• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.3
• /
• pp.377-383
• /
• 2021

Recently, in accordance with the 4th industrial revolution, The use of autonomous mobile robots for flexible logistics transfer is increasing in factories, the warehouses and the service areas, etc. In large factories, many manual work is required to use Simultaneous Localization and Mapping(SLAM), so the need for the improved mobile robot autonomous driving is emerging. Accordingly, in this paper, an algorithm for mapless navigation that travels in an optimal path avoiding fixed or moving obstacles is proposed. For mapless navigation, the robot is trained to avoid fixed or moving obstacles through Deep Q Network (DQN) and accuracy 90% and 93% are obtained for two types of obstacle avoidance, respectively. In addition, DQN requires a lot of learning time to meet the required performance before use. To shorten this, the target size change algorithm is proposed and confirmed the reduced learning time and performance of obstacle avoidance through simulation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.5
• /
• pp.367-372
• /
• 2001

This paper proposes a hierachically structured navigation algorithm for multiple mobile robots under unknown dynamic environment. The proposed algorithm consists of three basic parts as follows. The first part based on the fuzzy rule generates the turning angle and moving distance of the robot for goal approach without obstacles. In the second part, using both fuzzy and neural network, the angle and distance of the robot to avoid collision with dynamic and static obstacles are obtained. The final adjustment of the weighting factor based on fuzzy rule for moving and avoiding distance of the robots is provided in the third stage. Some simulation results show the effectiveness of the proposed algorithm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.2
• /
• pp.180-185
• /
• 2003

This paper proposes an intelligent navigation algorithm for multiple mobile robots under unknown dynamic environment. The proposed algorithm consists of three basic parts as follows. The first part based on the fuzzy rule generates the turning angle and moving distance of the robot for goal approach without obstacles. In the second part, using both fuzzy and neural network, the angle and distance of the robot to avoid collision with dynamic and static obstacles are obtained. The final adjustment of the weighting factor based on fuzzy rule for moving and avoiding distance of the robots is provided in the third stage. The experiments which demonstrate the performance of the proposed intelligent controller is described.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.10
• /
• pp.928-933
• /
• 2012

In this paper, the IR and compass sensors for the underwater system were used. The walls of the water tank have been recognized and avoided treating the walls as obstacles by the bio-mimetic underwater robot. This paper is consists of two parts: 1.The hardware part for the IR and compass sensors and 2.The software part for obstacle avoidance algorithm while the bio-mimetic robot is swimming with the obstacle recognition. Firstly, the hardware part controls through the RS-485 communications between a microcontroller and the bio-mimetic underwater robot. The software part is simulated for obstacle recognition and collision avoidance based upon the data from IR and compass sensors. Actually, the bio-mimetic underwater robot recognizes where is the obstacle as well as where is the bio-mimetic robot itself while it is moving in the water. While the underwater robot is moving at a constant speed recognizing the wall of water tank as an obstacle, an obstacle avoidance algorithm is applied for the wall following swimming based upon the IR and compass sensor data. As the results of this research, it is concluded that the bio-mimetic underwater robot can follow the wall of the water tank efficiently, while it is avoiding collision to the wall.

• 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.

• Journal of the Korean Society of Safety
• /
• v.28 no.4
• /
• pp.19-25
• /
• 2013

For safe remote control, information on remote environment has to be delivered to operator realistically, and there have been numerous research efforts on this respect. Among them, haptic technology can significantly enhance safety and overall effectiveness of remote operation by delivering various kinds of information on virtual or real environment to operator. In this study, remote control based on haptic feedback is applied to control of mobile robot moving according to the command from operator avoiding collision with environmental obstacles and maintaining safe distance from them using ultrasonic sensors. Specifically, a remote feedback control structure for mobile robot is proposed. The controller is based on the inner feedback loop that directly utilizes information on distance to obstacles, and the outer feedback loop that the operator directly commands using the haptic device on which the computed reaction force based on the distance information is acting. Effectiveness of the proposed remote control scheme using double feedback loops is verified through a series of experiments on mobile robot.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1496-1499
• /
• 2004

In this paper, we deal with a novel path planning algorithm to find collision-free path for a moving robot to find an appropriate path from initial position to goal position. The robot should make progress by avoiding obstacles located at unknown position. Such problem is called the path planning. We propose so called the subgoal generation algorithm to find an effective collision-free path. The generation and selection of the subgoal are the key point of this algorithm. Several subgoals, if necessary, are generated by analyzing the map information. The subgoal is the candidate for the final path to be pass through. Then selection algorithm is executed to choose appropriate subgoal to construct a correct path. Deep and through explanations are given for the proposed algorithm. Simulation example is given to show the effectiveness of the proposed algorithm.

• Annual Conference of KIPS
• /
• 2016.04a
• /
• pp.733-734
• /
• 2016

무인 차량의 자율 주행을 위해 장애물 회피, 주행 가능 도로 판단 등의 기술이 연구되고 있다. 이러한 연구를 실제 환경에서의 자율 주행에 활용하기 위해서는 주변 환경에 동적으로 움직이는 장애물의 위치를 고려할 필요가 있다. 본 연구는 차량에 탑재된 LIDAR로부터 획득한 포인트의 분포 변화를 이용하여 차량 주변에 동적 장애물이 존재하는 지역을 검출하는 방법을 제안한다. 해당 방법은 포인트에 대한 통계치를 활용하여 동적 객체가 존재하는 영역을 추정함으로써 동적 객체 영역을 고속으로 탐색할 수 있다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.8
• /
• pp.971-980
• /
• 2010

In this paper, we present a navigation control algorithm for mobile robots that move in environments having static and moving obstacles. The algorithm includes a global and a local path-planning algorithm that uses $D^*$ search algorithm, a fuzzy logic for determining the immediate level of danger due to collision, and a fuzzy logic for evaluating the required wheel velocities of the mobile robot. To apply the $D^*$ search algorithm, the two-dimensional space that the robot moves in is decomposed into small rectangular cells. The algorithm is verified by performing simulations using the Python programming language as well as by using the dynamic equations for a two-wheeled mobile robot. The simulation results show that the algorithm can be used to move the robot successfully to reach the goal position, while avoiding moving and unknown static obstacles.

• Nuclear Engineering and Technology
• /
• v.55 no.8
• /
• pp.3030-3038
• /
• 2023

Nowadays, mobile robots have been used to search for uncontrolled radioactive source in indoor environments to avoid radiation exposure for technicians. However, in the indoor environments, especially in the presence of obstacles, how to make the robots with limited sensing capabilities automatically search for the radioactive source remains a major challenge. Also, the source search efficiency of robots needs to be further improved to meet practical scenarios such as limited exploration time. This paper proposes an automatic source search strategy, abbreviated as ACA: the location of source is estimated by a convolutional neural network (CNN), and the path is planned by the A-star algorithm. First, the search area is represented as an occupancy grid map. Then, the radiation dose distribution of the radioactive source in the occupancy grid map is obtained by Monte Carlo (MC) method simulation, and multiple sets of radiation data are collected through the eight neighborhood self-avoiding random walk (ENSAW) algorithm as the radiation data set. Further, the radiation data set is fed into the designed CNN architecture to train the network model in advance. When the searcher enters the search area where the radioactive source exists, the location of source is estimated by the network model and the search path is planned by the A-star algorithm, and this process is iterated continuously until the searcher reaches the location of radioactive source. The experimental results show that the average number of radiometric measurements and the average number of moving steps of the ACA algorithm are only 2.1% and 33.2% of those of the gradient search (GS) algorithm in the indoor environment without obstacles. In the indoor environment shielded by concrete walls, the GS algorithm fails to search for the source, while the ACA algorithm successfully searches for the source with fewer moving steps and sparse radiometric data.