Rapid position estimation and tracking for autonomous driving

The Lateral Position Estimation System for Autonomous Driving of the Online Electric Vehicle

IFAC Proceedings Volumes ◽

10.3182/20100906-3-it-2019.00071 ◽

2010 ◽

Vol 43 (16) ◽

pp. 407-412

Author(s):

Youjun Choi ◽

Sunjong Lee ◽

Jinkyu Kim

Keyword(s):

Electric Vehicle ◽

Autonomous Driving ◽

Lateral Position ◽

Position Estimation ◽

Estimation System

Download Full-text

DMS-SLAM: A General Visual SLAM System for Dynamic Scenes with Multiple Sensors

Sensors ◽

10.3390/s19173714 ◽

2019 ◽

Vol 19 (17) ◽

pp. 3714 ◽

Cited By ~ 1

Author(s):

Guihua Liu ◽

Weilin Zeng ◽

Bo Feng ◽

Feng Xu

Keyword(s):

Large Deviation ◽

Autonomous Driving ◽

Position Estimation ◽

Visual Slam ◽

Dynamic Scenes ◽

Current Frame ◽

Multiple Sensors ◽

Pose Tracking ◽

Dynamic Objects ◽

Local Map

Presently, although many impressed SLAM systems have achieved exceptional accuracy in a real environment, most of them are verified in the static environment. However, for mobile robots and autonomous driving, the dynamic objects in the scene can result in tracking failure or large deviation during pose estimation. In this paper, a general visual SLAM system for dynamic scenes with multiple sensors called DMS-SLAM is proposed. First, the combination of GMS and sliding window is used to achieve the initialization of the system, which can eliminate the influence of dynamic objects and construct a static initialization 3D map. Then, the corresponding 3D points of the current frame in the local map are obtained by reprojection. These points are combined with the constant speed model or reference frame model to achieve the position estimation of the current frame and the update of the 3D map points in the local map. Finally, the keyframes selected by the tracking module are combined with the GMS feature matching algorithm to add static 3D map points to the local map. DMS-SLAM implements pose tracking, closed-loop detection and relocalization based on static 3D map points of the local map and supports monocular, stereo and RGB-D visual sensors in dynamic scenes. Exhaustive evaluation in public TUM and KITTI datasets demonstrates that DMS-SLAM outperforms state-of-the-art visual SLAM systems in accuracy and speed in dynamic scenes.

Download Full-text

Study on Automatic Operation of Manual Wheelchair Prototype and Basic Experiments

Journal of Robotics and Mechatronics ◽

10.20965/jrm.2021.p0069 ◽

2021 ◽

Vol 33 (1) ◽

pp. 69-77

Author(s):

Kazuteru Tobita ◽

◽

Yoshihito Shikanai ◽

Kazuhiro Mima

Keyword(s):

Nursing Homes ◽

Autonomous Driving ◽

Position Estimation ◽

Manual Wheelchair ◽

The Past ◽

Straight Line ◽

Before And After ◽

Sensor Measurement ◽

Autonomous Mobility ◽

Basic Experiments

In nursing homes, repeatedly guiding several carereceivers in wheelchairs before and after meals is one of the factors that increase the burden on caregivers. A solution to this problem is to incorporate autonomous mobility functions into the wheelchair. Although many autonomous electric wheelchairs have been developed in the past, it is not reasonable to introduce them to all users of nursing homes from the standpoint of cost, charging, and maintenance. In this study, we are developing a detachable robot that can operate a manual wheelchair autonomously. The basic concept, target specifications, and design conditions are defined herein, and the results of basic experiments such as straight-line stability tests, obstacle sensor measurement tests, and self-position estimation are reported. The implementation of autonomous driving functions such as path generation and localization will be promoted in the future.

Download Full-text