arXiv subjects

Zhaokui Wang

Publications and source records attributed to Zhaokui Wang.

8 recordsLinked to original sources

arXiv2026

Cross-View Action Consistency for Camera-Robust Vision-Language-Action Policies

Vision-language-action (VLA) policies fine-tuned from a fixed scene camera can fail when the camera is moved, even when the task, objects, language, and robot state are unchanged. We study scene-camera viewpoint robustness using only a scene RGB image, language, and proprioception, without camera labels, extrinsics, depth, or point-cloud inputs. The wrist stream is masked throughout to prevent an unperturbed visual shortcut from confounding attribution to scene-camera variation. For flow-based VLAs, we propose to regularize the action-flow velocity field, the quantity directly integrated to generate continuous action chunks. We construct action-equivalent view pairs by resetting original LIBERO demonstrations to the same MuJoCo state and rendering nominal and perturbed scene-camera views. Both views are supervised by flow matching, while a cross-view loss encourages their predicted action-flow velocities to agree at the same sampled flow coordinates. On the LIBERO-Plus camera-perturbation track, our method reaches 87.2$\pm$0.4% (4,797 rollouts per seed across 3 training seeds), +7.4pp over flow-matching-only training on the same paired data (79.8$\pm$0.8%, also 3 seeds) and +12.5pp over naive mixed-camera SFT, while maintaining nominal-camera ID performance (95.0$\pm$0.8%; same-data FM-only: 95.0$\pm$4.3%). A shuffled-pair control collapses to 25.8%, showing that the gain depends on action-equivalent pairing. On a real robot, we evaluate three tabletop tasks with 10 rollouts per task and camera placement; held-out-camera success improves from 53.3% to 74.4% under the same single-scene-RGB inference interface.

cs.RO↗

arXiv2026

Selective Cross-View Consistency for World Action Models: Held-Out Viewpoint Robustness Without Test-Time Camera Information

World action models (WAMs) jointly denoise future video frames and robot actions, and the video prior is expected to generalize their control. Camera viewpoint change remains one of their hardest perturbation axes. We study a question specific to this model class: when training with same-state cross-view image pairs, on which output coordinates should a consistency loss be imposed? The WAM denoising target mixes view-covariant coordinates, namely the predicted future scene, with view-invariant coordinates, namely the action chunk, future proprioception, and value. We show that consistency applied to the covariant block is provably harmful, shrinking legitimate view-specific content to a fraction $1/(1+4\lambda)$ of its true value, and we verify this shrinkage law in controlled experiments. Selective cross-view consistency (SCVC) therefore constrains only the invariant block, requires no camera labels, extrinsics, depth, or view synthesis at training or test time, and leaves the deployment interface unchanged. We introduce a carve-and-hold-out evaluation protocol on the LIBERO-Plus camera track that separates a distribution-matched ceiling from genuine interpolation and extrapolation to held-out viewpoints, with a matched pair-trained control isolating the effect of the consistency term from pair exposure. On held-out orbital viewpoints beyond the training envelope, SCVC improves closed-loop success over the matched control by 12.2 points (95% CI [7.4, 17.0]; +15.5, CI [11.7, 19.4], under an independent second seed) -- an effect two further camera axes replicate -- while interpolation within the envelope shows no gain in either seed (-1.2 and -4.3 points) and in-distribution competence is preserved (-0.6, -0.2). We also report a cross-backbone audit showing that published camera-robustness numbers are confounded by wrist-camera pose stability.

cs.RO↗

arXiv2026

Smart Commander: A Hierarchical Reinforcement Learning Framework for Fleet-Level PHM Decision Optimization

Decision-making in military aviation Prognostics and Health Management (PHM) faces significant challenges due to the "curse of dimensionality" in large-scale fleet operations, combined with sparse feedback and stochastic mission profiles. To address these issues, this paper proposes Smart Commander, a novel Hierarchical Reinforcement Learning (HRL) framework designed to optimize sequential maintenance and logistics decisions. The framework decomposes the complex control problem into a two-tier hierarchy: a strategic General Commander manages fleet-level availability and cost objectives, while tactical Operation Commanders execute specific actions for sortie generation, maintenance scheduling, and resource allocation. The proposed approach is validated within a custom-built, high-fidelity discrete-event simulation environment that captures the dynamics of aircraft configuration and support logistics.By integrating layered reward shaping with planning-enhanced neural networks, the method effectively addresses the difficulty of sparse and delayed rewards. Empirical evaluations demonstrate that Smart Commander significantly outperforms conventional monolithic Deep Reinforcement Learning (DRL) and rule-based baselines. Notably, it achieves a substantial reduction in training time while demonstrating superior scalability and robustness in failure-prone environments. These results highlight the potential of HRL as a reliable paradigm for next-generation intelligent fleet management.

cs.LG↗

arXiv2021

Cross-Modality Attentive Feature Fusion for Object Detection in Multispectral Remote Sensing Imagery

Cross-modality fusing complementary information of multispectral remote sensing image pairs can improve the perception ability of detection algorithms, making them more robust and reliable for a wider range of applications, such as nighttime detection. Compared with prior methods, we think different features should be processed specifically, the modality-specific features should be retained and enhanced, while the modality-shared features should be cherry-picked from the RGB and thermal IR modalities. Following this idea, a novel and lightweight multispectral feature fusion approach with joint common-modality and differential-modality attentions are proposed, named Cross-Modality Attentive Feature Fusion (CMAFF). Given the intermediate feature maps of RGB and IR images, our module parallel infers attention maps from two separate modalities, common- and differential-modality, then the attention maps are multiplied to the input feature map respectively for adaptive feature enhancement or selection. Extensive experiments demonstrate that our proposed approach can achieve the state-of-the-art performance at a low computation cost.

cs.CV↗

arXiv2021

Atmospheric Density Model Optimization and Spacecraft Orbit Prediction Improvements Based on Q-Sat Orbit Data

Atmospheric drag calculation error greatly reduce the low-earth orbit spacecraft trajectory prediction fidelity. To solve the issue, the "correction - prediction" strategy is usually employed. In the method, one parameter is fixed and other parameters are revised by inverting spacecraft orbit data. However, based on a single spacecraft data, the strategy usually performs poorly as parameters in drag force calculation are coupled with each other, which result in convoluted errors. A gravity field recovery and atmospheric density detection satellite, Q-Sat, developed by xxxxx Lab at xxx University, is launched on August 6th, 2020. The satellite is designed to be spherical for a constant drag coefficient regardless of its attitude. An orbit prediction method for low-earth orbit spacecraft with employment of Q-Sat data is proposed in present paper for decoupling atmospheric density and drag coefficient identification. For the first step, by using a dynamic approach-based inversion, several empirical atmospheric density models are revised based on Q-Sat orbit data. Depending on the performs, one of the revised atmospheric density model would be selected for the next step in which the same inversion is employed for drag coefficient identification for a low-earth orbit operating spacecraft whose orbit needs to be predicted. Finally, orbit prediction is conducted by extrapolation with the dynamic parameters in the previous steps. Tests are carried out with the proposed method by using a GOCE satellite 15-day continuous orbit data. Compared with legacy "correction - prediction" method in which only GOCE data is employed, the accuracy of the 24-hour orbit prediction is improved by about 171m the highest for the proposed method. 14-day averaged 24-hour prediction precision is elevated by approximately 70m.

physics.geo-ph↗

arXiv2021

A One-Shot Texture-Perceiving Generative Adversarial Network for Unsupervised Surface Inspection

Visual surface inspection is a challenging task owing to the highly diverse appearance of target surfaces and defective regions. Previous attempts heavily rely on vast quantities of training examples with manual annotation. However, in some practical cases, it is difficult to obtain a large number of samples for inspection. To combat it, we propose a hierarchical texture-perceiving generative adversarial network (HTP-GAN) that is learned from the one-shot normal image in an unsupervised scheme. Specifically, the HTP-GAN contains a pyramid of convolutional GANs that can capture the global structure and fine-grained representation of an image simultaneously. This innovation helps distinguishing defective surface regions from normal ones. In addition, in the discriminator, a texture-perceiving module is devised to capture the spatially invariant representation of normal image via directional convolutions, making it more sensitive to defective areas. Experiments on a variety of datasets consistently demonstrate the effectiveness of our method.

cs.CV↗

arXiv2020

Multi-robot Cooperative Object Transportation using Decentralized Deep Reinforcement Learning

Object transportation could be a challenging problem for a single robot due to the oversize and/or overweight issues. A multi-robot system can take the advantage of increased driving power and more flexible configuration to solve such a problem. However, increased number of individuals also changed the dynamics of the system which makes control of a multi-robot system more complicated. Even worse, if the whole system is sitting on a centralized decision making unit, the data flow could be easily overloaded due to the upscaling of the system. In this research, we propose a decentralized control scheme on a multi-robot system with each individual equipped with a deep Q-network (DQN) controller to perform an oversized object transportation task. DQN is a deep reinforcement learning algorithm thus does not require the knowledge of system dynamics, instead, it enables the robots to learn appropriate control strategies through trial-and-error style interactions within the task environment. Since analogous controllers are distributed on the individuals, the computational bottleneck is avoided systematically. We demonstrate such a system in a scenario of carrying an oversized rod through a doorway by a two-robot team. The presented multi-robot system learns abstract features of the task and cooperative behaviors are observed. The decentralized DQN-style controller is showing strong robustness against uncertainties. In addition, We propose a universal metric to assess the cooperation quantitatively.

cs.RO↗

arXiv2013

Effect of electrode geometry on photovoltaic performance of polymer solar cells

This paper investigates the impact of electrode geometry on the performance of polymer solar cells (PSCs). Four types of negative electrodes with equal area (0.09 cm2) but different shape (round, oval, square, and triangular) are evaluated with respect to short-circuit current density, open-circuit voltage, fill factor, and power conversion efficiency of PSCs. The results show that the device with round electrodes gives the best photovoltaic performance; in contrast, the device with triangular electrodes reveals the worst properties. Maximum almost twice increase in PCE with round electrode is obtained in the devices compared with that of the triangular electrode. As a conclusion, the electrode boundary curvature has a strong influence on the performance of PSCs. The larger curvature, i.e. the sharper electrodes edge, maybe is a negative effector on exciton separation and carrier transport in PSC system.

cond-mat.mtrl-sci↗