Author name cluster

Jun Hong

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.

7 papers

1 author row

EAAI Journal 2026 Journal Article

A global and local agent-based curriculum reinforcement learning approach for multi-end-effector robotic arm manipulation

Yichen Wang
Shuai Zheng
Ze Yang
Jingmin Guo
Zitong Yang
Jun Hong

Reinforcement learning is widely applied in robotic arm manipulation tasks. However, most of these tasks focus on single and simple end effector. When facing heavy robotic arm hoisting tasks, which are usually manipulated by robotic arms with multi-end-effectors and more degrees of freedom, the single-agent-based reinforcement learning method performs relatively ineffective. In this paper, we propose a multi-agent reinforcement learning approach for hoisting tasks manipulated by robotic arm with multi-end-effectors. The method decomposes the robotic arm into global and local agents based on the degrees of freedom, with one agent controlling global and rough movement, and the other controlling local and fine movement. In this way, the multi-end-effectors’ spatial trajectory can be accurately manipulated. Moreover, in the training process, a four levels curriculum learning strategy is introduced, in which different reward functions are designed respectively, to make the training efficiency and effectiveness. We develop a Unity engine environment-based simulation and perform several comparison experiments. The results demonstrate that the proposed approach outperforms conventional single-agent-based methods.

Details DOI

EAAI Journal 2026 Journal Article

A novel physics-constrained deep learning framework for the inverse design of assembly contact interfaces

Lifei Chen
Qiyin Lin
Mingjun Qiu
Chen Wang
Tao Wang
Hao Guan
Qiyuan Xie
Yuge Jiao

Assembly contact interface characteristics critically influence the performance of precision mechanical systems. Traditional design methods relying on iterative finite element analysis are computationally expensive, while existing deep learning approaches often neglect physical constraints and the complex effects of assembly processes. To address these limitations, this paper proposes a physics-constrained deep learning framework for the inverse design of assembly interfaces. Specifically, we introduce a novel network architecture which integrates multi-source inputs including target contact pressure, assembly parameters, and service conditions. To enforce physical consistency, a differentiable loss function incorporating the impenetrability condition is developed. Furthermore, an optimized learning rate scheduling strategy is implemented to enhance model convergence. Comprehensive ablation and comparative experiments demonstrate that our method outperforms conventional approaches in both accuracy and physical plausibility. When applied to an aero-engine flange structure, the framework enables rapid inverse design of interface morphology, reducing maximum contact pressure by 15. 67% and increasing the effective contact area by 45. 23% compared to traditional designs. This work provides a robust solution for assembly interface design and advances the application of physics-constrained deep learning in complex engineering systems.

Details DOI

EAAI Journal 2024 Journal Article

Progressive generative adversarial network for generating high-dimensional and wide-frequency signals in intelligent fault diagnosis

Zhijun Ren
Kai Huang
Yongsheng Zhu
Ke Feng
Zheng Liu
Hong Fu
Jun Hong
Adam Glowacz

Imbalance is a typical characteristic of data in the field of intelligent fault diagnosis. As a data augmentation method that both balances data and extends information, the generative adversarial network has aroused widespread concern in the data imbalance problem. However, it still suffers from high difficulty in model training and poor quality of generated samples. To address this issue, this paper proposes a progressive generative adversarial network, which is a strategy able to gradually generate complex signals from low-frequency signals to wide-frequency signals. In the developed network, on the one hand, decomposing signals into different frequency bands explicitly reduces the difficulty of directly generating high-dimensional and wide-frequency signals. On the other hand, different generative models can focus on different frequency bands, avoiding the interference of high-energy signals on the fault feature frequencies. In order to achieve good generative performance, the generators and training method for the progressive generative adversarial network are elaborately designed. The correlation shortcut avoids information suppression due to the poor selection of noise amplitudes, and the focusing shortcut forces the body of the generator to focus on key feature bands. Ultimately, the superiority of the progressive generative network is verified by evaluating the quality of the generated samples on three datasets and applying the generated samples to solve the data imbalance problem.

Details DOI

EAAI Journal 2023 Journal Article

Generative adversarial networks driven by multi-domain information for improving the quality of generated samples in fault diagnosis

Zhijun Ren
Dawei Gao
Yongsheng Zhu
Qing Ni
Ke Yan
Jun Hong

The performance of intelligent fault diagnosis models is often hindered by the lack of available samples, a common issue in both the few-shot learning and imbalanced learning problems. While data generation has been shown to be an effective strategy for addressing this issue, existing methods tend to focus solely on the similarity of the generated samples, overlooking their diversity. In this regard, a self-reasoning training strategy that enables the participation of highly reliable generated samples in the training process is proposed. By augmenting the training samples, the strategy provides the generation model with diverse input information, effectively enhancing the diversity of the samples generated by the model. To assess the reliability of the generated samples, Pearson correlation coefficient between the generated and real samples in the amplitude–frequency domain is utilized. To this end, an amplitude–frequency domain generation model is constructed. In order to avoid issues such as gradient disappearance and convergence degradation during the generation process in the amplitude–frequency domain, a phase-frequency domain generation model as well as a time domain discriminator model are developed. While the phase-frequency domain generation model enhances the diversity of the generated samples in that domain, the time domain discriminator model ensures sample similarity by correlating the amplitude–frequency domain generation model with the phase-frequency domain generation model. Through experiments, it is demonstrated that the proposed method can effectively address the overfitting problem of generative adversarial networks with few samples, improving the diversity of the generated samples. Moreover, the improvement in fault diagnosis performance achieved by the samples generated by the proposed method further underscores its potential and superiority in practical applications.

Details DOI

JAIR Journal 2017 Journal Article

Managing Different Sources of Uncertainty in a BDI Framework in a Principled Way with Tractable Fragments

Kim Bauters
Kevin McAreavey
Weiru Liu
Jun Hong
Lluís Godo
Carles Sierra

The Belief-Desire-Intention (BDI) architecture is a practical approach for modelling large-scale intelligent systems. In the BDI setting, a complex system is represented as a network of interacting agents - or components - each one modelled based on its beliefs, desires and intentions. However, current BDI implementations are not well-suited for modelling more realistic intelligent systems which operate in environments pervaded by different types of uncertainty. Furthermore, existing approaches for dealing with uncertainty typically do not offer syntactical or tractable ways of reasoning about uncertainty. This complicates their integration with BDI implementations, which heavily rely on fast and reactive decisions. In this paper, we advance the state-of-the-art w.r.t. handling different types of uncertainty in BDI agents. The contributions of this paper are, first, a new way of modelling the beliefs of an agent as a set of epistemic states. Each epistemic state can use a distinct underlying uncertainty theory and revision strategy, and commensurability between epistemic states is achieved through a stratification approach. Second, we present a novel syntactic approach to revising beliefs given unreliable input. We prove that this syntactic approach agrees with the semantic definition, and we identify expressive fragments that are particularly useful for resource-bounded agents. Third, we introduce full operational semantics that extend CAN, a popular semantics for BDI, to establish how reasoning about uncertainty can be tightly integrated into the BDI framework. Fourth, we provide comprehensive experimental results to highlight the usefulness and feasibility of our approach, and explain how the generic epistemic state can be instantiated into various representations.

PDF Details DOI

AAMAS Conference 2017 Conference Paper

The Event Calculus in Probabilistic Logic Programming with Annotated Disjunctions

Kevin McAreavey
Kim Bauters
Weiru Liu
Jun Hong

We propose a new probabilistic extension to the event calculus using the probabilistic logic programming (PLP) language ProbLog, and a language construct called the annotated disjunction. This is the first extension of the event calculus capable of handling numerous sources of uncertainty (e. g. from primitive event observations and from composite event definitions). It is also the first extension capable of handling multiple sources of event observations (e. g. in multi-sensor environments). We describe characteristics of this new extension (e. g. rationality of conclusions), and prove some important properties (e. g. validity in ProbLog). Our extension is directly implementable in ProbLog, and we successfully apply it to the problem of activity recognition under uncertainty in an event detection data set obtained from vision analytics of bus surveillance video.

PDF

AAAI Conference 2000 Conference Paper

Graph Construction and Analysis as a Paradigm for Plan Recognition

Jun Hong

We present a novel approach to plan recognition in which graph construction and analysis is used as a paradigm. We use a graph structure called a Goal Graph for the plan recognition problem. The Goal Graph is first constructed to represent the observed actions, the state of the world, and the achieved goals at consecutive time steps. It also represents various connections between nodes in the Goal Graph. The Goal Graph can then be analysed at each time step to recognise those achieved goals that are consistent with the actions observed so far. The Goal Graph analysis can also reveal valid plans for the recognised goals or part of the recognised goals. We describe two algorithms, Goal- GraphConstructor and GoalGraphAnalyser, based on this paradigm. Thesealgorithms are sound, polynomialtime and polynomial-space. The algorithms have been tested in two domains with up to 245 goal schemata and 100000 possible goals. They perform well in these domains in terms of efficiency, accuracy and scalability.

PDF Details