Abstract

Spatial cognition is an important branch of cognition science and also very common in our daily life when people work together. In terms of human-robot spatial cognition interaction, it would be dramatic if the robot could interact with people like a human. So we designed an intelligent robot which could communicate with people in natural language and think on the human's perspective in spatial cognition tasks, such as fetch tools and assemble machines. The innovative thing is that the human-robot spatial cognition interaction system is established based on ACT-R (Adaptive Control of Thought-Rational) cognitive architecture. And a brief scheme is proposed in this paper. Also, we combined the natural language recognition and synthesis technique, visual pattern processing technique and gesture recognition technique into the spatial cognitive model. The system can work stably in six typical working spatial cognition scenes.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call