Theme

The intersection of humanoid robotics and Artificial General Intelligence research is both obvious and extensive. To create mobile robots, active in everyday human environments, able to carry out a variety of goals in a flexible way, requires one to make a fair degree of headway toward the broader problem of Artificial General Intelligence. The intersection between robotics and AGI is particularly important where humanoid robotics are concerned, as people naturally expect the humanoid robots they interact with to display a certain level human-like savvy. The humanoid form factor also presents unique opportunities for learning intelligent behaviors via emotionally rich interactions with humans. The workshop will focus on the full breadth of issues at the intersection of humanoid robotics and Artificial General Intelligence. In other words, it will focus on

• the use of artificial general intelligence oriented software and hardware to cope with the challenges involved in achieving goals involving controlling humanoid bodies in the everyday world
• the design of humanoid bodies capable of serving as appropriate vehicles for artificial general intelligence technology

The workshop is open to contributions on any topic directly related to the interfacing between artificial general intelligence architectures and the problem of controlling humanoid robot bodies in the everyday human world. Contributions presenting empirical or mathematical results will be very welcome; contributions describing new approaches at an earlier stage of development will also be accepted in some cases, if the ideas are novel and clearly presented and argued for. Specific topics of interest include (but are definitely not limited to):

• Analog hardware for adaptive control and perceptual-motor integration
• Autonomy: the capabilities of a generally intelligent robot to find itself its own motivations and goals.
• Emotional intelligence: use of emotional expression and understanding to help a robotic system learn and understand better
• Entity identification: Identification of which groups of percepts or atomic objects in a world are sensibly grouped together as a coherent “entity”
• Event identification: Identification of which groups of temporal happenings in a world are sensibly grouped together as a coherent “event”
• Generally-intelligent adaptive control: Learning patterns of actuator control in a manner that displays strong adaptiveness, i.e. ability to learn to carry out actions qualitatively different from those for which a system was previously trained or programmed. E.g. a robot with the ability to learn to walk on different kinds of terrain via adapting to its experience.
• Generally-intelligent adaptive perception: Perception of objects and events in a world, in a manner that displays strong adaptiveness, i.e. ability to perceive objects and events qualitatively different from those for which a
• Modeling of other Agents: modeling of other agents, in terms of their likely behaviors in various contexts in the world
• Self-modeling: Building a model of the agent’s mental and physical self based on the agent’s observations of its own interactions in the world
• Sensorimotor integration: methodologies for linking perception with action in a robotically embodied AGI.
• Spatial, temporal and spatiotemporal reasoning: Inference about objects and events in a world, in a manner that takes careful account of the spatial and temporal relationships between them
• Symbol grounding: Learning of groundings for words and/or syntactic and/or semantic relationships, via experience interacting with objects and entities in a world
• Theory of mind: modeling of other agents, in terms of the knowledge and beliefs on which their actions are based