Vision based persistent localization of a humanoid robot for locomotion tasks

Abstract

Typical monocular localization schemes involve a search for matches between reprojected 3D world points and 2D image features in order to estimate the absolute scale transformation between the camera and the world. Successfully calculating such transformation implies the existence of a good number of 3D points uniformly distributed as reprojected pixels around the image plane. This paper presents a method to control the march of a humanoid robot towards directions that are favorable for visual based localization. To this end, orthogonal diagonalization is performed on the covariance matrices of both sets of 3D world points and their 2D image reprojections. Experiments with the NAO humanoid platform show that our method provides persistence of localization, as the robot tends to walk towards directions that are desirable for successful localization. Additional tests demonstrate how the proposed approach can be incorporated into a control scheme that considers reaching a target position.

Action Planning and Design of Humanoid Robot Based on Sports Analysis in Digital Economy Era

“…Kinematics mainly analyzes the space-time characteristics of motion from spatial position, motion trajectory, angle, angular velocity, angular acceleration and so on [18][19]. According to the way of motion data processing, it can be divided into forward kinematics and inverse kinematics.…”

Advances in sensing and processing methods for three-dimensional robot vision

“…Robot vision is a most important part in robotics, whose purpose is giving feedback to the robot motion control system about the location of the target or the pose and location of robot itself through vision techniques such as 3D location, scene understanding, and so on. Visual servo system is used for robot manipulator, 77 localization of humanoid robot for locomotion tasks, 78 object recognition with pose estimation, 79,80 robot ego-motion estimation, 81,82 and object grasping. 83,84 Aeronautics and astronautics.…”

A closed-loop approach for tracking a humanoid robot using particle filtering and depth data

“…Currently, PTAM has proved to be one of the most reliable visual-based localization system when enough cues are available. It has been integrated into an active localization method to control the locomotion of a humanoid robot [21,22]. Thereby, it is possible to guide the trajectory of the robot surrounding an object of interest in order to estimate its geometry from a monocular video sequence acquired while the robot is walking [22].…”

“…Thereby, it is possible to guide the trajectory of the robot surrounding an object of interest in order to estimate its geometry from a monocular video sequence acquired while the robot is walking [22]. Furthermore, a method to control the march of the robot towards directions that are favorable for visual based localization was presented in [21]. Here, a set of statistical criteria are used for the analysis of the 3D map and reprojected 2D points for targeting the robot towards directions of rich visual information.…”