The ICML 2003 workshop on Machine Learning Technologies for Autonomous Space Applications welcomes contributions from researchers and practitioners in machine learning, space science, and mission planning. This workshop aims to bring together those interested in developing novel machine learning algorithms for autonomous spacecraft with those concerned with misson safety, performance, and engineering constraints to bridge the "applicability divide". The workshop will provide a context for mission engineers and scientists to present their "wish lists" and real-world constraints to machine learning researchers and for ML scientists to present pertinent, cutting-edge technologies. The ultimate goal is to foster research and development leading to the application of machine learning methods on real, flown spacecraft.
Many of the significant advances of the machine learning community have come from tackling challenging, real world problems of large practical and economic importance. The application of ML techniques has often produced substantial savings in human time, energy, and money. The inherent flexibility in ML techniques is particularly relevant for space missions, where multi-million dollar hardware must operate without a human overseer, in sometimes unforeseeable situations.
Space environments impose several stringent resource and time constraints. Remote space missions must cope with very limited bandwidth and, often, response time delays too large to allow direct human teleoperation. Currently, limited bandwidth is often dealt with by shutting down science instruments entirely until the current batch of data has been downlinked. Likewise, if a pre-loaded command sequence fails for some reason, a remote rover is often programmed to shut down and sit idle until the next direct Earth communications opportunity.
In contrast, methods designed to intelligently filter observations, compress redundant information, and devote more time and bandwidth to novel, unusual events, could greatly enhance the efficiency and science return of such missions. Reinforcement learning and other techniques could be useful for adapting to changing environments, adjusting science objectives, making navigational decisions, and generally enhancing the autonomy of our remote, robotic delegates.
Despite progress in developing applicable ML techniques, adoption and integration into fielded remote space missions remains a challenge. Scientists and mission PIs are reluctant to entrust critical mission components, such as science target identification and vehicle control, to methods that take decision making out of human hands. Similar concerns arise in any situation where failure brings with it an unacceptably high cost. This hesitation, while understandable, is at odds with our desire to overcome the sometimes formidable communication delays, to make the best use of severely limited bandwidth, and to improve the science return of such missions.
In recognition of the gap between the development of ML methods and their adoption in fielded space systems, we convene this workshop as a forum where we can address the following critical questions:
We are interested in discussing both social and political barriers to adoption of ML methods in space applications, and technological solutions that would help erode those barriers. We will also welcome contributions from the entire spectrum of associated fundamental, methodological, and practical research.
Because we wish to encourage discussion and maintain a small group atmosphere, attendance will be limited to invitation only. We welcome your innovative, controversial, yet well reasoned ideas. We want to spark productive debates. Those wishing to participate in this workshop should submit one (or more) of the following:
For those not wishing to contribute a technical paper, there is also a fourth option:
In addition, submitting authors must include (as a separate file), up to 500 words of ASCII text describing their biography, relevant experience, and contact information. The purpose of these biographies is to assist attendees in getting to know others with relevant or complementary interests. They will appear in the published workshop notes. We ask that authors not include lists of publications, but we will be happy to accept URLs pointing to personal research pages.
All technical submissions (categories 1-3, above) should be in PDF or PostScript format and should employ the same formatting conventions specified by the ICML conference. Submissions of interest (category 4) do not have a required format (as they will not appear in the proceedings), but we do request that you submit them in PostScript, PDF, or ASCII text. Biographies do not require any special templates or formatting but must be in ASCII text and adhere to the 500 word limit.
Submissions should be by email and must identify which option they are submitting under (#1, #2, #3, or #4) in the subject line. For example, "Subject: ML in Space Workshop Submission type #3". Attach your .ps or .pdf submission, along with your text biography, and email to firstname.lastname@example.org. If you intend to submit more than one paper, please send them in separate emails.
Submissions that do not adhere to these guidelines may be returned unread.
Accepted submissions will be published in a bound proceedings provided to workshop attendees and will also be available online at the workshop website.
Last changed Tue, Aug 12, 2003 20:46:33 .
Last changed Tue, Aug 12, 2003 20:46:33 .