Searcharxiv⌕ Search

arXiv subjects

Yancong Wei

Publications and source records attributed to Yancong Wei.

8 recordsLinked to original sources

What Can a VLA Learn from the Agent That Calls It? Task-Level Experience Distillation for Embodied Navigation

Vision-language-action (VLA) models drive the robot directly from camera views, yet a VLA alone shows three typical failures. It walks past the goal, stops before reaching it, and rarely recovers after going off track. Pairing a VLA with a large language model (LLM) planner fixes these failures, but queries the LLM throughout every episode, adding token costs and latency. We introduce Harness-to-Executor (H2E), a task-level distillation method that pairs an LLM planner and a frozen VLA as a heterogeneous training agent, keeps only sessions that reach the goal, and then trains a VLA alone on them so no LLM is used at test time. In these sessions, the planner gives sub-instructions and moves the robot with its own tools, detours are common, and the planner decides when to stop. H2E therefore labels every motion as a VLA action for the original task, whoever made it. It masks the loss on steps moving away from the goal and assigns end labels to states near it, so the VLA learns where the task ends. H2E sets a new state of the art on REVERIE-CE and NavRAG-CE. It raises an 8B VLA's success rate by 15.6% and 11.1% respectively, surpassing a method trained on 10M samples. The distilled VLA exceeds its agent on unseen episodes with zero LLM tokens and runs 3.7 times faster.

cs.RO↗

PRIME W0: Physical Priors from World Models for Embodied Manipulation

Vision-Language-Action (VLA) models excel at instruction following, yet most remain feed-forward: they condition actions only on the current observation and discard both long-horizon temporal context and the hierarchical structure of VLM representations. We present PRIME W0, a hierarchical conditional flow-matching framework that closes this gap through three synergistic designs: (1)per-layer KV injection from a pretrained VLM into an Adaptive MoE action expert; (2)dynamics-aware conditioning via asynchronous world-model subgoal-image prediction and a DINOv2 historical-frame semantic bridge; and (3)Action Dynamic Manifold (ADM) flow matching with covariance-structured noise that respects robot kinematic coupling. PRIME W0 is trained in four stages---VLM pre-training, DAT/NTP visuomotor pre-training, DiT flow-matching decoder assembly with WM injection, and end-to-end SFT---and achieves state-of-the-art results on LIBERO and real-robot benchmarks, with systematic ablations validating each architectural component.

cs.RO↗

REDIRECT: A 1% Fix for Bad Robot Habits

Robots can acquire bad habits from a few defective moments in otherwise useful teleoperation. In mixed-quality robot data, normal and problematic demonstrations share most task behavior and differ only at a local action continuation. Full retraining is costly, while fine-tuning on clean data alone offers limited recovery under a small update budget. We ask whether the local difference can instead be fixed with only 1% of the full-training sample-backward budget. Using only episode-level retained/problematic labels, REDIRECT localizes the branch, assigns a coherent retained continuation to the original observations around it, and anchors shared behavior, without frame-level annotations or additional interaction. Across three randomized ManiSkill tasks and three seeds, REDIRECT raises the mean success rate from 68.2% to 90.3%, recovering 88.8% of the clean-retraining gap versus 22.1% for matched-compute fine-tuning. On a PiPER arm, it recovers 86.7-92.9% of the clean-only gap across cup insertion and towel folding. Local robot habits can therefore be repaired by spending the update budget on the behavioral difference rather than relearning shared behavior.

cs.RO↗

DeViGrasp: Robust Visual Mobile Grasping for Quadruped Manipulators under Degraded Perception

Quadruped manipulators enable mobile grasping in complex environments, yet their whole-body control policies remain vulnerable to unreliable onboard visual perception. Existing methods are typically developed under relatively reliable observations and have not systematically examined how occlusion, segmentation-mask dropout, depth noise, and target-localization jitter affect grasp reasoning and target tracking. To address this gap, we introduce DeViGrasp-Bench, a benchmark for mobile grasping under degraded vision that incorporates controlled visual degradations, seen and unseen objects, multiple difficulty levels, and complex terrains, and evaluates task success, execution efficiency, and action smoothness. We further propose DeViGrasp-Net, a teacher--student framework that combines state-conditioned grasp reasoning with reliability-aware temporal target estimation. The privileged teacher attends to offline grasp candidates conditioned on object, robot, end-effector, and task states, while the deployable student fuses dual-view segmented-depth observations with current, memory, and recovery target hypotheses through Target Hold Memory and Temporal Memory Attention. DeViGrasp-Net outperforms VBC across degradation levels, unseen objects, and complex terrains, and surpasses an adapted DQ-Net across all evaluated degradation levels. Under the Difficult setting, it achieves a success rate of 62.3\%, improving upon VBC and DQ-Net by 16.1 and 4.3 percentage points, respectively; under the Hard setting, its margin over DQ-Net increases to 10.5 percentage points. Ablation studies confirm the complementary benefits of grasp-aware supervision and reliability-aware temporal memory.

cs.RO↗

Safe Expeditious Whole-Body Control of Mobile Manipulators for Collision Avoidance

Whole-body reactive obstacle avoidance for mobile manipulators (MM) remains an open research problem. Control Barrier Functions (CBF), combined with Quadratic Programming (QP), have become a popular approach for reactive control with safety guarantees. However, traditional CBF methods often face issues such as pseudo-equilibrium problems (PEP) and are ineffective in handling dynamic obstacles. To overcome these challenges, we introduce the Adaptive Cyclic Inequality (ACI) method. ACI takes into account both the obstacle's velocity and the robot's nominal control to define a directional safety constraint. When added to the CBF-QP, ACI helps avoid PEP and enables reliable collision avoidance in dynamic environments. We validate our approach on a MM that includes a low-dimensional mobile base and a high-dimensional manipulator, demonstrating the generality of the framework. In addition, we integrate a simple yet effective method for avoiding self-collisions, allowing the robot enabling comprehensive whole-body collision-free operation. Extensive benchmark comparisons and experiments demonstrate that our method performs well in unknown and dynamic scenarios, including difficult tasks like avoiding sticks swung by humans and rapidly thrown objects.

cs.RO↗

Missing Data Reconstruction in Remote Sensing image with a Unified Spatial-Temporal-Spectral Deep Convolutional Neural Network

Because of the internal malfunction of satellite sensors and poor atmospheric conditions such as thick cloud, the acquired remote sensing data often suffer from missing information, i.e., the data usability is greatly reduced. In this paper, a novel method of missing information reconstruction in remote sensing images is proposed. The unified spatial-temporal-spectral framework based on a deep convolutional neural network (STS-CNN) employs a unified deep convolutional neural network combined with spatial-temporal-spectral supplementary information. In addition, to address the fact that most methods can only deal with a single missing information reconstruction task, the proposed approach can solve three typical missing information reconstruction tasks: 1) dead lines in Aqua MODIS band 6; 2) the Landsat ETM+ Scan Line Corrector (SLC)-off problem; and 3) thick cloud removal. It should be noted that the proposed model can use multi-source data (spatial, spectral, and temporal) as the input of the unified framework. The results of both simulated and real-data experiments demonstrate that the proposed model exhibits high effectiveness in the three missing information reconstruction tasks listed above.

cs.CV↗

A Multi-Scale and Multi-Depth Convolutional Neural Network for Remote Sensing Imagery Pan-Sharpening

Pan-sharpening is a fundamental and significant task in the field of remote sensing imagery processing, in which high-resolution spatial details from panchromatic images are employed to enhance the spatial resolution of multi-spectral (MS) images. As the transformation from low spatial resolution MS image to high-resolution MS image is complex and highly non-linear, inspired by the powerful representation for non-linear relationships of deep neural networks, we introduce multi-scale feature extraction and residual learning into the basic convolutional neural network (CNN) architecture and propose the multi-scale and multi-depth convolutional neural network (MSDCNN) for the pan-sharpening of remote sensing imagery. Both the quantitative assessment results and the visual assessment confirm that the proposed network yields high-resolution MS images that are superior to the images produced by the compared state-of-the-art methods.

cs.CV↗

Boosting the accuracy of multi-spectral image pan-sharpening by learning a deep residual network

In the field of fusing multi-spectral and panchromatic images (Pan-sharpening), the impressive effectiveness of deep neural networks has been recently employed to overcome the drawbacks of traditional linear models and boost the fusing accuracy. However, to the best of our knowledge, existing research works are mainly based on simple and flat networks with relatively shallow architecture, which severely limited their performances. In this paper, the concept of residual learning has been introduced to form a very deep convolutional neural network to make a full use of the high non-linearity of deep learning models. By both quantitative and visual assessments on a large number of high quality multi-spectral images from various sources, it has been supported that our proposed model is superior to all mainstream algorithms included in the comparison, and achieved the highest spatial-spectral unified accuracy.

cs.CV↗