This chapter sets the foundation for the next two chapters. It introduces the reader to robotics platforms for the development of acting, planning, and learning functions. The study of motion is based on classical mechanics for the modeling of forces and their effects on mouvements. Robotics builds on this knowledge to master computational motion, navigation, and manipulation over different types of devices and environments. Robotic devices are informally introduced in the following section. Motion problems and the metric representations with continuous state variables needed for geometric, kinematic, and dynamic operational models are then presented. Section 20.3 introduces localization and navigation problems, followed by a section on manipulation problems and their representations.

This chapter is about representing HTN planning domains and solving HTN planning problems. Several of the formal definitions require the same "classical planning" restrictions as in Part I, but most practical HTN implementations loosen or drop several of these restrictions. We first discuss ways to represent and solve planning problems in which there is a totally ordered sequence of tasks to accomplish. We then generalize to allow partially ordered tasks and describe ways to combine classical planning and HTN planning. Finally, we briefly discuss heuristic functions, expressivity, and computational complexity.

The chapters in Part II are about algorithms for planning, acting, and learning using hierarchical task networks (HTNs). HTNs can describe ways to perform complex tasks without the overhead of searching through a large state space, how to avoid situations where unanticipated events are likely to cause bad outcomes, and how to recover when unanticipated events occur.

This chapter discusses several ways for actors to use HTN domain models. These include a way to use HTN methods for purely reactive acting, some simple ways for an actor to make use of an HTN planner, and some ways to repair HTN plans when unexpected events occur during acting.

The hierarchical refinement approach in the previous two chapters requires a priori domain knowledge of the methods, action models, and heuristics used by RAE and UPOM. The topic of this chapter is to use machine learning techniques to synthesize planning heuristics and domain knowledge. It illustrates the "planning to learn" paradigm for learning domain-dependent heuristics to guide RAE and UPOM. Given methods and a sample function, UPOM generates near-optimal choices that are taken as targets by a deep Q-learning procedure. The chapter shows how to synthesize methods for tasks using hierarchical reinforcement techniques.

In Chapter 2 the evolution of ship structures from the prehistoric period up to the present day is described. The aim of this chapter is to bring together the results of underwater archaeology with that of documents, images and models in order to underline the important stages in the evolution of waterborne craft, focusing on structural design and construction practice. The discussion concerning the prehistoric period deals mainly with Egypt and Greece. Fabrication methods used in antiquity are discussed (laced ships, mortise-and-tenon joint). A section is devoted to ship construction in Greece during the historical period (trieris and later ship types). This is followed by descriptions of ships built during the later Roman period and Byzantium covering the first ten centuries of the Christian era. Ship construction practice in Venice is discussed, followed by a discussion of ship construction in China. Evolution of ships in Western Europe included several ship types (cog, hulk, carrack, caravel and galleon). The impact of the introduction of iron and internal combustion engines is discussed. Theoretical developments in mechanics of materials and elasticity theory are discussed in relation to the practice of ship structural design during the 19th century and the first half of the 20th century. The chapter ends with a discussion of computer-based techniques and the introduction of reliability theory.

In this chapter the use of the finite element method in hull girder analysis and design is described. Quasi-static and vibration analysis of the hull girder are considered. The use of approximate simplified quasi-static analysis and of linear elastic finite element analysis using both 2D and 3D models are discussed. The implementation of FE models to the residual and ultimate strength is described and various approaches compared. FE models used in vibration response are considered and the matrix equations of dynamic equilibrium given. Free vibration and forced vibration response are discussed and vibration modes resulting from main engine excitation described. Rule requirements for the implementation of the FEM are discussed. The rational design of the hull girder using a classification society approach is described. Finite element codes used in ship structural analysis and design are mentioned and their capabilities compared. Two case studies are described in detail. The first of these concerns the use of nonlinear elasto-plastic analysis to determine the ultimate strength of a bulk carrier in the alternate hold loading condition. The second study presents a comparison of the dynamic response of single and double-skin bulk carriers involved in a collision incident.

This chapter provides an introduction to ship structures and includes descriptions of structural arrangements of the most important types of merchant ships and the properties of the materials used. This is followed by a discussion of the need to consider ship structures at different levels of analysis (top-down approach). The role of structural modelling, and in particular modelling applicable to global strength, is described. In the second part of the chapter an overview of current practice in ship structural design is presented, in which similarities between merchant and warship structural design are highlighted. The role of classification societies is described as well as that of the IMO Goal-Based-Standards. A comparison of classification society rules follows. The role of computer-based techniques is discussed. In the last section recommendations for good practice in ship structural design are provided.

The optimum structural design of the hull girder is discussed in this chapter. In the first part, early efforts at optimisation are described: structural optimisation, topology and scantlings optimisation and nonlinear programming. The use of linear and sequential linear programming and its use in the MAESTRO program are described. The need to consider wider issues is discussed and the various single-parameter optimisation criteria described (design for X). Multi-objective optimisation criteria and Pareto optimality are discussed. The background to genetic algorithms and the fundamental theorem of genetic algorithms are presented. Single and multi-objective optimisation using genetic algorithms is described and illustrated with application to a catamaran structure. The analytic hierarchy process used in the ranking of different criteria put forward by stakeholders in an optimum structural design problem is described. This is applied in a case study described in the last part of the chapter that concerns the optimum structural design of a RoPax carrier. In this finite element models are used in the concept design stage to select a topology of the structure as well as the preliminary design stage. A series of criteria selected by a number of stakeholders are used as a basis for the optimisation process.

Chapter 3 provides an introduction to the sea loads that act on ship structures, focusing on environment-related and transient loads. A hypothetical but realistic scenario of a loaded voyage of a bulk carrier is presented, and is used to identify and subsequently classify all loads that act on the hull girder. These are classified as environment-related, hull girder-related, mechanical equipment-related and cargo-related. The sources of environment-related loads are then discussed. These include hydrostatic pressure, wave loads, thermal gradients, ice loads, wind pressure and related variations on a geographic and temporal basis. Transient wave loads are then discussed (bottom slamming, bow flare impact and deck wetting), followed by a discussion on springing. The discussion of slamming includes hydroelastic effects. The need for nonlinear analysis in estimating springing and whipping loads is discussed in the last section of the chapter.

This chapter deals with the linear response of the hull girder to primary loads. The primary structure is defined and vertical bending axial and shear stresses are determined. The theory of shear stresses in open and closed sections is presented. Deflections related to both axial and shear stresses are discussed and hull girder longitudinal bending theory is validated against full-scale measurements. Initial design considerations for longitudinal strength are discussed in relation to rule requirements and the calculation of the section modulus of a transverse section. The combined effect of axial bending and shear-induced axial stresses is discussed and shear lag is defined and calculated. The effective breadth method is described. Horizontal bending of the hull girder is discussed next. The response of the hull girder to torsional loading is discussed next. Torsion theory of thin-walled sections is presented and this leads is applied to the analysis of sections consisting of a number of closed cells subjected to uniform torsion. The last section deals with the determination of critical regions of the hull girder for longitudinal strength with respect to yielding, given that the stress field is multiaxial, longitudinal bending stresses being one component.

The design of ship hulls girders for strength is presented in this chapter. Engineering design is introduced and the tasks of ship structural design discussed. The stages of ship structural design are presented: concept design, preliminary structural design and detail structural design. The concepts of design principles, design criteria and design philosophy are discussed and elucidated. The elastic and plastic design philosophies of ship structures are presented and differentiated. The means to perform rational design of ship structures are listed. The need to perform limit state design of ship structures is discussed and the limit states included in IACS rules mentioned. (serviceability limit state, the ultimate limit state, the fatigue limit state and the accidental limit state). The interaction of limit states is discussed as is that of relevant failure modes. In the last part of the chapter the theoretical basis of the design loads used in the IACS Common Structural Rules is described. The concept of the design sea state is introduced, the use of short-term analysis, the selection of dominant short-term sea states and the identification of dominant load components described. The concept of the equivalent design wave is introduced and in the last section design loads discussed.