Applications of Answer Set Programming in Cognitive Robotics


The project Applications of Answer Set Programming in Cognitive Robotics was granted by the Scientific & Technological Research Council of Turkey (TUBITAK) under program 2216 "Research Fellowships for International Researchers".

The project was conducted in the Cognitive Robotics Laboratory at Sabanci University.

Project Team

Scope and Results

Cognitive Robotics is concerned with endowing robotic or software agents with higher level cognitive functions that involve reasoning. In this project we investigate the integration of high-level causal reasoning with low-level geometric reasoning, which is necessary for achieving high-level goals that can be executed in the (low-level) physical world. However this is tricky, as high-level reasoning must be abstract to be efficient, while low-level geometric reasoning must be concrete to be effective. We tackle this challenge using computational methods of Answer Set Programming and related AI methods.

In this project we developed a new method of representing high-level reasoning in AI formalisms where efficient integration of low-level reasoning formalisms is possible. We performed a theoretical analysis, created a prototype implementation, and conducted an empirical evaluation by means of simulation in real-world application scenarios such as housekeeping, cognitive factories, robotic manipulation, and legged locomotion.

Research Activities

J  Journal Article  C  Conference Paper  E  Editorship  O  Other  

Publications 2016:

J , , and . A systematic analysis of levels of integration between high-level task planning and low-level feasibility checks. AI Communications 29 (2), pages 319-349, , DOI: 10.3233/AIC-150697. [  ] [  ]

Publications 2014:

C , , and . A Systematic Analysis of Levels of Integration between High-Level Task Planning and Low-Level Feasibility Checks. In: Workshop on Experimental Evaluation of Algorithms for Solving Problems with Combinatorial Explosion (RCRA), . [  ]

Publications 2013:

J , , , , and . Finding Optimal Plans for Multiple Teams of Robots through a Mediator: A Logic-Based Approach. Theory and Practice of Logic Programming, Special Issue: International Conference on Logic Programming 13 (4-5), pages 831-846, , DOI: 10.1017/S1471068413000525. [  ] [  ]

C , , and . Levels of Integration between Low-Level Reasoning and Task Planning. In: Knowledge Representation and Reasoning in Robotics (KRR) Workshop at International Conference on Logic Programming (ICLP), , arXiv:1307.7461. [  ]

C , , , and . A General Formal Framework for Pathfinding Problems with Multiple Agents. In: AAAI Conference on Artificial Intelligence (AAAI), pages 290-296, . [  ] [  ]

C , , and . Levels of Integration between Low-Level Reasoning and Task Planning. In: AAAI Workshop on Intelligent Robotics Systems (IRS) at AAAI, . [  ] [  ]

C , , , and . Experimental Evaluation of Multi-Agent Pathfinding Problems using Answer Set Programming. In: Workshop on Experimental Evaluation of Algorithms for Solving Problems with Combinatorial Explosion (RCRA), . [  ]

C , , and . Levels of Integration between Low-Level Reasoning and Task Planning. In: Austrian Robotics Workshop (ARW), . [  ]

C , , and . A Systematic Analysis of Levels of Integration between Low-Level Reasoning and Task Planning. In: Workshop on Combining Task and Motion Planning (at IEEE International Conference on Robotics and Automation), . [  ]

C , , , and . Bilişsel Fabrikalarda Birden Fazla Robot Takımı için Eniyileştirilmiş Ayrıştırılabilir Plan Hesaplanması (Finding Optimal Decoupled Plans for Multiple Teams of Robots in Cognitive Factories). In: 21. Sinyal İşleme ve İletişim Uygulamaları Kurultayı (21st Signal Processing and Communications Applications Conference), pages 1681-1684, . [  ]

Impressum: Medieninhaber Peter Schüller (Privatperson), Marmara Universitesi Muhendislik Fakultesi, Bilgisayar Muhendislik Bolumu, Goztepe Kampusu, Kadikoy 34722 - Istanbul, TURKEY. Email: schueller.p@gmail.com. Telefon: +4369910963525 +905533390009