Ari K. Jónsson

Constraint-Based Attribute and Interval Planning

In this paper we describe Constraint-based Attribute and Interval Planning (CAIP), a paradigm for representing and reasoning about plans. The paradigm enables the description of planning domains with time, resources, concurrent activities, mutual exclusions among sets of activities, disjunctive preconditions and conditional effects. We provide a theoretical foundation for the paradigm, based on temporal intervals and attributes. We show how the plans are naturally expressed by networks of constraints, and show that the process of planning maps directly to dynamic constraint reasoning. We describe compatibilities, a compact mechanism for describing planning domains. We also demonstrate how this framework incorporates the use of constraint representation and reasoning technology to improve planning. Finally, we describe EUROPA, an implementation of the CAIP framework.

MAPGEN: mixed-initiative planning and scheduling for the Mars Exploration Rover mission

The Mars Exploration Rover mission is one of NASAs most ambitious science missions to date. Launched in the summer of 2003, each rover carries instruments for conducting remote and in site observations to elucidate the planets past climate, water activity, and habitability. Science is MERs primary driver, so making best use of the scientific instruments, within the available resources, is a crucial aspect of the mission. To address this criticality, the MER project team selected MAPGEN (mixed initiative activity plan generator) as an activity-planning tool. MAPGEN combines two existing systems, each with a strong heritage: the APGEN activity-planning tool from the Jet Propulsion Laboratory and the Europa planning and scheduling system from NASA Ames Research Center. We discuss the issues arising from combining these tools in this missions context. MAPGEN is the first AI-based system to control a space platform on another planets surface.

Universal Executive and PLEXIL: Engine and Language for Robust Spacecraft Control and Operations

This paper presents an execution engine and the associated execution language for spacecraft operations. The software tool highlighted is the Universal Executive execution system and the language is PLEXIL. PLEXIL is a lightweight, well-defined, predictable, and verifiable language capable of expressing spacecraft control concepts used by human operators and many high-level automated planners. The Universal Executive is a lightweight execution system that can autonomously execute PLEXIL plans on spacecraft, robots, instruments, and habitats. The Universal Executive and PLEXIL allow variable levels of autonomy and co-ordination with various other spacecraft systems, and human operators.

Verification of autonomous systems for space applications

Autonomous software, especially if it is based on model, can play an important role in future space applications. For example, it can help streamline ground operations, or, assist in autonomous rendezvous and docking operations, or even, help recover from problems (e.g., planners can be used to explore the space of recovery actions for a power subsystem and implement a solution without (or with minimal) human intervention). In general, the exploration capabilities of model-based systems give them great flexibility. Unfortunately, it also makes them unpredictable to our human eyes, both in terms of their execution and their verification. The traditional verification techniques are inadequate for these systems since they are mostly based on testing, which implies a very limited exploration of their behavioral space. In our work, we explore how advanced V&V techniques, such as static analysis, model checking, and compositional verification, can be used to gain trust in model-based systems. We also describe how synthesis can be used in the context of system reconfiguration and in the context of verification

The Future of AI in Space

Casual observers of NASA spacecraft, systems, and missions might assume that artificial intelligence has long been integral to what NASA does. However, the reality of high-stakes space missions must balance bold concepts with careful engineering, especially risk management. New capabilities, whether based on AI or other technologies, are adopted only when they offer overwhelming benefits to a mission. Even then, a new capabilitys risks must be well understood and aggressively retired. And yet, space exploration, whether by robotic spacecraft or astronauts, is not for the faint of heart or vision. Since 1998, when we initiated this department via a special issue, AI has made steady progress in the space realm. In particular, two successful flight-technology experiments-the Remote Agent Experiment (RAX) in 1999, and the Autonomous Sciencecraft Experiment (ASE), deployed in 2003 and still functioning on the Earth Observing One (EO-1) platform-validated appropriate uses of AI-based capabilities in future robotic missions. These capabilities also support NASAs renewed emphasis on robotic and human exploration of the Moon, Mars, and beyond

On Reformulating Planning as Dynamic Constraint Satisfaction

In recent years, researchers have reformulated STRIPS planning problems as SAT problems or CSPs. In this paper, we discuss the Constraint-Based Interval Planning (CBIP) paradigm, which can represent planning problems incorporating interval time and resources. We describe how to reformulate mutual exclusion constraints for a CBIP-based system, the Extendible Uniform Remote Operations Planner Architecture (EUROPA). We show that reformulations involving dynamic variable domains restrict the algorithms which can be used to solve the resulting DCSP. We present an alternative formulation which does not employ dynamic domains, and describe the relative merits of the different reformulations.

Autonomy in Space Exploration: Current Capabilities and Future Challenges

Deep space exploration requires vehicles with appropriate autonomous capabilities. In order to accomplish their missions, spacecraft need to respond to potential hazards while seeking to expand human knowledge of deep space. This paper provides an overview of the role of autonomy for space exploration. First, we explore the range of autonomous behavior that is useful in space exploration. Second, three core requirements are defined for autonomous space systems. Fourth, we identify the decision-making capabilities that will ensure the effectiveness and safety of autonomous systems. Fifth, we describe architectures for integrating capabilities into an autonomous system. Finally, we discuss the challenges that are faced currently in developing and deploying autonomy technologies for space.

Autonomy in Space: Current Capabilities and Future Challenge

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.

Simulation-based planning for planetary rover experiments

Time and resource limitations mean that current Mars rovers (and any future planetary rovers) cannot hope to achieve every desirable scientific goal. We must therefore select and plan for a subset of the possible experiments, maximizing some utility metric. The use of simulation in planning is appealing because of its potential for representing complex, realistic details about the rover and its environment. We demonstrate a planning algorithm that performs high-level planning in a space of plan strategies, rather than actual plans. In the current implementation, candidate strategies are evaluated by a simple simulation, and a genetic algorithm is to search for effective strategies. Preliminary results are encouraging, particularly the potential for modeling uncertainty about the time required to complete actions, and the ability to develop strategies that can deal with this uncertainty gracefully

Challenges in verification and validation of autonomous systems for space exploration

Space exploration applications offer a unique opportunity for the development and deployment of autonomous systems, due to limited communications, large distances, and great expense of direct operation. At the same time, the risk and cost of space missions leads to reluctance to taking on new, complex and difficult-to-understand technology. A key issue in addressing these concerns is the validation of autonomous systems. In recent years, higher-level autonomous systems have been applied in space applications. In this presentation, we highlight those autonomous systems, and discuss issues in validating these systems. We then look to future demands on validating autonomous systems for space, identify promising technologies and open issues.