Geometric proto-symbol manipulation towards language-based motion pattern synthesis and recognition

In this paper, we propose an improved mimesis method for interpolation and extrapolation of motion patterns in the proto-symbol space towards an ultimate goal that motion pattern synthesis and recognition of humanoid robots are achieved by means of natural language. The proto-symbol space is a topological space which abstracts motion patterns by utilizing continuous hidden Markov models. An interpolation algorithm for the proto-symbol space was proposed in a previous work, but an extrapolation algorithm was not. Therefore, in this study, we propose and extrapolation method which can further clarify the physical meaning of the dimension of the proto-symbol space that is one of the most essential issues for the realization of translation between motion patterns and language using the proto-symbol space. The extrapolation method also enables the robot to recognize and synthesis various kinds of motion patterns using a fewer number of proto-symbols. The feasibility of the proposed method is demonstrated through simulation experiments.