Robotic systems have yet to match humans in skill for movement planning and tool manipulation. For example, humans can robustly grasp and manipulate objects even under task variation. However, successful grasping methods for robotic manipulators are often limited to structured environmental conditions. Our dual goals are to understand manipulation actions in humans and to add such skills to a r...

This paper surveys control architectures proposed in the literature and describes a control architecture that is being developed for a semi-autonomous underwater vehicle for intervention missions (SAUVIM) at the Universip of Hawaii. Conceived as hybrid, this architecture has been organized in three Layers: Planning, Control and Execution. The mission is planned with a sequence of subgoals. Each...

This paper presents an application of Hierarchical Transition Network (HTN) planning to a squad-based military simulation. The hierarchical planner produces collaborative plans for the whole squad in real time, generating the type of highly coordinated behaviours typical for armed combat situations involving trained professionals. Here, we detail the extensions to HTN planning necessary to prov...

In this paper we present the GraphHTN algorithm, a hybrid planning algorithm that does Hierarchical Task-Network (HTN) planning using a combination of HTN-style problem reduction and Graphplan-style planning-graph generation. We also present experimental results comparing GraphHTN with ordinary HTN decomposition (as implemented in the UMCP planner) and ordinary Graphplan search (as implemented ...

We present an extension to the HTN planning paradigm, which provides a more knowledge centred assessment of activities and ordering constraints. Based upon a knowledge-rich model, DART-Network planning applies mixed mode reasoning to determine the need for activities and ordering constraints within a plan. We describe a simple construction problem to demonstrate the limitations of existing HTN ...

Plan generation is important in a number of agent applications, but such applications generally require elaborate domain models that include not only the definitions of the actions that an agent can perform in a given domain, but also information about the most effective ways to generate plans for the agent in that domain. Such models typically take a large amount of human effort to create. To ...

Low-level motion planning techniques must be combined with high-level task planning formalisms in order to generate realistic plans that can be carried out by humans and robots. Previous attempts to integrate these two planning formalisms mostly used either Classical Planning or HTN Planning. Recently, we developed Hierarchical Goal Networks (HGNs), a new hierarchical planning formalism that co...

Hierarchies are the most common structure used to understand the world better. In galaxies, for instance, multiple-star systems are organised in a hierarchical system. Then, governmental and company organisations are structured using a hierarchy, while the Internet, which is used on a daily basis, has a space of domain names arranged hierarchically. Since Artificial Intelligence (AI) planning p...

Think-aloud and pre-test data were collected from 49 undergraduates with varying levels of prior domain knowledge to examine the relationship between prior domain knowledge and self-regulated learning with hypermedia. During the experimental session, each participant individually completed a pretest on the circulatory system, and then one 40-min hypermedia learning task during which he or she l...