

VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments

This paper proposes VLA-AN, an efficient and onboard Vision-Language-Action (VLA) framework dedicated to autonomous drone navigation in complex environments. VLA-AN addresses four major limitations of existing large aerial navigation models: the data domain gap, insufficient temporal navigation with reasoning, safety issues with generative action policies, and onboard deployment constraints. First, we construct a high-fidelity dataset utilizing 3D Gaussian Splatting (3D-GS) to effectively bridge the domain gap. Second, we introduce a progressive three-stage training framework that sequentially reinforces scene comprehension, core flight skills, and complex navigation capabilities. Third, we design a lightweight, real-time action module coupled with geometric safety correction. This module ensures fast, collision-free, and stable command generation, mitigating the safety risks inherent in stochastic generative policies. Finally, through deep optimization of the onboard deployment pipeline, VLA-AN achieves a robust real-time 8.3x improvement in inference throughput on resource-constrained UAVs. Extensive experiments demonstrate that VLA-AN significantly improves spatial grounding, scene reasoning, and long-horizon navigation, achieving a maximum single-task success rate of 98.1%, and providing an efficient, practical solution for realizing full-chain closed-loop autonomy in lightweight aerial robots.

cs.RO↗

arXiv2025

Flying in Clutter on Monocular RGB by Learning in 3D Radiance Fields with Domain Adaptation

Modern autonomous navigation systems predominantly rely on lidar and depth cameras. However, a fundamental question remains: Can flying robots navigate in clutter using solely monocular RGB images? Given the prohibitive costs of real-world data collection, learning policies in simulation offers a promising path. Yet, deploying such policies directly in the physical world is hindered by the significant sim-to-real perception gap. Thus, we propose a framework that couples the photorealism of 3D Gaussian Splatting (3DGS) environments with Adversarial Domain Adaptation. By training in high-fidelity simulation while explicitly minimizing feature discrepancy, our method ensures the policy relies on domain-invariant cues. Experimental results demonstrate that our policy achieves robust zero-shot transfer to the physical world, enabling safe and agile flight in unstructured environments with varying illumination.

cs.RO↗

arXiv2025

Evaluation of Nuclear Microreactor Cost-competitiveness in Current Electricity Markets Considering Reactor Cost Uncertainties

This paper evaluates the cost competitiveness of microreactors in today's electricity markets, with a focus on uncertainties in reactor costs. A Genetic Algorithm (GA) is used to optimize key technical parameters, such as reactor capacity, fuel enrichment, tail enrichment, refueling interval, and discharge burnup, to minimize the Levelized Cost of Energy (LCOE). Base case results are validated using Simulated Annealing (SA). By incorporating Probability Distribution Functions (PDFs) for fuel cycle costs, the study identifies optimal configurations under uncertainty. Methodologically, it introduces a novel framework combining probabilistic cost modeling with evolutionary optimization. Results show that microreactors can remain cost-competitive, with LCOEs ranging from \$48.21/MWh to \$78.32/MWh when supported by the Production Tax Credit (PTC). High reactor capacity, low fuel enrichment, moderate tail enrichment and refueling intervals, and high discharge burnup enhance cost efficiency. Among all factors, overnight capital cost (OCC) has the most significant impact on LCOE, while O&M and fuel cost uncertainties have lesser effects. The analysis highlights how energy policies like the PTC can reduce LCOE by 22-24%, improving viability despite cost variability. Compared to conventional nuclear, coal, and renewable sources like offshore wind, hydro, and biomass, optimized microreactors show strong economic potential. This research defines a realistic design space and key trade-offs, offering actionable insights for policymakers, reactor designers, and energy planners aiming to accelerate the deployment of affordable, sustainable microreactors.

cs.NE↗

arXiv2025

An Adaptive Mixer Allocation Algorithm for the Quantum Alternating Operator Ansatz

Recently, Hadfield et al. proposed the quantum alternating operator ansatz algorithm (QAOA+), an extension of the quantum approximate optimization algorithm (QAOA), to solve constrained combinatorial optimization problems (CCOPs). Compared with QAOA, QAOA+ enables the search for optimal solutions within a feasible solution space by encoding problem constraints into the mixer Hamiltonian, thereby reducing the search space and eliminating the possibility of yielding infeasible solutions. However, QAOA+ may incur high overall gate costs when the mixer is applied to all qubits in each layer, and each mixer is costly to implement. To address this challenge, an adaptive mixer allocation strategy is tailored for QAOA+. The resulting algorithm, which integrates this strategy into the original QAOA+ framework, is referred to as AMA-QAOA+. Unlike QAOA+, AMA-QAOA+ adaptively applies the mixer to a subset of qubits in each layer of the mixer unitary operator based on an evaluation function. The performance of AMA-QAOA+ is evaluated on the maximum independent set problem. Numerical simulation results show that, under the same number of optimization runs, AMA-QAOA+ achieves better solution quality than QAOA+, with the optimal approximation ratio improved by $5.30\%$ on ER random graphs and $5.41\%$ on 3-regular graphs. Moreover, AMA-QAOA+ significantly reduces the CNOT gate consumption, requiring only $15.30\%$ and $25.18\%$ of the CNOT gates used by QAOA+ on ER and 3-regular random graphs, respectively. These results demonstrate that AMA-QAOA+ enhances solution quality and computational efficiency, enabling the design of more compact and resource-efficient quantum circuits.

quant-ph↗

arXiv2025

COMET: A Dual Swashplate Autonomous Coaxial Bi-copter AAV with High-Maneuverability and Long-Endurance

Coaxial bi-copter autonomous aerial vehicles (AAVs) have garnered attention due to their potential for improved rotor system efficiency and compact form factor. However, balancing efficiency, maneuverability, and compactness in coaxial bi-copter systems remains a key design challenge, limiting their practical deployment. This letter introduces COMET, a coaxial bi-copter AAV platform featuring a dual swashplate mechanism. The coaxial bi-copter system's efficiency and compactness are optimized through bench tests, and the whole prototype's efficiency and robustness under varying payload conditions are verified through flight endurance experiments. The maneuverability performance of the system is evaluated in comprehensive trajectory tracking tests. The results indicate that the dual swashplate configuration enhances tracking performance and improves flight efficiency compared to the single swashplate alternative. Successful autonomous flight trials across various scenarios verify COMET's potential for real-world applications.

cs.RO↗

arXiv2025

UMind-VL: A Generalist Ultrasound Vision-Language Model for Unified Grounded Perception and Comprehensive Interpretation

Despite significant strides in medical foundation models, the ultrasound domain lacks a comprehensive solution capable of bridging low-level Ultrasound Grounded Perception (e.g., segmentation, localization) and high-level Ultrasound Comprehensive Interpretation (e.g., diagnosis, reasoning). To bridge this gap, we propose UMind-VL, a unified foundation model designed to synergize pixel-level structural understanding with complex clinical reasoning. We first introduce UMind-DS, a large-scale multimodal dataset comprising 1.2 million ultrasound image-text pairs across 16 anatomical regions, enriching standard data with pixel-level annotations and clinician-validated rationales. Architecturally, UMind-VL incorporates a lightweight Dynamic Convolutional Mask Decoder that generates masks via dynamic kernels conditioned on LLM outputs. This design, combined with task-specific tokens, unifies segmentation, detection, geometric measurement, and diagnosis tasks within a single framework. Extensive evaluations demonstrate that UMind-VL significantly outperforms existing generalist multimodal models and achieves performance on par with, or superior to, state-of-the-art specialist models across segmentation, detection, keypoint localization, and diagnostic reasoning benchmarks, while maintaining strong generalization ability. We demonstrate the capability of UMind-VL in Figure 1.

cs.CV↗

arXiv2025

TopAY: Efficient Trajectory Planning for Differential Drive Mobile Manipulators via Topological Paths Search and Arc Length-Yaw Parameterization

Differential drive mobile manipulators combine the mobility of wheeled bases with the manipulation capability of multi-joint arms, enabling versatile applications but posing considerable challenges for trajectory planning due to their high-dimensional state space and nonholonomic constraints. This paper introduces TopAY, an optimization-based planning framework designed for efficient and safe trajectory generation for differential drive mobile manipulators. The framework employs a hierarchical initial value acquisition strategy, including topological paths search for the base and parallel sampling for the manipulator. A polynomial trajectory representation with arc length-yaw parameterization is also proposed to reduce optimization complexity while preserving dynamic feasibility. Extensive simulation and real-world experiments validate that TopAY achieves higher planning efficiency and success rates than state-of-the-art method in dense and complex scenarios. The source code is released at https://github.com/TopAY-Planner/TopAY .

cs.RO↗

arXiv2025

Logic Distillation: Learning from Code Function by Function for Decision-making Tasks

Large language models (LLMs) have garnered increasing attention owing to their powerful logical reasoning capabilities. Generally, larger LLMs (L-LLMs) that require paid interfaces exhibit significantly superior performance compared to smaller LLMs (S-LLMs) that can be deployed on a variety of devices. Knowledge distillation (KD) aims to empower S-LLMs with the capabilities of L-LLMs, while S-LLMs merely mimic the outputs of L-LLMs, failing to get the powerful logical reasoning capabilities. Consequently, S-LLMs are helpless when it comes to planning and decision-making tasks that require logical reasoning capabilities. To tackle the identified challenges, we propose a novel framework called Logic Distillation (LD). Initially, LD employs L-LLMs to instantiate complex instructions into discrete functions and illustrates their usage to establish a function base. Subsequently, based on the function base, LD fine-tunes S-LLMs to learn the logic employed by L-LLMs in planning and decision-making. During testing, LD utilizes a retriever to identify the top-$K$ relevant functions based on instructions and current states, which will be selected and invoked by S-LLMs. Ultimately, S-LLMs yield planning and decision-making outcomes, function by function. Relevant experiments demonstrate that with the assistance of LD, S-LLMs can achieve outstanding results in planning and decision-making tasks, comparable to, or even surpassing, those of L-LLMs.

cs.AI↗

arXiv2025

LiDAR-VGGT: Cross-Modal Coarse-to-Fine Fusion for Globally Consistent and Metric-Scale Dense Mapping

Reconstructing large-scale colored point clouds is an important task in robotics, supporting perception, navigation, and scene understanding. Despite advances in LiDAR inertial visual odometry (LIVO), its performance remains highly sensitive to extrinsic calibration. Meanwhile, 3D vision foundation models, such as VGGT, suffer from limited scalability in large environments and inherently lack metric scale. To overcome these limitations, we propose LiDAR-VGGT, a novel framework that tightly couples LiDAR inertial odometry with the state-of-the-art VGGT model through a two-stage coarse- to-fine fusion pipeline: First, a pre-fusion module with robust initialization refinement efficiently estimates VGGT poses and point clouds with coarse metric scale within each session. Then, a post-fusion module enhances cross-modal 3D similarity transformation, using bounding-box-based regularization to reduce scale distortions caused by inconsistent FOVs between LiDAR and camera sensors. Extensive experiments across multiple datasets demonstrate that LiDAR-VGGT achieves dense, globally consistent colored point clouds and outperforms both VGGT-based methods and LIVO baselines. The implementation of our proposed novel color point cloud evaluation toolkit will be released as open source.

cs.RO↗

arXiv2025

A Domain Adaptive Position Reconstruction Method for Time Projection Chamber based on Deep Neural Network

Transverse position reconstruction in a Time Projection Chamber (TPC) is crucial for accurate particle tracking and classification, and is typically accomplished using machine learning techniques. However, these methods often exhibit biases and limited resolution due to incompatibility between real experimental data and simulated training samples. To mitigate this issue, we present a domain-adaptive reconstruction approach based on a cycle-consistent generative adversarial network. In the prototype detector, the application of this method led to a 60.6% increase in the reconstructed radial boundary. Scaling this method to a simulated 50-kg TPC, by evaluating the resolution of simulated events, an additional improvement of at least 27% is achieved.

hep-ex↗

arXiv2025

Global-State-Free Obstacle Avoidance for Quadrotor Control in Air-Ground Cooperation

CoNi-MPC provides an efficient framework for UAV control in air-ground cooperative tasks by relying exclusively on relative states, eliminating the need for global state estimation. However, its lack of environmental information poses significant challenges for obstacle avoidance. To address this issue, we propose a novel obstacle avoidance algorithm, Cooperative Non-inertial frame-based Obstacle Avoidance (CoNi-OA), designed explicitly for UAV-UGV cooperative scenarios without reliance on global state estimation or obstacle prediction. CoNi-OA uniquely utilizes a single frame of raw LiDAR data from the UAV to generate a modulation matrix, which directly adjusts the quadrotor's velocity to achieve obstacle avoidance. This modulation-based method enables real-time generation of collision-free trajectories within the UGV's non-inertial frame, significantly reducing computational demands (less than 5 ms per iteration) while maintaining safety in dynamic and unpredictable environments. The key contributions of this work include: (1) a modulation-based obstacle avoidance algorithm specifically tailored for UAV-UGV cooperation in non-inertial frames without global states; (2) rapid, real-time trajectory generation based solely on single-frame LiDAR data, removing the need for obstacle modeling or prediction; and (3) adaptability to both static and dynamic environments, thus extending applicability to featureless or unknown scenarios.

cs.RO↗

arXiv2025

A General Framework for Designing and Evaluating Active-Controlled Trials with Non-Inferiority Objectives

Active-controlled trials with non-inferiority objectives are often used when effective interventions are available, but new options may offer advantages or meet public health needs. In these trials, participants are randomized to an experimental intervention or an active control. The traditional non-inferiority criterion requires that the new intervention preserve a substantial proportion of the active control effect. A key challenge is the absence of a placebo arm, which necessitates reliance on historical data to estimate the active control effect and assumptions about how well this effect applies to the target population. Another challenge arises when the active control is highly effective, as the new intervention may still be valuable even if it does not meet the traditional criterion. This has motivated alternative criteria based on sufficient efficacy relative to a hypothetical placebo. In this work, we propose a general framework for designing and evaluating non-inferiority trials that integrates all existing analytical methods and accommodates both traditional and alternative success criteria. The framework enables the systematic comparison of methods in terms of type I error, power, and robustness to misspecification of the active control effect. We illustrate its applicability in the design of a future HIV prevention trial with a highly effective active control. In this application, our framework identifies methods that provide greater efficiency and robustness than commonly used approaches and demonstrates practical advantages of the alternative non-inferiority criterion. Overall, this framework offers a comprehensive toolkit for rigorous non-inferiority trial design, supporting method selection and the evaluation of new interventions.

stat.ME↗

arXiv2025

Real-time Spatial-temporal Traversability Assessment via Feature-based Sparse Gaussian Process

Terrain analysis is critical for the practical ap- plication of ground mobile robots in real-world tasks, espe- cially in outdoor unstructured environments. In this paper, we propose a novel spatial-temporal traversability assessment method, which aims to enable autonomous robots to effectively navigate through complex terrains. Our approach utilizes sparse Gaussian processes (SGP) to extract geometric features (curvature, gradient, elevation, etc.) directly from point cloud scans. These features are then used to construct a high- resolution local traversability map. Then, we design a spatial- temporal Bayesian Gaussian kernel (BGK) inference method to dynamically evaluate traversability scores, integrating historical and real-time data while considering factors such as slope, flatness, gradient, and uncertainty metrics. GPU acceleration is applied in the feature extraction step, and the system achieves real-time performance. Extensive simulation experiments across diverse terrain scenarios demonstrate that our method outper- forms SOTA approaches in both accuracy and computational efficiency. Additionally, we develop an autonomous navigation framework integrated with the traversability map and validate it with a differential driven vehicle in complex outdoor envi- ronments. Our code will be open-source for further research and development by the community, https://github.com/ZJU-FAST-Lab/FSGP_BGK.

cs.RO↗

arXiv2025

Stratos: An End-to-End Distillation Pipeline for Customized LLMs under Distributed Cloud Environments

The growing industrial demand for customized and cost-efficient large language models (LLMs) is fueled by the rise of vertical, domain-specific tasks and the need to optimize performance under constraints such as latency and budget. Knowledge distillation, as an efficient model compression and transfer technique, offers a feasible solution. However, existing distillation frameworks often require manual intervention and struggle to meet such complex user-defined distillation requirements. To bridge this gap, we propose Stratos, an end-to-end LLM distillation pipeline that automates server and model selection, knowledge distillation, and deployment in distributed cloud environments. Given user-defined constraints on model performance and system budget, Stratos automatically selects Pareto-optimal servers, dynamically matches teacher-student pairs, and adapts distillation strategies based on task complexity to optimize cloud hosting. Experiments show that Stratos produces a student model that achieves four times the accuracy of its GPT-4o teacher baseline on a rare, domain-specific Mahjong reasoning task with reverse synthetic data and knowledge injection. Moreover, it achieves reduced latency and cost without compromising accuracy. These results highlight its promise for vertical-domain LLM deployment.

cs.LG↗

arXiv2025

Heavy-light mesons from a flavour-dependent interaction

We introduce a new symmetry-preserving framework for the physics of heavy-light mesons, whose key element is the effective incorporation of flavour-dependent contributions into the corresponding bound-state and quark gap equations. These terms originate from the fully-dressed quark-gluon vertices appearing in the kernels of these equations, and provide a natural distinction between ``light" and ``heavy" quarks. In this approach, only the classical form factor of the quark-gluon vertex is retained, and is evaluated in the so-called ``symmetric" configuration. The standard Slavnov-Taylor identity links this form factor to the quark wave-function, allowing for the continuous transition from light to heavy quarks through the mere variation of the current quark mass in the gap equation. The method is used to compute the masses and decay constants of specific pseudoscalars and vector heavy-light systems, showing good overall agreement with both experimental data and lattice simulations.

hep-ph↗

arXiv2025

FastViDAR: Real-Time Omnidirectional Depth Estimation via Alternative Hierarchical Attention

In this paper we propose FastViDAR, a novel framework that takes four fisheye camera inputs and produces a full $360^\circ$ depth map along with per-camera depth, fusion depth, and confidence estimates. Our main contributions are: (1) We introduce Alternative Hierarchical Attention (AHA) mechanism that efficiently fuses features across views through separate intra-frame and inter-frame windowed self-attention, achieving cross-view feature mixing with reduced overhead. (2) We propose a novel ERP fusion approach that projects multi-view depth estimates to a shared equirectangular coordinate system to obtain the final fusion depth. (3) We generate ERP image-depth pairs using HM3D and 2D3D-S datasets for comprehensive evaluation, demonstrating competitive zero-shot performance on real datasets while achieving up to 20 FPS on NVIDIA Orin NX embedded hardware. Project page: \href{https://3f7dfc.github.io/FastVidar/}{https://3f7dfc.github.io/FastVidar/}

cs.CV↗

arXiv2025

Reinforcement Learning on Pre-Training Data

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we introduce Reinforcement Learning on Pre-Training data (RLPT), a new training-time scaling paradigm for optimizing LLMs. In contrast to prior approaches that scale training primarily through supervised learning, RLPT enables the policy to autonomously explore meaningful trajectories to learn from pre-training data and improve its capability through reinforcement learning (RL). While existing RL strategies such as reinforcement learning from human feedback (RLHF) and reinforcement learning with verifiable rewards (RLVR) rely on human annotation for reward construction, RLPT eliminates this dependency by deriving reward signals directly from pre-training data. Specifically, it adopts a next-segment reasoning objective, rewarding the policy for accurately predicting subsequent text segments conditioned on the preceding context. This formulation allows RL to be scaled on pre-training data, encouraging the exploration of richer trajectories across broader contexts and thereby fostering more generalizable reasoning skills. Extensive experiments on both general-domain and mathematical reasoning benchmarks across multiple models validate the effectiveness of RLPT. For example, when applied to Qwen3-4B-Base, RLPT yields absolute improvements of $3.0$, $5.1$, $8.1$, $6.0$, $6.6$, and $5.3$ on MMLU, MMLU-Pro, GPQA-Diamond, KOR-Bench, AIME24, and AIME25, respectively. The results further demonstrate favorable scaling behavior, suggesting strong potential for continued gains with more compute. In addition, RLPT provides a solid foundation, extending the reasoning boundaries of LLMs and enhancing RLVR performance.

cs.CL↗