A Bionic Robot Navigation Algorithm Based on Cognitive Mechanism of Hippocampus

摘要

The firing of space cell in hippocampus is considered to be able to form an intrinsic map for the environment which is called cognitive map. Previous bionic navigation algorithms (such as rat simultaneous localization and mapping) and traditional SLAM algorithms lack sufficient physiological basis and cannot reflect the cognitive mechanism of hippocampal formation. Based on the cognitive mechanism of hippocampal space cells, this paper proposes a navigation algorithm for constructing accurate environmental cognitive map. This algorithm is characterized by the construction of a unified spatial cell attractor model for self-motion trajectory path integration. The expressions of grid cells and place cells are driven by stripe cells. The algorithm performs closed-loop detection by collecting depth image, red green blue+depthmap information and corrects the error of spatial cells' path integral. Eventually, we get a precise cognitive map of the environment and bionic robot navigation is achieved by global navigation and local navigation algorithm based on the map. The cognitive map is a topological metric map that contains the topological relations of the environment feature point coordinates, visual cues, and specific sites. In this paper, the method is verified by the simulation experiment and the physical experiment on the robot platform. The research results laid the foundation for the research of the robot navigation method based on the hippocampus cognitive mechanism. Note to Practitioners Environmental cognition and navigation ability are the main function of intelligent mobile robots. People and animals have strong adaptability and cognitive ability in unfamiliar environment, and they can independently recognize and navigate in unfamiliar environment. Now, the environmental cognition and navigation ability of intelligent robots are far from the level of human and animal. This paper suggests a bionic robot navigation algorithm based on the cognitive mechanism of rat hippocampus. The bionic robot navigation algorithm makes mobile robots more intelligent by learning and imitating human and animal's environmental cognition and navigation ability. This navigation algorithm conforms to the physiological characteristics and is pretty accurate and intelligent. The experimental results demonstrate the effectiveness of this algorithm in building environment map and navigation.