Overview

Robots have long been imagined as mechanical workers, operating alongside us in our daily lives. However, if robots are to leave the confines of highly structured laboratory environments, and succeed at unstructured, everyday tasks, they will require substantial intelligence and dexterity. The problem of designing complete, intelligent robotic systems presents us with the opportunity to develop fully fledged agents that interact with the real world, and the challenge of coping with the complexity and uncertainty that such interaction entails.

However, the field of AI has fragmented into many challenging subfields that require and often reward isolation and specialization. Consequently, there is a lack of mainstream AI venues for publishing integrative research that combines techniques from multiple different fields to achieve a working robot system capable of complex behavior, addresses the technical challenges that such integration efforts present, and investigates the important research questions posed by such complex systems. Such research speaks to the original impulse behind AI, creates an immensely rich source of research questions that address real-world problems, and should be considered a valid endeavor in its own right.

In order to encourage the integration of various research streams from AI, robotics, and other relevant disciplines, this workshop aims to bring together a diverse and multidisciplinary group of researchers interested in designing intelligent robotic systems. The workshop will include a poster session, discussion sessions, and invited talks in addition to the paper sessions.

Ample time will be left in the schedule for both spontaneous and guided discussions between presentations. The guided sessions will be driven by a set of key questions on bridging AI and robotics. These questions include but are not limited to:

• How can symbolic and geometric planning be integrated?
• How can noisy physical sensors be captured in high level representation and reasoning?
• How can high level reasoning help mitigate the limitations of noisy physical sensors?
• How can knowledge be represented and used in a robotic system?
• How can a robot work seamlessly among humans?
• How can geometric maps be augmented with semantic information?
• How can a robot learn key concepts from its experience?
• How can a robot extract semantic information from its acquired knowledge?

A final open-floor discussion will aim at summarizing the main outcomes of the workshop around those questions, and planning the next steps for widening and consolidating the community.

This workshop builds on a series of workshops and symposia focused on AI Robotics.