AIS'09

The IJCAI-09/SMC-IT-09/IWPSS-09 Workshop on Artificial Intelligence in Space

held in coordination with the International Joint Conference on Artificial Intelligence (IJCAI-09), the 3rd IEEE International Conference on Space Mission Challenges for Information Technology (SMC-IT-09), and the 6th International Workshop on Planning and Scheduling for Space (IWPSS-09)

In order to briefly summarize the up-to-date contributions from different fields of AI to space science and applications, to indicate how recent AI findings can be utilized and to identify new areas of AI which could be of use in space science and research, the Advanced Concepts Team of the European Space Agency and the Artificial Intelligence Group of the Jet Propulsion Laboratory of the National Aeronautics and Space Administration will be organising a workshop on Artificial Intelligence in Space in coordination with IJCAI-09, SMC-IT-09, and IWPSS-09, in Pasadena, California, on July 17-18, 2009.

Intelligent machines, programs, or agents, are systems that adapt, learn or perceive their environment and take actions which maximize their chances of success. The design of intelligent systems for operation in known and predictable environments or under a well-defined set of conditions is a demanding task that has been widely addressed in the past decades. However, existing machine intelligence has not been extensively tried and tested in highly unpredictable and hazardous environments, as space. Arguably, successful operation in space is a far more challenging endeavour than operation in, e.g., controlled robotic arenas. Similarly, space applications may need novel programming paradigms, far more flexible and adaptive than conventional computing.

Two keywords in our quest for designing artificially intelligent entities are autonomy and adaptivity. Spacecrafts, satellites, rovers and other machines need to be able to autonomously make decisions, to quickly process and categorise vast amounts of incoming data, monitor their health status, detect and self-heal faults. Machines need to learn to adapt fast to growing user demands, to interact in more complex ways with other machines and humans, and new algorithms need to emerge to tackle the complexity of real-world problems. The research field of Artificial Intelligence with its many flavours can significantly contribute to this goal. From solutions inspired by the behaviour of social animals, to imitating how the human brain functions during decision-making; from robust optimisation algorithms to natural language interfaces for human-computer interactions; from efficient control algorithms to data mining and knowledge discovery, advances in AI research can be applied to space related problems.