Artificial intelligence (AI) reasoning technology involving, e.g., inference, planning, and learning, has a track record with a healthy number of successful applications. So, can it be used as a toolbox of methods for autonomous mobile robots? Not necessarily, as reasoning on a mobile robot about its dynamic, partially known environment may differ substantially from that in knowledge-based pure software systems, where most of the named successes have been registered. This Chapter sketches the main robotics-relevant topics of symbol-based AI reasoning. Basic methods of knowledge representation and inference are described in general, covering both logic- and probability-based approaches. Then, some robotics-related particularities are addressed specially: issues in logic-based high-level robot control, fuzzy logics, and reasoning under time constraints. Two generic applications of reasoning are then described in some detail: action planning and learning. General reasoning is currently not a standard feature onboard autonomous mobile robots. Beyond sketching the state of the art in robotics-related AI reasoning, this Chapter points to the involved research problems that remain to be solved towards that end. The Chapter first reviews knowledge representation and deduction in general (Sect. 9.1), and then goes into some detail regarding reasoning issues that are considered particularly relevant for applications in robots (Sect. 9.2). Having presented reasoning methods, we then enter the field of generic reasoning applications, namely, action planning (Sect. 9.3) and machine learning (Sect. 9.4). Section 9.5 concludes.
CITATION STYLE
Hertzberg, J., & Chatila, R. (2008). AI Reasoning Methods for Robotics. In Springer Handbook of Robotics (pp. 207–223). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-540-30301-5_10
Mendeley helps you to discover research relevant for your work.