Combining Answer Set Programming and Domain Heuristics for Solving Hard Industrial Problems (Application Paper)
University of Calabria（卡拉布里亚大学）；Alpen-Adria-Universität Klagenfurt（阿尔卑斯-亚德里亚大学克拉根福分校）
Carmine Dodaro, Philip Gasteiger, Nicola Leone, Benjamin Musitsch, Francesco Ricca, Kostyantyn Shchekotykhin
备注：
Paper presented at the 32nd International Conference on Logic Programming (ICLP 2016), New York City, USA, 16-21 October 2016, 15 pages, LaTeX, 3 PDF figures
Answer Set Programming (ASP) is a popular logic programming paradigm that has been applied for solving a variety of complex problems. Among the most challenging real-world applications of ASP are two industrial problems defined by Siemens: the Partner Units Problem (PUP) and the Combined Configuration Problem (CCP). The hardest instances of PUP and CCP are out of reach for state-of-the-art ASP solvers. Experiments show that the performance of ASP solvers could be significantly improved by embedding domain-specific heuristics, but a proper effective integration of such criteria in off-the-shelf ASP implementations is not obvious. In this paper the combination of ASP and domain-specific heuristics is studied with the goal of effectively solving real-world problem instances of PUP and CCP. As a byproduct of this activity, the ASP solver WASP was extended with an interface that eases embedding new external heuristics in the solver. The evaluation shows that our domain-heuristic-driven ASP solver finds solutions for all the real-world instances of PUP and CCP ever provided by Siemens. This paper is under consideration for acceptance in TPLP.
BANSAI: Towards Bridging the AI Adoption Gap in Industrial Robotics with Neurosymbolic Programming
ArtiMinds Robotics（阿蒂敏兹机器人公司）；Institute for Artificial Intelligence, University of Bremen（不来梅大学人工智能研究所）；wbk Institute of Production Science, Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院生产科学wbk研究所）
ConstraintLLM: A Neuro-Symbolic Framework for Industrial-Level Constraint Programming
Hangzhou Institute for Advanced Study, UCAS, Hangzhou, China（杭州高等研究院，UCAS，杭州，中国）；University of Oxford, Oxford, UK（牛津大学，牛津，英国）；University of Science and Technology Beijing, Beijing, China（北京科技大学，北京，中国）；SKLCS and Key Laboratory of System Software, ISCAS, Beijing, China（SKLCS和系统软件重点实验室，ISCAS，北京，中国）；Laboratory of Parallel Software and Computational Science, ISCAS, Beijing, China（并行软件与计算科学实验室，ISCAS，北京，中国）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国）
Optimizing Answer Set Computation via Heuristic-Based Decomposition
Department of Mathematics and Computer Science University of Calabria（卡利亚里大学数学与计算机科学系）；University of Calabria（卡利亚里大学）；Department of Mathematics and Computer Science（数学与计算机科学系）；Rende Italy（伦代（意大利）（注：此为地址信息，非机构，不应提取，原提取有误，正确应为仅提取前两个有效机构相关部分，但按文本结构准确提取应为“Department of Mathematics and Computer Science University of Calabria”））
Revisiting the Training of Logic Models of Protein Signaling Networks with a Formal Approach based on Answer Set Programming
CNRS（法国国家科学研究中心）；IRISA（法国信息与随机系统研究所）；INRIA（法国国家信息与自动化研究所）；National Center for Tumor Diseases（国家肿瘤疾病中心）；University of Padova（帕多瓦大学）；European Bioinformatics Institute (EMBL-EBI)（欧洲生物信息研究所（EMBL-EBI））；University of Potsdam（波茨坦大学）
Comparing Heuristics, Constraint Optimization, and Reinforcement Learning for an Industrial 2D Packing Problem
Technische Hochschule Rosenheim（罗森海姆应用技术大学）；Technische Universität München（慕尼黑工业大学）；Institut für nachhaltige Energieversorgung（可持续能源供应研究所）；Technische Hochschule Ingolstadt（因戈尔施塔特应用技术大学）
Action-Increment-Constrained Policy Optimization for Smooth Online Adaptive Critic Flight Control with Actuator Rate Constraints and Low Computational Complexity (extended version with Ultimate Uniform Boundedness analysis)
Section Control and Simulation, Faculty of Aerospace Engineering, Delft University of Technology（控制与仿真部门，航空航天工程学院，代尔夫特理工大学）
Bilevel Learning Model Towards Industrial Scheduling
Hong Kong University（香港大学）；University College London（伦敦大学学院）
自动调度是制造业中广泛需要的一种调度方法，其目标是在有限的资源范围内优化作业顺序。然而，现有的调度系统严重依赖于启发式算法，这要么产生无效的解决方案或计算效率低下时，作业规模的增加。因此，开发新的大规模算法，不仅是高效和有效的，而且能够满足复杂的约束在实践中是非常重要的。在本文中，我们提出了一个双层深度强化学习模型，\textit{BDS}，其中较高的水平是负责探索一个初始的全局序列，而较低的水平是旨在开发部分序列的改进，这两个层次是通过滑动窗口采样机制连接。在实现中，双深度Q网络（DDQN）用于上层，图指针网络（GPN）位于下层。在理论上保证了BDS的收敛性之后，我们在工业自动化仓库的场景中对其进行了评估，每条生产线上的作业数高达$5000$。结果表明，我们提出的BDS显著优于两种最常用的算法，三种强大的深度网络和另一种双层基线方法。特别是，与现实世界中最常用的基于贪婪的启发式算法（需要近1个小时）相比，我们的BDS在3个最大数据集上的最大完工时间分别减少了27.5%、28.6%和22.1%，计算时间小于200 s.
Guiding Large Language Models with Genetic Programming-Evolved Heuristic Knowledge for Dynamic Multi-Mode Project Scheduling
Centre for Data Science and Artificial Intelligence（数据科学与人工智能中心）；School of Engineering and Computer Science（工程与计算机科学学院）；Victoria University of Wellington（惠灵顿维多利亚大学）
Accelerated Genetic Programming Hyper-Heuristics for Simulation-Based Scheduling via Agentic AI
Research Engineering Team REANNZ New Zealand；Centre for Data Science；Artificial Intelligence \& School of Engineering；Computer Science Victoria University of Wellington New Zealand
Genetic Programming with Reinforcement Learning Trained Transformer for Real-World Dynamic Scheduling Problems
Digital Port Technologies Lab, School of Computer Science, University of Nottingham Ningbo China（诺丁汉大学宁波校区计算机科学学院数字港口技术实验室）；School of Computer Science, University of Nottingham（诺丁汉大学计算机科学学院）；Department of Engineering, University of Cambridge（剑桥大学工程学院）；School of Engineering, Westlake University（西湖大学工程学院）
