Obstacle Avoidance and Trajectory Planning for an Indoor Mobile Robot Using Stereo Vision and Delaunay Triangulation

1992 ◽  
pp. 268-283 ◽  
Author(s):  
Michel Buffa ◽  
Olivier D. Faugeras ◽  
Zhengyou Zhang
Keyword(s):  
Mobile Robot ◽  
Obstacle Avoidance ◽  
Delaunay Triangulation ◽  
Stereo Vision ◽  
Trajectory Planning ◽  
Indoor Mobile Robot

A Stereo Vision Based Target Tracking and Obstacle Avoidance

2009 ◽  
Vol 419-420 ◽  
pp. 565-568 ◽  
Author(s):  
Chao Ching Ho
Keyword(s):  
Mobile Robot ◽  
Target Tracking ◽  
Obstacle Avoidance ◽  
Visual Tracking ◽  
Stereo Vision ◽  
Vision System ◽  
Tracking System ◽  
Video Data ◽  
Corner Detection ◽  
Harris Corner

Designing a visual tracking system to track an object is a complex task because a large amount of video data must be transmitted and processed in real time. In this study, a stereo vision system is used to acquire the 3D positions of the target, tracking can be achieved by applying the CAMSHIFT algorithm, then apply the fuzzy reasoning control to steer the mobile robot to follow the selected target and avoid the in-path obstacles. The adopted obstacle avoidance component is based on the Harris corner detection and the binocular stereo imaging, which performs the correspondence calculation. Therefore a depth map is created and showing the relative 3D distances of the detected substantial features to the robot, which provides the information of the in-path obstacles in front of the wheeled mobile robot. The designed visual tracking and servo system is less sensitive to lighting influences and thus performs more efficiently. Experimental results showed that the mobile robot vision system successfully finished the target-following task by avoiding obstacles.

scholarly journals Multimodal Deep Reinforcement Learning with Auxiliary Task for Obstacle Avoidance of Indoor Mobile Robot

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1363
Author(s):  
Hailuo Song ◽  
Ao Li ◽  
Tong Wang ◽  
Minghui Wang
Keyword(s):  
Reinforcement Learning ◽  
Mobile Robot ◽  
Obstacle Avoidance ◽  
Representation Learning ◽  
Velocity Estimation ◽  
Depth Images ◽  
Indoor Mobile Robot ◽  
Multimodal Information ◽  
Testing Environments ◽  
Accumulated Reward

It is an essential capability of indoor mobile robots to avoid various kinds of obstacles. Recently, multimodal deep reinforcement learning (DRL) methods have demonstrated great capability for learning control policies in robotics by using different sensors. However, due to the complexity of indoor environment and the heterogeneity of different sensor modalities, it remains an open challenge to obtain reliable and robust multimodal information for obstacle avoidance. In this work, we propose a novel multimodal DRL method with auxiliary task (MDRLAT) for obstacle avoidance of indoor mobile robot. In MDRLAT, a powerful bilinear fusion module is proposed to fully capture the complementary information from two-dimensional (2D) laser range findings and depth images, and the generated multimodal representation is subsequently fed into dueling double deep Q-network to output control commands for mobile robot. In addition, an auxiliary task of velocity estimation is introduced to further improve representation learning in DRL. Experimental results show that MDRLAT achieves remarkable performance in terms of average accumulated reward, convergence speed, and success rate. Moreover, experiments in both virtual and real-world testing environments further demonstrate the outstanding generalization capability of our method.

scholarly journals 3 Bio-Mimetic Vision System For Autonomous Mobile Robot Navigation

2013 ◽  
Vol 3 (1) ◽  
pp. 4
Author(s):  
Muhammad Safwan ◽  
Muhammad Yasir Zaheen ◽  
M. Anwar Ahmed ◽  
Muhammad Shujaat Kamal ◽  
Raj Kumar
Keyword(s):  
Mobile Robot ◽  
Obstacle Avoidance ◽  
Stereo Vision ◽  
Robot Navigation ◽  
Vision System ◽  
Experimental Results ◽  
Mobile Robot Navigation ◽  
Absolute Difference ◽  
Autonomous Mobile Robot ◽  
Dc Motors

Bio-Mimetic Vision System (BMVS) for AutonomousMobile Robot Navigation encompasses three major fields, namelyrobotics, navigation and obstacle avoidance. Bio-mimetic vision isbased on stereo vision. Summation of Absolute Difference (SAD)is applied on the images from the two cameras and disparity mapis generated which is then used to navigate and avoid obstacles.Camera calibration and SAD is applied on Matlab software.AT89C52 microcontroller, along with Matlab, is used to efficientlycontrol the DC motors mounted on the robot frame. It is observedfrom experimental results that the developed system effectivelydistinguishes objects at different distances and avoids them whenthe path is blocked.

A New Mobile Robot With a Passive Mechanism and a Stereo Vision System for Hazardous Terrain Exploration

2004 ◽  
Author(s):  
Sukjune Yoon ◽  
Chun-Kyu Woo ◽  
Hyun Do Choi ◽  
Sung-Kee Park ◽  
Sung-Chul Kang ◽  
...  
Keyword(s):  
Remote Control ◽  
Mobile Robot ◽  
Obstacle Avoidance ◽  
Stereo Vision ◽  
High Speed ◽  
Vision System ◽  
Three Dimensional ◽  
Linkage Mechanism ◽  
Passive Mechanism ◽  
Stereo Vision System

The purpose of this project is to develop a mobile robot for hazardous terrain exploration. The exploration of hazardous terrain requires the development of a passive mechanism adaptable to such terrain and a sensing system for obstacle avoidance, as well as a remote control. We designed a new mobile robot, the Ronahz 6-wheel robot, which uses a passive mechanism that can adapt to hazardous terrains and building stairways without any active control. The suggested passive linkage mechanism consists of a simple four-bar linkage mechanism. In addition, we install a stereo vision system for obstacle avoidance, as well as a remote control. Wide dynamic range CCD cameras are used for outdoor navigation. A stereo vision system commonly requires high computational power. Therefore, we use a new high-speed stereo correspondence algorithm, triangulation, and iterative closest point (ICP) registration to reduce computation time. Disparity maps computed by a newly proposed, high-speed method are sent to the operator by a wireless LAN equipment. At the remote control site, a three-dimensional digital map around a mobile robot is built by ICP registration and reconstruction process, and this three-dimensional map is displayed for the operator. This process allows the operator to sense the environment around the robot and to give commands to the mobile robot when the robot is in a remote site.

Sign in / Sign up

Export Citation Format

Share Document