State Estimation Approach for Depth Sensor^|^apos;s Posture Attached to a Vehicle or a Human Body

Abstract

The author has been developing a navigation system for safety for mobile robots, mobility scooters and pedestrians by using depth sensors which can capture range data of image size. If the geometrical relation between the sensor and the space is completely known, each point of the captured range data can be classified into three groups: upper than the ground, on the ground, and lower than the ground. However, it is essential to be able to deal with the unpredictable change of the posture of the sensor due to the movement of the attached body. The author already developed a real-time estimation scheme of the posture including pitch angle, roll angle, and height from the observed data in the framework of optimization. In this paper, the author proposes an estimation scheme based on the state space model and apply Extended Kalman filter for the same application problem. We will compare the algorithms by experimental results and will show the usefulness of the proposed algorithm.

Estimation of the Posture of Mobile Depth Sensor for Detecting the Ground and Walls in Terms of Initial Values

“…The author has been developing a mobile alarming system for a blind person, an elderly person on a mobility scooter and unmanned mobile vehicles such as a mobile robot by using a depth sensor [1][2][3][4][5]. The system is intended to raise an alarm for dangerous situations that can be detected by a depth sensor attached to the mobile body.…”

“…Next, an estimation scheme based on Extended Kalman Filter was proposed, where the problem was formulated by a nonlinear state space model [4,5]. The state vector to be estimated was expressed as a 3dimensional vector consisting of the pitch and roll angles and the height, where the range information from the sensor to the ground point excluding the data apart from the ground level is used as the observation data.…”

Ground Surface Estimation and Environmental Recognition by a Small Mobile Depth Sensor

“…The main part of this model was reported in [4]. In this paper, the model and the algorithm will be briefly introduced.…”

“…The objective of this algorithm is to detect the ground surface condition by using a depth sensor, where the Proceedings of the 48th ISCIE International Symposium on Stochastic Systems Theory and Its Applications Fukuoka, Nov. [4][5]2016 detection targets include some obstacles on the ground, holes, ditches, and anything that is higher or lower than the ground. Fig.…”

“…By using the depth sensor, the author is developing an alarm dispatching system in taking a mobility scooter (also called as "senior car" in Japanese) for a blind person or an elderly person [1,2,3,4,5,6]. It should also work for an unmanned mobile vehicle such as a mobile robot.…”