Navigation behavior based on self-organized spatial representation in hierarchical recurrent neural network. (3rd June 2019)

• Record Type: Journal Article
• Authors: Noguchi, Wataru; Iizuka, Hiroyuki; Yamamoto, Masahito
• Is Part Of: Advanced robotics. Volume 33:Number 11(2019)
• Page Start: 539
• Page End: 549
• Publication Date: 2019-06-03
• Subjects: Cognitive map -- navigation -- prediction learning -- visuomotor integration -- hierarchical recurrent neural network; Robotics -- Periodicals; Robotics -- Japan -- Periodicals; Robotics; Japan; Periodicals; 629.89205
• DOI: 10.1080/01691864.2019.1566088
• Languages: English
• ISSNs: 0169-1864

Abstract

ABSTRACT: A cognitive map is an internal model of the external world and contains the spatial representation of the surrounding environment. The existence of the cognitive map was first identified in rats; rats can navigate to their desired destination using cognitive maps while dealing with environmental uncertainty. We performed a mobile robot navigation experiment where obstacles were randomly placed using hierarchical recurrent neural network (HRNN) with multiple timescales. The HRNN was trained to navigate the mobile robot to the destination indicated by a snapshot image. After the training, the HRNN was able to successfully avoid the obstacles and navigate to the destination from any location in the environment. Analysis of the internal states of the HRNN showed that the module with fast timescale handles obstacle avoidance and the one with slow timescale has spatial representation corresponding to the spatial position of the destination. Moreover, in the experiment wherein the novel path appeared, the trained HRNN performed shortcut behavior. The shortcut behavior shows that the HRNN performed navigation using the self-organized spatial representation in the slow recurrent neural network. This indicates that training of goal-oriented navigation, i.e. the navigation motivated by a snapshot image of the destination results in the self-organization of cognitive map-like representation. GRAPHICAL ABSTRACT: