Russell Knight

Integrated planning and execution for autonomous spacecraft

An autonomous spacecraft must balance long-term and short-term considerations. It must perform purposeful activities that ensure long-term science and engineering goals are achieved and ensure that it maintains positive resource margins. This requires planning in advance to avoid a series of shortsighted decisions that can lead to failure. However, it must also respond in a timely fashion to a somewhat dynamic and unpredictable environment. Thus, in terms of high-level, goal-oriented activity, spacecraft plans must often be modified due to fortuitous events such as early completion of observations and setbacks such as failure to acquire a guidestar for a science observation. This paper describes an integrated planning and execution architecture that supports continuous modification and updating of a current working plan in light of changing operating context.

The Techsat-21 autonomous space science agent

The Autonomous Sciencecraft Experiment (ASE) will fly onboard the Air Force TechSat-21 constellation of three spacecraft scheduled for launch in 2004. ASE uses onboard continuous planning, robust task and goal-based execution, model-based mode identification and reconfiguration, and onboard machine learning and pattern recognition to radically increase science return by enabling intelligent downlink selection and autonomous retargeting. In this paper we discuss how these AI technologies are synergistically integrated in a hybrid multi-layer control architecture to enable a virtual spacecraft science agent. We also describe our working software prototype and preparations for flight.

A planning approach to monitor and control for deep space communications

In recent years with the large increase in the number of space missions at NASA and JPL (Jet Propulsion Laboratory), the demand for deep space communications services to command and collect data from these missions has become more difficult to manage. In an attempt to increase the efficiency of operating deep space communications antennas, we are developing a prototype system to perform monitor, control, execution and recovery in order to automate the operations of the Deep Space Network (DSN) communication antenna stations. The authors describe the antenna automation problem, the GASPER planning and scheduling system, how GASPER is used to generate antenna track plans and perform monitor and control during execution, and future work utilizing dynamic planning technology.

Balancing deliberation and reaction, planning and execution for space robotic applications

Intelligent behavior for robotic agents requires a careful balance of fast reactions and deliberate consideration of long-term ramifications. The need for this balance is particularly acute in space applications, where hostile environments demand fast reactions, and remote locations dictate careful management of consumables that cannot be replenished. However, fast reactions typically require procedural representations with limited scope and handling long-term considerations in a general fashion is often computationally expensive. We describe three major areas for autonomous systems for space exploration: free-flying spacecraft, planetary rovers, and ground communications stations. In each of these broad applications areas, we identify operational considerations requiring rapid response and considerations of long-term ramifications. We describe these issues in the context of ongoing efforts to deploy autonomous systems using planning and task execution systems.

An Empirical Evaluation of the Effectiveness of Local Search for Replanning

Local search has been proposed as a means of responding to changes in problem context requiring replanning. Iterative repair and iterative improvement have desirable properties of preference for plan stability (e.g., non-disruption, minimizing change), and have performed well in a number of practical applications. However, there has been little real empirical evidence to support this case. This paper focuses on the use of local search to support a continuous planning process (e.g., continuously replanning to account for problem changes) as is appropriate for autonomous spacecraft control. We describe results from ongoing empirical tests using the CASPER system to evaluate the effectiveness of local search to replanning using a number of spacecraft scenario simulations including landed operations on a comet and rover operations.

Leveraging Multiple Artificial Intelligence Techniques to Improve the Responsiveness in Operations Planning: ASPEN for Orbital Express

The challenging timeline for DARPA’s Orbital Express mission demanded a flexible, responsive, and (above all) safe approach to mission planning. Mission planning for space is challenging because of the mixture of goals and constraints. Every space mission tries to squeeze all of the capacity possible out of the spacecraft. For Orbital Express, this means performing as many experiments as possible, while still keeping the spacecraft safe. Keeping the spacecraft safe can be very challenging because we need to maintain the correct thermal environment (or batteries might freeze), we need to avoid pointing cameras and sensitive sensors at the sun, we need to keep the spacecraft batteries charged, and we need to keep the two spacecraft from colliding... made more difficult as only one of the spacecraft had thrusters. Because the mission was a technology demonstration, pertinent planning information was learned during actual mission execution. For example, we didn’t know for certain how long it would take to transfer propellant from one spacecraft to the other, although this was a primary mission goal. The only way to find out was to perform the task and monitor how long it actually took. This information led to amendments to procedures, which led to changes in the mission plan. In general, we used the ASPEN planner scheduler to generate and validate the mission plans. ASPEN is a planning system that allows us to enter all of the spacecraft constraints, the resources, the communications windows, and our objectives. ASPEN then could automatically plan our day. We enhanced ASPEN to enable it to reason about uncertainty. We also developed a model generator that would read the text of a procedure and translate it into an ASPEN model. Note that a model is the input to ASPEN that describes constraints, resources, and activities. These technologies had a significant impact on the success of the Orbital Express mission. Finally, we formulated a technique for converting procedural information to declarative information by transforming procedures into models of hierarchical task networks (HTNs). The impact of this effort on the mission was a significant reduction in (1) the execution time of the mission, (2) the daily staff required to produce plans, and (3) planning errors. Not a single miss-configured command was sent during operations.

Onboard autonomy software on the Three Corner Sat mission

Three Corner Sat (3CS) is a mission of 3 university nanosatellites scheduled for launch in late 2002. The 3CS mission will utilize significant autonomy to improve mission robustness and science return. The 3CS mission will use onboard science data validation, responsive replanning, robust execution, and anomaly detection based on multiple models. Flight of these revolutionary technologies will enable new opportunities in space-borne science and space exploration.

Enabling onboard spacecraft autonomy though goal-based architectures: an integration of model-based artificial intelligence planning with procedural elaboration

This paper describes the integration of a model-based planner into a procedural architecture. This architecture is unusual in that the internal procedures and the planners inter-operate in an asynchronous fashion in a multithreaded environment via a goal-based interface. The submission of goals may trigger either internal procedures or planners, and both internal procedures and planners may submit goals. The procedural architecture described is the Mission Data System (MDS) Goal Achieving Module (GAM) architecture. The planner described is the CASPER (Continuous Activity Scheduling Planning Execution and Replanning) system. This approach has been prototyped and tested against virtual spacecraft and comet-lander operation scenarios and simulations.

Board-Laying Techniques Improve Local Search in Mixed Planning and Scheduling

When searching the space of possible plans for combined planning and scheduling problems we often reach a local maximum and find it difficult to make further progress. To help move out of a local maximum, we can often make large steps in the search space by aggregating constraints. Our techniques improve the performance of our plannerlscheduler on real problems.

Studying mountain glacier processes using a staring instrument

Mountain glaciers around the globe are retreating rapidly, but the exact mechanisms causing the retreat are not well understood. Is warming of the atmosphere the key driver? What are the roles of changes in surface albedo due to contaminants and snow optical grain size and surface roughness? Improved understanding of the response of mountain glaciers to global and environmental change is key to answering these questions. A staring instrument that provides measurements from multiple viewing and illumination angles enables simultaneous measurement of 3D surface structure, including texture, material characteristics, and albedo. Such measurements make it possible to determine melt due to absorbed solar energy separately from melt due to other sources. The International Space Station (ISS) provides a possible host platform for a staring instrument that could access all tropical and most temperate mountain glaciers. The non-sun-synchronous orbit enables varying solar illumination angles.