Author name cluster

Wentao He

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

EAAI Journal 2026 Journal Article

Machine learning-based prediction of crack growth path and remaining life by data-driven surrogate model with adaptive dynamic correction algorithm

Wenyue Zhang
Xiaoshun Yan
Yongbo Shao
Xudong Gao
Wentao He

This paper proposes a high-fidelity surrogate model for rapid and accurate automatic crack propagation and remaining life prediction. The program is developed by establishing a machine learning-based surrogate model using a Multilayer Perceptron Neural Network, which incorporates linear elastic fracture mechanics theory and a dynamic adaptive correction algorithm. The training dataset of the high-fidelity surrogate model is generated through co-simulation of ABAQUS and FRANC3D, with Principal Component Analysis utilized to enhance training efficiency. A comprehensive comparative analysis is performed on training performance of various machine learning models. The adaptive dynamic correction algorithm is devised corresponding to different crack growth stages. The proposed data-driven surrogate model with the dynamic adaptive correction algorithm is applied to predict the crack growth paths and remaining life at different locations of an actual cracked flange joint. The correction algorithm is ultimately triggered following crack penetration, which achieves high predictive accuracy, with maximum post-correction errors below 2 % for the crack path and 1 % for the life prediction. The predicted results well consistently with the test set in terms of the stress intensity factor, crack growth path and remaining life, which demonstrates the robustness of the surrogate model and the accuracy of the adaptive dynamic correction algorithm.

Details DOI

IROS Conference 2025 Conference Paper

AnyBipe: An Automated End-to-End Framework for Training and Deploying Bipedal Robots Powered by Large Language Models

Yifei Yao
Wentao He
Chenyu Gu
Jiaheng Du
Fuwei Tan
Zhen Zhu 0004
Jun-Guo Lu

Training and deploying reinforcement learning (RL) policies for robots is a complex task, requiring careful design of reward functions, sim-to-real transfer, and performance evaluation across various robot configurations. These tasks traditionally demand significant human expertise and effort. To address these challenges, this paper introduces Anybipe, a novel, fully automated, end-to-end framework for training and deploying bipedal robots, leveraging large language models (LLMs) for reward function generation, while supervising model training, evaluation, and deployment. The framework integrates comprehensive quantitative metrics to assess policy performance, deployment effectiveness, and safety. Additionally, it allows users to incorporate prior knowledge and preferences, improving the accuracy and alignment of generated policies with expectations. We demonstrate how Anybipe reduces human labor while maintaining high levels of accuracy and safety, examined on three different bipedal robots, showcasing its potential for autonomous RL training and deployment.

Details

AAAI Conference 2024 Conference Paper

Scale Optimization Using Evolutionary Reinforcement Learning for Object Detection on Drone Imagery

Jialu Zhang
Xiaoying Yang
Wentao He
Jianfeng Ren
Qian Zhang
Yitian Zhao
Ruibin Bai
Xiangjian He

Object detection in aerial imagery presents a significant challenge due to large scale variations among objects. This paper proposes an evolutionary reinforcement learning agent, integrated within a coarse-to-fine object detection framework, to optimize the scale for more effective detection of objects in such images. Specifically, a set of patches potentially containing objects are first generated. A set of rewards measuring the localization accuracy, the accuracy of predicted labels, and the scale consistency among nearby patches are designed in the agent to guide the scale optimization. The proposed scale-consistency reward ensures similar scales for neighboring objects of the same category. Furthermore, a spatial-semantic attention mechanism is designed to exploit the spatial semantic relations between patches. The agent employs the proximal policy optimization strategy in conjunction with the evolutionary strategy, effectively utilizing both the current patch status and historical experience embedded in the agent. The proposed model is compared with state-of-the-art methods on two benchmark datasets for object detection on drone imagery. It significantly outperforms all the compared methods. Code is available at https://github.com/UNNC-CV/EvOD/.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Hierarchical ConViT with Attention-Based Relational Reasoner for Visual Analogical Reasoning

Wentao He
Jialu Zhang
Jianfeng Ren
Ruibin Bai
Xudong Jiang

Raven’s Progressive Matrices (RPMs) have been widely used to evaluate the visual reasoning ability of humans. To tackle the challenges of visual perception and logic reasoning on RPMs, we propose a Hierarchical ConViT with Attention-based Relational Reasoner (HCV-ARR). Traditional solution methods often apply relatively shallow convolution networks to visually perceive shape patterns in RPM images, which may not fully model the long-range dependencies of complex pattern combinations in RPMs. The proposed ConViT consists of a convolutional block to capture the low-level attributes of visual patterns, and a transformer block to capture the high-level image semantics such as pattern formations. Furthermore, the proposed hierarchical ConViT captures visual features from multiple receptive fields, where the shallow layers focus on the image fine details while the deeper layers focus on the image semantics. To better model the underlying reasoning rules embedded in RPM images, an Attention-based Relational Reasoner (ARR) is proposed to establish the underlying relations among images. The proposed ARR well exploits the hidden relations among question images through the developed element-wise attentive reasoner. Experimental results on three RPM datasets demonstrate that the proposed HCV-ARR achieves a significant performance gain compared with the state-of-the-art models. The source code is available at: https://github.com/wentaoheunnc/HCV-ARR.

PDF Details DOI