FPGA-based CPG Robot Locomotion Modulation Using a Fuzzy Scheme and Visual Information

摘要

Locomotion and visual information have been treated as separated problems in the field of robotics. However the locomotion and vision should be connected or interact as suggested by biological evidence, i.e., to change from visual information domain to locomotion domain. Mathematically, this problem consists in finding the function that maps from the visual information to locomotion parameters, V→ <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">f</sup> L. Some authors consider creating a direct coupling of visual perception to action, and others have proposed to use map planing. These implementations require a huge knowledge base or the solution is computationally intense and too slow for real-time. From these necessities, a feasible function based on fuzzy logic (FL) to be implemented in field programmable gate array (FPGA) is proposed. The presented function is composed by blocks that compute the basic arithmetic operations that use fixed point arithmetic and are configurable. This advantage let to have a multi precision fixed point arithmetic in each stage of the function. As a result, the function based on FL requires few FPGA resources and is able to map between the different maps. Also, it is possible to be used in autonomous robots with size and power consumption restrictions.