Mailing list for continued discussion.
To join, send a message to email@example.com with the body
Many of the significant advances of the machine learning community have come
from tackling challenging, real world problems of practical and economic
importance. Of particular interest are space exploration missions where robots
must operate autonomously in unknown environments. The robots need to
maintain their safety while still exploring the region and accomplishing the
overall objectives of the mission. Machine learning methods are ideal to assist
the robots in these goals by intelligently filtering observations, learning to
identify novel experiences, and knowing when the robot needs to call for human
help versus when it can solve the issue itself.
This workshop focused on the following critical questions:
How can we design algorithms that can train for a long time
under controlled situations, but must work almost perfectly in a remote,
How can ML techniques be tested so as to convince someone
outside the field that they are reliable, robust, and effective for real space
systems? What are the best analogue problems and situations, here on Earth, for
the development and study of applicable ML techniques?
Are there specific, possibly novel, metrics and methodologies
for evaluation that would be most appropriate for these problems?
What ML algorithms drawn from other domains (e.g., tasks with a
high cost of failure) are applicable to the problems faced by fielded space
Can we provide formal performance guarantees for ML algorithms
in the constrained and sometimes hostile environments in which remote space
systems will exist?
How can we strengthen connections between ML researchers and
the people making operational decisions for space missions?