Scope

This workshop is intended for roboticists from both scientific and industrial communities working in the areas of perception, control, planning, and learning. It is especially aimed at roboticists interested in improving the reliability and autonomy of robots. We hope to bring together outstanding researchers and graduate students to discuss current trends, problems, and opportunities in semantic action (policy) representations, encouraging communication and common practices among scientists and industrial researchers in this field.

We wish to bring together researchers in computer vision, robotic skill learning, task and motion planning, and natural language processing to discuss how robots can learn semantically meaningful skills that they can use to accomplish long-horizon tasks in human environments, since these semantic representations should ideally allow for explainable AI and for better instruction of robots.

Topics

The topics that are indicative but by no means exhaustive are as follows:

• Task and Motion Planning

• Explainable AI

• Perception-informed Semantic Representations

• Task-oriented and Perception-informed Language Grounding

• Task and Environment Semantics

• Robot Learning from Demonstration and Exploration

• Cognitive Robotics