A New Dynamic Self-Organizing Method for Mobile Robot Environment Mapping

To solve the mapping problem for the mobile robots in the unknown environment, a dynamic growing self-organizing map with growing-threshold tuning automatically algorithm (DGSOMGT) based on Self-organizing Map is proposed. It introduces a value of spread factor to describe the changing process of the growing threshold dynamically. The method realizes the network structure growing by training through mobile robot movement constantly in the unknown environment. The proposed algorithm is based on self-organizing map and can adjust the growing-threshold value by the number of network neurons increasing. It avoids tuning the parameters repeatedly by human. The experimental results show that the proposed method detects the complex environment quickly, effectively and correctly. The robot can realize environment mapping automatically. Compared with the other methods the proposed mapping strategy has better topological properties and time property.

PC-VINS-Mono: A Robust Mono Visual-Inertial Odometry with Photometric Calibration

Feature detection and Tracking, which heavily rely on the gray value information of images, is a very importance procedure for Visual-Inertial Odometry (VIO) and the tracking results significantly affect the accuracy of the estimation results and the robustness of VIO. In high contrast lighting condition environment, images captured by auto exposure camera shows frequently change with its exposure time. As a result, the gray value of the same feature in the image show vary from frame to frame, which poses large challenge to the feature detection and tracking procedure. Moreover, this problem further been aggravated by the nonlinear camera response function and lens attenuation. However, very few VIO methods take full advantage of photometric camera calibration and discuss the influence of photometric calibration to the VIO. In this paper, we proposed a robust monocular visual-inertial odometry, PC-VINS-Mono, which can be understood as an extension of the opens-source VIO pipeline, VINS-Mono, with the capability of photometric calibration. We evaluate the proposed algorithm with the public dataset. Experimental results show that, with photometric calibration, our algorithm achieves better performance comparing to the VINS-Mono.

Motor Learning Based on the Cooperation of Cerebellum and Basal Ganglia for a Self-Balancing Two-Wheeled Robot

A novel motor learning method is present based on the cooperation of the cerebellum and basal ganglia for the behavior learning of agent. The motor learning method derives from the principle of CNS and operant learning mechanism and it depends on the interactions between the basal ganglia and cerebellum. The whole learning system is composed of evaluation mechanism, action selection mechanism, tropism mechanism. The learning signals come from not only the Inferior Olive but also the Substantia Nigra in the beginning. The speed of learning is increased as well as the failure time is reduced with the cerebellum as a supervisor. Convergence can be guaranteed in the sense of entropy. With the proposed motor learning method, a motor learning system for the self-balancing two-wheeled robot has been built using the RBF neural networks as the actor and evaluation function approximator. The simulation experiments showed that the proposed motor learning system achieved a better learning effect, so the motor learning based on the coordination of cerebellum and basal ganglia is effective.

Bionic autonomous learning control of a two-wheeled self-balancing flexible robot

This paper presents an OCPA （operant conditioning probabilistic automaton） bionic autonomous learning system based on Skinner＇s operant conditioning theory for solving the balance control problem of a two-wheeled flexible robot. The OCPA learning system consists of two stages： in the first stage, an operant action is selected stochastically from a set of operant actions and then used as the input of the control system; in the second stage, the learning system gathers the orientation information of the system and uses it for optimization until achieves control target. At the same time, the size of the operant action set can be automatically reduced during the learning process for avoiding little probability event. Theory analysis is made for the designed OCPA learning system in the paper, which theoretically proves the convergence of operant conditioning learning mechanism in OCPA learning system, namely the operant action entropy will converge to minimum with the learning process. And then OCPA learning system is applied to posture balanced control of two-wheeled flexible self-balanced robots. Robot does not have posutre balanced skill in initial state and the selecting probability of each operant in operant sets is equal. With the learning proceeding, the selected probabilities of optimal operant gradually tend to one and the operant action entropy gradually tends to minimum, and so robot gradually learned the posture balanced skill.