IROS 2017 Workshop
As humans, understanding our own limitations, failures and shortcomings is a key for improvement and development. Correspondingly, equipping robots with a set of skills that allows them to assess the quality of their sensory data, internal models, used methods and state of the hardware is expected to greatly improve the overall performance of an autonomous system.
The aim of this workshop is to discuss the following research question:
In other words, how to improve robots' introspective abilities?
Research on introspection directly or indirectly relates to other research topics such as safety, active perception and mapping. Accordingly, development of introspection in robotics is expected to have a direct impact on a large variety of application areas (most notably service robots in long-term operation, and search and rescue robots).
Introspection has a number of benefits for robotics: (i) can be used to estimate the likelihood of failure and prevent the failure, (ii) improves safety by assessing the internal state of the robot, (iii) can speed up the recovery and/or repair process by providing detailed information to a human operator or be a part of self-repair process, (iv) it is crucial to make decisions if it is safe to execute the assigned mission.
Unpublished original contributions may be submitted to the workshop. The criteria for acceptance is the work's relation to the topics of the workshop and technical quality. We also encourage submission of position papers that address the challenge(s) of introspection methods for reliable autonomy.
Papers can be submitted until the submission deadline via EasyChair. Submissions, to be uploaded as a PDF file, should be no longer than eight pages, including references. Papers should be formatted with the IEEE Conference Latex or Word style. All papers will go through a single-blind peer review with at least two reviewers. Accepted papers will be published on the workshop website.