Heuristic Planning for Space Missions

Dear Colleagues, 

Autonomous planning is one of the primary research interests in the field of artificial intelligence. A variety of methods have been proposed to solve classical planning problems, such as the coloring problem and the air cargo transportation problem, including forward state space search, graph planning, hierarchical task network planning, etc. Autonomous planning methods have greatly increased the effectiveness of solving planning problems and promoted the application of planning technology.

In a classical planning task with the search space of transforming an initial world state into a goal-satisfying state, one common means of reaching a solution is to use the heuristic search method. For the candidate nodes in the search space, the heuristic evaluation strategy can provide certain rules with which to calculate the cost of the nodes based on the target set of the planning problem. Thus enables the planner to eliminate the interference of irrelevant nodes during the search process and select the appropriate action or state to speed up the solution of the planning problem. There are two important branches in the study of heuristic evaluation strategies in classical planning: delete relaxation and landmark heuristics.

However, traditional planning methods struggle to deal with spacecraft planning problems that have complex constraints such as time, resources, and other parameters. The space powers have carried out a wealth of studies on autonomous and heuristic planning technology.

Autonomous planning technology was first applied and verified in space exploration missions in the 1990s. In the initial applications, only part of the onboard system operated with autonomy, which reduced the mission operations conducted by ground personnel. The whole-spacecraft autonomy was verified by Deep Space One, with the developed remote agent software system implementing the probe's autonomous task management, mission planning, autonomous execution, condition monitoring, etc. At present, NASA’s Automated Scheduling and Planning Environment system (ASPEN), Extensible Universal Remote Operations Planning Architecture (EUROPA) and ESA’s Advanced Planning and Scheduling Initiative (APSI) have successively served in Earth Observing One and various Mars rover missions.

Due to the complexity of spacecraft systems, complicated constraints, concurrent activities, and uncertain environments, traditional planning techniques are no longer applicable to state-of-the-art space missions. The autonomous planning of space applications faces new challenges, including the following:

1. Complicated temporal constraints. Most activities must be performed in a specific time window. For example, communication activities must be performed in a certain order, whereas some activities need to be performed in parallel.
2. Limited resources. The energy and storage capacity of spacecraft is limited, and the resources need to be managed and allocated for use within a certain time interval to ensure the safe operation of the spacecraft and the completion of the mission.
3. Complex mission objectives. There are many goals that need to be achieved with different values, and reasonable arrangements should be made to obtain the greatest scientific return. At the same time, some planning tasks must be used to find the shortest path timewise or in length, while others require the least fuel consumption to achieve the goal.
4. Execution uncertainty. There is uncertainty about when to move to a designated location, complete a maintenance operation, or assemble a structure.

To summarize, the research on the autonomous and heuristic planning technology of space applications has the following significance for future space missions:

1. Reduce ground intervention and reduce spacecraft operating costs and demand for space telemetry networks;
2. Respond to the uncertainty in space missions and increase the reliability of mission execution;
3. Adopt advanced mission instructions to enhance the interactivity of ground and spacecraft systems;
4. Efficient allocation and utilization of various resources of the system for better return of the tasks;
5. The planning system can be flexibly applied to the design and development of future spacecraft, shortening the development cycle of small spacecraft. 

This Special Issue solicits works in areas of interests that include, but are not limited to, the following:

• Multi-agent heuristic planning;
• Moon/Mars/asteroid landing sequence planning;
• Satellite observing/communication planning and scheduling;
• Spacecraft payload operation planning;
• Space station operation and management planning;
• Spacecraft attitude maneuver planning;
• Rover path planning;
• Lander trajectory planning;
• Autonomous planning applications on space missions.

Prof. Dr. Rui Xu
Prof. Dr. Shengying Zhu
Dr. Zhaoyu Li
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Aerospace is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.