Nicola Muscettola

Remote Agent: to boldly go where no AI system has gone before

Abstract Renewed motives for space exploration have inspired NASA to work toward the goal of establishing a virtual presence in space, through heterogeneous fleets of robotic explorers. Information technology, and Artificial Intelligence in particular, will play a central role in this endeavor by endowing these explorers with a form of computational intelligence that we call remote agents . In this paper we describe the Remote Agent, a specific autonomous agent architecture based on the principles of model-based programming, on-board deduction and search, and goal-directed closed-loop commanding, that takes a significant step toward enabling this future. This architecture addresses the unique characteristics of the spacecraft domain that require highly reliable autonomous operations over long periods of time with tight deadlines, resource constraints, and concurrent activity among tightly coupled subsystems. The Remote Agent integrates constraintbased temporal planning and scheduling, robust multi-threaded execution, and model-based mode identification and reconfiguration. The demonstration of the integrated system as an on-board controller for Deep Space One, NASAs first New Millennium mission, is scheduled for a period of a week in mid 1999. The development of the Remote Agent also provided the opportunity to reassess some of AIs conventional wisdom about the challenges of implementing embedded systems, tractable reasoning, and knowledge representation. We discuss these issues, and our often contrary experiences, throughout the paper.

An autonomous spacecraft agent prototype

This paper describes the New Millennium Remote Agent (NMRA) architecture for autonomous spacecraft control systems. The architecture supports challenging requirements of the autonomous spacecraft domain not usually addressed in mobile robot architectures, including highly reliable autonomous operations over extended time periods in the presence of tight resource constraints, hard deadlines, limited observability, and concurrent activity. A hybrid architecture, NMRA integrates traditional real-time monitoring and control with heterogeneous components for constraint-based planning and scheduling, robust multi-threaded execution, and model-based diagnosis and reconfiguration. Novel features of this integrated architecture include support for robust closed-loop generation and execution of concurrent temporal plans and a hybrid procedural/deductive executive.

On-board planning for New Millennium Deep Space One autonomy

The Deep Space One (DS1) mission, scheduled to fly in 1998, will be the first NASA spacecraft to feature an on-board planner. The planner is part of an artificial intelligence based control architecture that comprises the planner/scheduler, a plan execution engine, and a model-based fault diagnosis and reconfiguration engine. This autonomy architecture reduces mission costs and increases mission quality by enabling high-level commanding, robust fault responses, and opportunistic responses to serendipitous events. This paper describes the on-board planning and scheduling component of the DS1 autonomy architecture.

Scheduling by iterative partition of bottleneck conflicts

The author describes conflict partition scheduling (CPS), a novel methodology that constructs solutions to scheduling problems by repeatedly identifying bottleneck conflicts and posting constraints to resolve them. The identification of bottleneck conflicts is based on a capacity analysis using a stochastic simulation methodology. Once a conflict is identified, CPS does not attempt to resolve it completely; instead it introduces constraints that merely decrease its criticality. By reducing the amount by which each scheduling decision prunes the search space, CPS tries to minimize the chance of getting lost in blind alleys. The effectiveness of CPS was demonstrated by an experimental analysis that compared CPS to two current scheduling methods: micro-opportunistic constraint-directed search and min-conflict iterative repair. CPS is shown to perform better than both on a standard benchmark of constraint satisfaction scheduling problems.<<ETX>>

Issues in temporal reasoning for autonomous control systems

Deep Space One will be the rst spacecraft to be controlled by an autonomous agent poten tially capable of carrying out a complete mission with minimal commanding from Earth The New Millennium Remote Agent NMRA includes a planner scheduler that produces plans and an executive that carries them out In this paper we discuss several issues arising at the interface between planning and execution including exe cution latency plan dispatchability and the dis tinction between controllable and uncontrollable events Temporal information in the plan is rep resented within the general framework of Simple Temporal Constraint networks as introduced by Dechter Meiri and Pearl However the execu tion requirements have a substantial impact on the topology of the links and the propagation through the network

Automated planning and scheduling for goal-based autonomous spacecraft

Automated planning and scheduling technology enables a new class of autonomous spacecraft. We describe our use of symbolic AI in planning systems, provide an overview of the spacecraft-operations domain, and discuss several past, ongoing, and future deployments of planning systems technology at NASA.

Coordinating space telescope operations in an integrated planning and scheduling architecture

The heuristic scheduling testbed system (HSTS), a software architecture for integrated planning and scheduling, is discussed. The architecture has been applied to the problem of generating observation schedules for the Hubble Space Telescope. This problem is representative of the class of problems that can be addressed: their complexity lies in the interaction of resource allocation and auxiliary task expansion. The architecture deals with this interaction by viewing planning and scheduling as two complementary aspects of the more general process of constructing behaviors of a dynamical system. The principal components of the software architecture are described, indicating how to model the structure and dynamics of a system, how to represent schedules at multiple levels of abstraction in the temporal database and how the problem solving machinery operates. A scheduler for the detailed management of Hubble Space Telescope operations that has been developed within HSTS is described. Experimental performance results are given that indicate the utility and practicality of the approach. >

OPIS: an opportunistic factory scheduling system

In this paper, we describe a knowledge-based system for factory scheduling that dynamically focuses its decision-making according to characteristics of current solution constraints. Both problem decomposition and subproblem solution rely on knowledge of the time and resource capacity constraints that are imposed by the current factory state and the scheduling decisions that have already been made. The architecture of the system derives from standard blackboard style architectures and similarly assumes an organization comprised of a number of knowledge sources that extend, revise and analyze the global factory schedule.

Mapping temporal planning constraints into timed automata

Planning and model checking are similar in concept. They both deal with reaching a goal state from an initial state by applying specified rules that allow for the transition from one state to another. Exploring the relationship between them is an interesting new research area. We are interested in planning frameworks that combine both planning and scheduling. For that, we focus our attention on real time model checking. As a first step, we developed a mapping from planning domain models into timed automata. Since timed automata are the representation structure of real-time model checkers, we are able to exploit what model checking has to offer for planning domains. We present the mapping algorithm, which involves translating temporal specifications into timed automata, and list some of the planning domain questions someone can answer by using model checking.

Mission operations with an autonomous agent

The Remote Agent (RA) is an Artificial Intelligence (AI) system which automates some of the tasks normally reserved for human mission operators and performs these tasks autonomously on-board the spacecraft. These tasks include activity generation, sequencing, spacecraft analysis, and failure recovery. The RA will be demonstrated as a flight experiment on Deep Space One (DS1), the first deep space mission of the NASAs New Millennium Program (NMP). As we moved from prototyping into actual flight code development and teamed with ground operators, we made several major extensions to the RA architecture to address the broader operational context in which RA would be used. These extensions support ground operators and the RA sharing a long-range mission profile with facilities for asynchronous ground updates; support ground operators monitoring and commanding the spacecraft at multiple levels of detail simultaneously; and enable ground operators to provide additional knowledge to the RA, such as parameter updates, model updates, and diagnostic information, without interfering with the activities of the RA or leaving the system in an inconsistent state. The resulting architecture supports incremental autonomy, in which a basic agent can be delivered early and then used in an increasingly autonomous manner over the lifetime of the mission. It also supports variable autonomy, as it enables ground operators to benefit from autonomy when they want it, but does not inhibit them from obtaining a detailed understanding and exercising tighter control when necessary. These issues are critical to the successful development and operation of autonomous spacecraft.