Pipesworld: Applying Planning Systems to Pipeline Transportation

2004 ◽  
Author(s):  
Ruy L. Milidiu´ ◽  
Frederico dos Santos Liporace
Keyword(s):  
Artificial Intelligence ◽  
Transportation Problem ◽  
General Purpose ◽  
Benchmark Problems ◽  
Planning Problem ◽  
Due Dates ◽  
Planning Systems ◽  
Pipeline Transportation ◽  
Specific Knowledge ◽  
Artificial Intelligence Planning

Most transportation problems consist of moving carriers of stationary cargo. Pipelines are unique in the sense that they are stationary carriers of moving cargo. As a consequence, the planning problem of these systems has singularities that make it very challenging. In this paper we present the Pipesworld model, a transportation problem inspired by the transportation of petroleum derivatives in Petrobras’ pipelines. Pipesworld takes into account important features like product interface constraints, limited product storage capacities and due dates for product delivery. The relevance and unique characteristics of Pipesworld has been recognized by the Artificial Intelligence planning community. Pipesworld has been selected as one of the benchmark problems to be used in the Fourth International Planning Competition, a biannual event to benchmark the state-of-the-art general purpose artificial planning systems. We report the results obtained by general purpose artificial intelligence planning systems when applied to the Pipesworld instances. We also analyze how different modelling techniques may be used to significantly improve the planners’ performance. Although the basic algorithms of these planners do not incorporate any specific knowledge about the pipeline transportation problem, the results obtained so far are quite satisfactory. We also describe our current work in developing Plumber, a dedicated solver, aimed to tackle effective operational situations. Plumber uses general purpose planning techniques but also incorporates domain specific knowledge and may work together with a human expert during the planning process. By applying Plumber to the Pipesworld instances, we compare its performance against general purpose planning systems. Preliminary tests with a first version of Plumber shows that it already outperforms Fast-Forward (FF), one of the best available general purpose planning systems. This shows that improved versions of Plumber have the potential to effectively deal with pipeline transportation operational scenarios.

Comparing HTN Planning Method With Grammar-Based Approach in Generative Design

2000 ◽  
Author(s):  
Hai Shi ◽  
Linda C. Schmidt
Keyword(s):  
Artificial Intelligence ◽  
Conceptual Design ◽  
Planning Method ◽  
Future Research ◽  
Planning Problem ◽  
Generative Design ◽  
Artificial Intelligence Planning ◽  
Design Alternatives ◽  
Htn Planning ◽  
Initial Comparison

Abstract In mechanical conceptual design, the more design alternatives generated, the higher the benefit to designers. In this paper we explore the use of HTN planning, an artificial intelligence planning method, to perform generative conceptual design. The HTN planning method is “goal driven” while the grammar method is “feasibility driven”. We mapped a grammar-based generative method for conceptual design of Meccano carts into an HTN planning problem format. An initial comparison of the two methods is provided in this paper. Exploring the use of a planning method provides a benchmark for future research in generative design.

scholarly journals Reduce Artificial Intelligence Planning Effort by using Map-Reduce Paradigm

2021 ◽  
Vol 10 (7) ◽  
pp. 24-32
Author(s):  
Mohamed Elkawkagy* ◽  
Elbeh Heba
Keyword(s):  
Artificial Intelligence ◽  
Search Space ◽  
Processing Technique ◽  
Substantial Improvement ◽  
Domain Model ◽  
Map Reduce ◽  
Planning Problem ◽  
Ai Planning ◽  
Hierarchical Planning ◽  
Artificial Intelligence Planning

While several approaches have been developed to enhance the efficiency of hierarchical Artificial Intelligence planning (AI-planning), complex problems in AI-planning are challenging to overcome. To find a solution plan, the hierarchical planner produces a huge search space that may be infinite. A planner whose small search space is likely to be more efficient than a planner produces a large search space. In this paper, we will present a new approach to integrating hierarchical AI-planning with the map-reduce paradigm. In the mapping part, we will apply the proposed clustering technique to divide the hierarchical planning problem into smaller problems, so-called sub-problems. A pre-processing technique is conducted for each sub-problem to reduce a declarative hierarchical planning domain model and then find an individual solution for each so-called sub-problem sub-plan. In the reduction part, the conflict between sub-plans is resolved to provide a general solution plan to the given hierarchical AI-planning problem. Preprocessing phase helps the planner cut off the hierarchical planning search space for each sub-problem by removing the compulsory literal elements that help the hierarchical planner seek a solution. The proposed approach has been fully implemented successfully, and some experimental results findings will be provided as proof of our approach's substantial improvement inefficiency.

scholarly journals Organic chemistry synthesis problem as artificial intelligence planning.

2021 ◽  
Author(s):  
Arman Masoumi
Keyword(s):  
Organic Chemistry ◽  
Artificial Intelligence ◽  
Functional Groups ◽  
Organic Synthesis ◽  
Chemical Reactions ◽  
Benchmark Problems ◽  
Logical Language ◽  
Artificial Intelligence Planning ◽  
Planning Problems ◽  
Novel Algorithm

This thesis formulates organic chemistry synthesis problems as Artificial Intelligence planning problems and uses a combination of techniques developed in the field of planning to solve organic synthesis problems. To this end, a methodology for axiomatizing organic chemistry is developed, which includes axiomatizing molecules and functional groups, as well as two approaches for representing chemical reactions in a logical language amenable to reasoning. A novel algorithm for planning specific to organic chemistry is further developed, based on which a planner capable of identifying 75 functional groups and chemical classes is implemented with a knowledge base of 55 generic chemical reactions. The performance of the planner is empirically evaluated on two sets of benchmark problems and analytically compared with a number of competing algorithms. v

scholarly journals Organic chemistry synthesis problem as artificial intelligence planning.

2021 ◽  
Author(s):  
Arman Masoumi
Keyword(s):  
Organic Chemistry ◽  
Artificial Intelligence ◽  
Functional Groups ◽  
Organic Synthesis ◽  
Chemical Reactions ◽  
Benchmark Problems ◽  
Logical Language ◽  
Artificial Intelligence Planning ◽  
Planning Problems ◽  
Novel Algorithm

This thesis formulates organic chemistry synthesis problems as Artificial Intelligence planning problems and uses a combination of techniques developed in the field of planning to solve organic synthesis problems. To this end, a methodology for axiomatizing organic chemistry is developed, which includes axiomatizing molecules and functional groups, as well as two approaches for representing chemical reactions in a logical language amenable to reasoning. A novel algorithm for planning specific to organic chemistry is further developed, based on which a planner capable of identifying 75 functional groups and chemical classes is implemented with a knowledge base of 55 generic chemical reactions. The performance of the planner is empirically evaluated on two sets of benchmark problems and analytically compared with a number of competing algorithms. v

scholarly journals Lessons from the COVID-19 Pandemic on the Use of Artificial Intelligence in Digital Radiology: The Submission of a Survey to Investigate the Opinion of Insiders

Healthcare ◽  
2021 ◽  
Vol 9 (3) ◽  
pp. 331
Author(s):  
Daniele Giansanti ◽  
Ivano Rossi ◽  
Lisa Monoscalco
Keyword(s):  
Artificial Intelligence ◽  
General Purpose ◽  
Point Of View ◽  
General Point ◽  
Thoracic Radiography ◽  
Digital Radiology ◽  
Electronic Survey ◽  
Radiology Technicians ◽  
Medical Radiology ◽  
Great Development

The development of artificial intelligence (AI) during the COVID-19 pandemic is there for all to see, and has undoubtedly mainly concerned the activities of digital radiology. Nevertheless, the strong perception in the research and clinical application environment is that AI in radiology is like a hammer in search of a nail. Notable developments and opportunities do not seem to be combined, now, in the time of the COVID-19 pandemic, with a stable, effective, and concrete use in clinical routine; the use of AI often seems limited to use in research applications. This study considers the future perceived integration of AI with digital radiology after the COVID-19 pandemic and proposes a methodology that, by means of a wide interaction of the involved actors, allows a positioning exercise for acceptance evaluation using a general purpose electronic survey. The methodology was tested on a first category of professionals, the medical radiology technicians (MRT), and allowed to (i) collect their impressions on the issue in a structured way, and (ii) collect their suggestions and their comments in order to create a specific tool for this professional figure to be used in scientific societies. This study is useful for the stakeholders in the field, and yielded several noteworthy observations, among them (iii) the perception of great development in thoracic radiography and CT, but a loss of opportunity in integration with non-radiological technologies; (iv) the belief that it is appropriate to invest in training and infrastructure dedicated to AI; and (v) the widespread idea that AI can become a strong complementary tool to human activity. From a general point of view, the study is a clear invitation to face the last yard of AI in digital radiology, a last yard that depends a lot on the opinion and the ability to accept these technologies by the operators of digital radiology.

Sign in / Sign up

Export Citation Format

Share Document