This article provides an overview of the nature and role of autonomy for space exploration, with a bias in focus towards describing the relevance of AI technologies. It explores the range of autonomous behavior that is relevant and useful in space exploration and illustrates the range of possible behaviors by presenting four case studies in space-exploration systems, each differing from the others in the degree of autonomy exemplified. Three core requirements are defined for autonomous space systems, and the architectures for integrating capabilities into an autonomous system are described. The article concludes with a discussion of the challenges that are faced currently in developing and deploying autonomy technologies for space. As NASA and other space agencies around the world formulate and deploy missions to return to the moon and explore Mars and beyond, the realization is emerging that smarter mobile systems that are themselves instruments of knowledge and understanding must be ...

A principal one among them is the existence of multiple domains that share the same underlying causal structure for actions. We describe an approach that exploits this shared causal structure to discover a hierarchical task structure in a source domain, which in turn speeds up learning of task execution knowledge in a new target domain. Our approach is theoretically justified and compares favorably to manually designed task hierarchies in learning efficiency in the target domain. We demonstrate that causally motivated task hierarchies transfer more robustly than other kinds of detailed knowledge that depend on the idiosyncrasies of the source domain and are hence less transferable. These domains are complex, and good performance requires selecting long chains of actions to achieve subgoals needed for ultimate success.

The DSE provides core automation functionality for scheduling the network, including the interpretation of scheduling requirements expressed by users, their elaboration into tracking passes, and the resolution of conflicts and constraint violations. The DSE incorporates both systematic search-and repairbased algorithms, used for different phases and purposes in the overall system. It has been integrated with a web application that provides DSE functionality to all DSN users through a standard web browser, as part of a peer-to-peer schedule negotiation process for the entire network. The system has been deployed operationally and is in routine use, and is in the process of being extended to support long-range planning and forecasting and near real-time scheduling. ASA's Deep Space Network (DSN) provides communications and other services for planetary exploration missions as well as other missions beyond geostationary orbit, supporting both NASA and international users.

Assembly plays a fundamental role in the manufacturing of most products. Parts that have been individually formed or machined to meet designed specifications are assembled into a configuration that achieves the functions of the final product or mechanism. The economic importance of assembly as a manufacturing process has led to extensive efforts to improve the efficiency and cost effectiveness of assembly operations. The sequence of mating operations that can be carried out to assemble a group of parts is constrained by the geometric and mechanical properties of the parts, their assembled configuration, and the stability of the resulting subassemblies. An approach to representation and reasoning about these sequences is described here and leads to several alternative explicit and implicit plan representations.

This path, however, is typically not a shortest path in the continuous terrain. In this overview article, we discuss a path-planning methodology for quickly finding paths in continuous terrain that are typically shorter than shortest grid paths. Anyangle path-planning algorithms are variants of the heuristic path-planning algorithm A* that find short paths by propagating information along grid edges (like A*, to be fast) without constraining the resulting paths to grid edges (unlike A*, to find short paths). In robotics and video games, (continuous) terrain is often discretized into grids with blocked and unblocked grid cells and from there into grid graphs (Tozour 2004; Rabin 2000; Chrpa and Komenda 2011; Björnsson et al. 2003; Nash 2012). Our objective is to find short unblocked paths from given start vertices to given goal vertices.

Recent developments have clarified the process of generating partially ordered, partially specified sequences of actions whose execution will achieve an agent's goal. Thus, it should be no surprise that the quest of building intelligent agents has forced AI researchers to investigate algorithms for generating appropriate actions in a timely fashion. Of course, the problem is not yet solved, but considerable progress has been made. In particular, AI researchers have developed two complementary approaches to the problem of generating these actions: (1) planning and (2) situated action. These two techniques have different strengths and weaknesses, as I illustrate later.

Khosrow Hadavi, Wen-Ling Hsu, Tony Chen, and Cheoung-Nam Lee Industrial managers, engineers, and technologists have many expectations from artificial intelligence and its application to knowledge-based systems. Although the past decade has witnessed a number of innovative applications of AI in manufacturing, the field is still in its infancy and holds even greater promise for the future. The AAAI Press book Artificial Intelligence Applications in Manufacturing, (from which the following article was selected) presents a number of articles that relate to the enhancement of planning and decision making capabilities in today's automated production environments. Scheduling problems can generally be described as allocating resources to tasks while satisfying a set of constraints (Baker 1974; Conway et al. 1967). More often than not, the constraint sets are large and diverse, the objectives conflict with each other, and the scheduling problems quickly become NPhard.

Satellite domains are becoming a fashionable area of research within the AI community due to the complexity of the problems that satellite domains need to solve. With the current U.S. and European focus on launching satellites for communication, broadcasting, or localization tasks, among others, the automatic control of these machines becomes an important problem. Many new techniques in both the planning and scheduling fields have been applied successfully, but still much work is left to be done for reliable autonomous architectures. The purpose of this article is to present CONSAT, a real application that plans and schedules the performance of nominal operations in four satellites during the course of a year for a commercial Spanish satellite company, HISPASAT. For this task, we have used an AI domain-independent planner that solves the planning and scheduling problems in the HISPASAT domain thanks to its capability of representing and handling continuous variables, coding functions to obtain the operators' variable values, and the use of control rules to prune the search.

This planning graph structure is then fed to a heuristic extractor module that is capable of extracting a variety of effective and admissible heuristics, based on our recent theory (Nguyen and Kambhampati 2000). This heuristic, along with the problem specification, and the set of ground actions in the final action level of the planning graph structure are fed to a regression state search planner. To guide a regression search in the state space, a heuristic function needs to evaluate the cost of some set S of subgoals, comprising a regression state from the initial state, in terms of the number of actions required to achieve S from the initial state. This heuristic approximates the cost of a set S as the length of a "relaxed plan" for supporting S, ignoring all the mutex relations, plus the penalty for ignoring these negative interac-88 AI MAGAZINE Yochan is the planning group directed by Subbarao Kambhampati at Arizona State University.

The planning competition has become a regular part of the biennial Artificial Intelligence Planning and Scheduling (AIPS) conferences. AIPS'98 featured the very first competition, and for AIPS'00, we built on this foundation to run the second competition. The 2000 competition featured a much larger group of participants and a wide variety of different approaches to planning. Some of these approaches were refinements of known techniques, and others were quite different from anything that had been tried before. Besides the dramatic increase in participation, the 2000 competition demonstrated that planning technology has taken a giant leap forward in performance since 1998.