Supervised learning of internal models for autonomous goal-oriented robot navigation using Reservoir Computing

Abstract

In this work we propose a hierarchical architecture which constructs internal models of a robot environment for goal-oriented navigation by an imitation learning process. The proposed architecture is based on the Reservoir Computing paradigm for training Recurrent Neural Networks (RNN). It is composed of two randomly generated RNNs (called reservoirs), one for modeling the localization capability and one for learning the navigation skill. The localization module is trained to detect the current and previously visited robot rooms based only on 8 noisy infra-red distance sensors. These predictions together with distance sensors and the desired goal location are used by the navigation network to actually steer the robot through the environment in a goal-oriented manner. The training of this architecture is performed in a supervised way (with examples of trajectories created by a supervisor) using linear regression on the reservoir states. So, the reservoir acts as a temporal kernel projecting the inputs to a rich feature space, whose states are linearly combined to generate the desired outputs. Experimental results on a simulated robot show that the trained system can localize itself within both simple and large unknown environments and navigate successfully to desired goals

Multiobjective model-free learning for robot pathfinding with environmental disturbances

“…Learning is an effective way for guiding a robot towards its goal in a dynamic environment. Early research 17 has employed supervised learning to train a robot in a given map for deciding its next optimal position. However, a small change in the environment can lead to the failure of executing a planned path.…”

Estimating the non-linear dynamics of free-flying objects

“…An Echo State Network (ESN) is used for nonlinear dynamical modeling [37], and modeling the localization capability and the navigation skill for a mobile robot. [38]. The Hidden Markov model (HMM) is used for recognition and regeneration of human motion across various demonstrations [39,40], and to teach a robot to perform assembly tasks [41].…”

An electromyography-driven central pattern generator model for robotic control application

“…Moreover, it could be modulated along control dimensions [7]. ESN, liquid state machines and backpropagation decorrelation were unified as reservoir computing, which was widely applied in autonomous robot localization, map, path plan and navigation [8,9]. Wyffels and et al [10] designed a CPG model based on ESNs to learn the human motion data from CMU Graphics Lab Motion Capture Database [11].…”