• Title/Summary/Keyword: Obstacle-avoiding

Search Result 85, Processing Time 0.03 seconds

Improved View-Based Navigation for Obstacle Avoidance using Ego-Motion

  • Hagiwara, Yoshinobu;Suzuki, Akimasa;Kim, Youngbok;Choi, Yongwoon
    • Journal of Power System Engineering
    • /
    • v.17 no.5
    • /
    • pp.112-120
    • /
    • 2013
  • In this study, we propose an improved view-based navigation method for obstacle avoidance and evaluate the effectiveness of the method in real environments with real obstacles. The proposed method possesses the ability to estimate the position and rotation of a mobile robot, even if the mobile robot strays from a recording path for the purpose of avoiding obstacles. In order to achieve this, ego-motion estimation was incorporated into the existing view-based navigation system. The ego-motion is calculated from SURF points between a current view and a recorded view using a Kinect sensor. In conventional view-based navigation systems, it is difficult to generate alternate paths to avoid obstacles. The proposed method is anticipated to allow a mobile robot greater flexibility in path planning to avoid humans and objects expected in real environments. Based on experiments performed in an indoor environment using a mobile robot, we evaluated the measurement accuracy of the proposed method, and confirmed its feasibility for robot navigation in museums and shopping mall.

Implementation of a sensor fusion system for autonomous guided robot navigation in outdoor environments (실외 자율 로봇 주행을 위한 센서 퓨전 시스템 구현)

  • Lee, Seung-H.;Lee, Heon-C.;Lee, Beom-H.
    • Journal of Sensor Science and Technology
    • /
    • v.19 no.3
    • /
    • pp.246-257
    • /
    • 2010
  • Autonomous guided robot navigation which consists of following unknown paths and avoiding unknown obstacles has been a fundamental technique for unmanned robots in outdoor environments. The unknown path following requires techniques such as path recognition, path planning, and robot pose estimation. In this paper, we propose a novel sensor fusion system for autonomous guided robot navigation in outdoor environments. The proposed system consists of three monocular cameras and an array of nine infrared range sensors. The two cameras equipped on the robot's right and left sides are used to recognize unknown paths and estimate relative robot pose on these paths through bayesian sensor fusion method, and the other camera equipped at the front of the robot is used to recognize abrupt curves and unknown obstacles. The infrared range sensor array is used to improve the robustness of obstacle avoidance. The forward camera and the infrared range sensor array are fused through rule-based method for obstacle avoidance. Experiments in outdoor environments show the mobile robot with the proposed sensor fusion system performed successfully real-time autonomous guided navigation.

A simple and efficient planning of robot motions with obstacle avoidance (장애물이 있는 경우의 효율적인 로보트 동자계획)

  • 정봉주;이영훈
    • Proceedings of the Korean Operations and Management Science Society Conference
    • /
    • 1995.04a
    • /
    • pp.880-885
    • /
    • 1995
  • This paper deals with the efficient planning of robot motions in the Cartesian space while avoiding the collision with obstacles. The motion planning problem is to find a path from the specified starting robot configuration that avoids collision with a known set of stationary obstacles. A simple and efficient algorithm was developed using "Backward" approach to solve this problem. The computational result was satisfactory enough to real problems. problems.

  • PDF

Global Path Planning Algorithm Using a Skeleton Map and Dynamic Programming (골격지도와 동적 계획법을 이용한 전역경로계획 알고리즘)

  • Yang, Dong-Hoon;Hong, Suk-Kyo
    • Proceedings of the KIEE Conference
    • /
    • 2005.07d
    • /
    • pp.2790-2792
    • /
    • 2005
  • This paper proposes a path-planning algorithm that enables a robot to reach the goal position while avoiding obstacles. The proposed method, which is based on dynamic programming, finds an optimum path to follow using a modified skeleton map method which exploits information on obstacle positions. Simulation results show the feasibility of the proposed method.

  • PDF

An Auto Obstacle Collision Avoidance System using Reinforcement Learning and Motion VAE (강화학습과 Motion VAE 를 이용한 자동 장애물 충돌 회피 시스템 구현)

  • Zheng Si;Taehong Gu;Taesoo Kwon
    • Journal of the Korea Computer Graphics Society
    • /
    • v.30 no.4
    • /
    • pp.1-10
    • /
    • 2024
  • In the fields of computer animation and robotics, reaching a destination while avoiding obstacles has always been a difficult task. Moreover, generating appropriate motions while planning a route is even more challenging. Recently, academic circles are actively conducting research to generate character motions by modifying and utilizing VAE (Variational Auto-Encoder), a data-based generation model. Based on this, in this study, the latent space of the MVAE model is learned using a reinforcement learning method[1]. With the policy learned in this way, the character can arrive its destination while avoiding both static and dynamic obstacles with natural motions. The character can easily avoid obstacles moving in random directions, and it is experimentally shown that the performance is improved, and the learning time is greatly reduced compared to existing approach.

Fuzzy Navigation and Obstacle Avoidance Control for Docking of Modular Robots (모듈형 로봇의 자가 결합을 위한 퍼지 주행 제어 및 장애물 회피 제어)

  • Na, Doo-Young;Noh, Su-Hee;Moon, Hyung-Pil;Jung, Jin-Woo;Kim, Yong-Tae
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.19 no.4
    • /
    • pp.470-477
    • /
    • 2009
  • Modular reconfigurable robots with physical docking capability easily adapt to a new environment and many studies are necessary for the modular robots. In this paper, we propose a vision-based fuzzy autonomous docking controller for the modular docking robots. A modular docking robot platform which performs real-time image processing is designed and color-based object recognition method is implemented on the embedded system. The docking robot can navigate to a subgoal near a target robot while avoiding obstacles. Both a fuzzy obstacle avoidance controller and a fuzzy navigation controller for subgoal tracking are designed. We propose an autonomous docking controller using the fuzzy obstacle avoidance and navigation controllers, absolute distance information and direction informations of robots from PSD sensors and a compass sensor. We verify the proposed docking control method by docking experiments of the developed modular robots in the various environments with different distances and directions between robots.

Development of Adaptive Moving Obstacle Avoidance Algorithm Based on Global Map using LRF sensor (LRF 센서를 이용한 글로벌 맵 기반의 적응형 이동 장애물 회피 알고리즘 개발)

  • Oh, Se-Kwon;Lee, You-Sang;Lee, Dae-Hyun;Kim, Young-Sung
    • The Journal of Korea Institute of Information, Electronics, and Communication Technology
    • /
    • v.13 no.5
    • /
    • pp.377-388
    • /
    • 2020
  • In this paper, the autonomous mobile robot whit only LRF sensors proposes an algorithm for avoiding moving obstacles in an environment where a global map containing fixed obstacles. First of all, in oder to avoid moving obstacles, moving obstacles are extracted using LRF distance sensor data and a global map. An ellipse-shaped safety radius is created using the sum of relative vector components between the extracted moving obstacles and of the autonomuos mobile robot. Considering the created safety radius, the autonomous mobile robot can avoid moving obstacles and reach the destination. To verify the proposed algorithm, use quantitative analysis methods to compare and analyze with existing algorithms. The analysis method compares the length and run time of the proposed algorithm with the length of the path of the existing algorithm based on the absence of a moving obstacle. The proposed algorithm can be avoided by taking into account the relative speed and direction of the moving obstacle, so both the route and the driving time show higher performance than the existing algorithm.

Development of Reinforcement Learning-based Obstacle Avoidance toward Autonomous Mobile Robots for an Industrial Environment (산업용 자율 주행 로봇에서의 격자 지도를 사용한 강화학습 기반 회피 경로 생성기 개발)

  • Yang, Jeong-Yean
    • The Journal of the Korea Contents Association
    • /
    • v.19 no.3
    • /
    • pp.72-79
    • /
    • 2019
  • Autonomous locomotion has two essential functionalities: mapping builds and updates maps by uncertain position information and measured sensor inputs, and localization is to find the positional information with the inaccurate map and the sensor information. In addition, obstacle detection, avoidance, and path designs are necessarily required for autonomous locomotion by combining the probabilistic methods based on uncertain locations. The sensory inputs, which are measured by a metric-based scanner, have difficulties of distinguishing moving obstacles like humans from static objects like walls in given environments. This paper proposes the low resolution grid map combined with reinforcement learning, which is compared with the conventional recognition method for detecting static and moving objects to generate obstacle avoiding path. Finally, the proposed method is verified with experimental results.

A study on Moving OBstacle Avoidance for an Intelligent Vehicle Using Fuzzy Controller (퍼지 제어기를 이용한 지능형 차량의 이동장애물 회피에 관한 연구)

  • Kim, Hun-Mo
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.6 no.2
    • /
    • pp.155-163
    • /
    • 2000
  • This paper presents a path planning method of the sensor based intelligent vehicle using fuzzy logic controller for avoidance of moving obstacles in unknown environments. Generally it is too difficult and complicated to control intelligent vehicle properly by recognizing unknown terrain with sensors because the great amount of imprecise and ambiguous information has to be considered. In this respect a fuzzy logic can manage such the enormous information in a quite efficient manner. Furthermore it is necessary to use the relative velocity to consider the mobility of obstacles, In order to avoid moving obstacles we must deliberate not only vehicle's relative speed toward obstacles but also self-determined acceleration and steering for the satisfaction of avoidance efficiency. In this study all the primary factors mentioned before are used as the input elements of fuzzy controllers and output signals to control velocity and steering angle of the vehicle. The main purpose of this study is to develop fuzzy controllers for avoiding collision with moving obstacles when they approach the vehicle travelling with straight line and for returning to original trajectory. The ability are and effectiveness of the proposed algorithm are demonstrated by simulations and experiments.

  • PDF

The Design of Evading Collision System of Unman Vehicle (무인 이동체의 충돌 회피 시스템 설계)

  • Kim, Tae-Hyoung;Jang, Jong-Wook
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2016.10a
    • /
    • pp.254-255
    • /
    • 2016
  • The Human have sought convenience through advancing Science skill, The Generation that unman control all machine have came. the unman - vehicle have used and applied flight, ship, car, manufacturing all over the world. plus which, that is researching. but pros and cons of unman - vehicle is that unman control machine, It mean that unman - vehicle have high possibility which have collision with obstacle on driving. I will show you that this evading collision will be made from fuzzy control and video recognition and sensor recognition.I look for good effect for this system.

  • PDF