Method For Autonomous Mobile Robots Research Articles

Navigation method for autonomous mobile robots based on ROS and multi-robot improved Q-learning

Navigation method for autonomous mobile robots based on ROS and multi-robot improved Q-learning

Dynamic obstacle avoidance method for autonomous mobile robot based on machine vision

Dynamic obstacle avoidance method for autonomous mobile robot based on machine vision

Unsupervised dissimilarity-based fault detection method for autonomous mobile robots

Unsupervised dissimilarity-based fault detection method for autonomous mobile robots

Complete coverage planning with clustering method for autonomous mobile robots

SummaryComplete coverage planning (CCP) is a task to cover the entire area on the map, according to the job description of the autonomous mobile robot. The most widely used method for CCP in the literature is the grid‐based coverage method. In this method, the problem is processing the partially filled cell as completely filled, which reduces the coverage performance. The ability to use the clustering method, which will be created by considering the characteristics of the environment, was determined as a research question to solve this problem. In this direction, it is aimed to use K‐means++ algorithm, which is a widely used clustering algorithm and segmentation technique. In this context, an offline K‐means++ complete coverage planning (Km++CCP) method, in which the navigable area on the map of the indoor where a mobile robot will navigate is clustered using the K‐means++ algorithm and the centroids can be used as waypoints, is proposed. To test the proposed method, 2 simulations and 36 real‐world experiments were conducted. The indoor coverage ratio of Km++CCP was calculated higher than the grid‐based method in all experiments.

Turning at Intersections Using Virtual LiDAR Signals Obtained from a Segmentation Result

We implemented a novel visual navigation method for autonomous mobile robots, which is based on the results of semantic segmentation. The novelty of this method lies in its control strategy used for a robot during road-following: the robot moves toward a target point determined through semantic information. Previous implementations of the method sometimes failed to turn at an intersection owing to a fixed value of the turning angle. To address this issue, this study proposes a novel method for turning at an intersection using a control method based on a target point, which was originally developed for road-following. Here, an intersection is modeled as consisting of multiple straight roads. Evaluation using the CARLA simulator showed that the proposed method could accurately estimate the parameters representing a virtual road composing an intersection. In addition, run experiments conducted at the Ikuta Campus of Meiji University using an actual robot confirmed that the proposed method could appropriately make turns at intersections.

Development of an Intelligent Vital Sign Monitoring Robot System

We want to solve the problem that the elderly or heart patients will not miss the golden time for rescue incase of sudden death or emergency event at home. Therefore, this work proposes an intelligent vital signmonitoring robot system. Considering data protection and privacy issues, the heart rate of the elderly or heart patient can be measured and monitored through the millimetre wave radar on an autonomous mobilerobot (AMR). Additionally, by object detection technology, the infrared thermal imager is integrated todetect the temperature of a person’s head. The measured head temperature, thermal image and heart ratedata can be uploaded to cloud database with blockchain technology to prevent data tampering. We develop an interrupt method for multi-target navigationof AMR to interrupt the patrol when a custom triggersituation happened and to run the interrupt process for vital signs measurement. While the interrupt process is completed, the robot will patrol again. When the system detects an abnormal situation, familymembers or caregivers can be notified through IFTTT service and Line notification messages. The systemcan help us to monitor the situations of elderly and provide response in time when a sudden emergencyevent or health crisis happened.

Robot Navigation Using Experience-Based Cost Prediction with Image-based 3D Terrain Reconstruction

We propose a motion optimization method for autonomous mobile robots that minimizes transition cost when a mobile robot traverses uneven terrain. The proposed method is able to reflect traversing cost of bumps to trajectory planning of robot including posture of bumps. The proposed method is implemented with a mobile robot platform and evaluated by experiment of navigation to find an appropriate route in uneven terrain environment.

Development of Autonomous Mobile Robot “MML-05” Based on i-Cart Mini for Tsukuba Challenge 2015

[abstFig src='/00280004/04.jpg' width='300' text='Autonomous mobile robots entered in the Tsukuba Challenge 2015' ] This paper describes a self-localization method for autonomous mobile robots entered in the Tsukuba Challenge 2015. One of the important issues in autonomous mobile robots is accurately estimating self-localization. An occupancy grid map, created manually before self-localization has typically been utilized to estimate the self-localization of autonomous mobile robots. However, it is difficult to create an accurate map of complex courses. We created an occupancy grid map combining local grid maps built using a leaser range finder (LRF) and wheel odometry. In addition, the self-localization of a mobile robot was calculated by integrating self-localization estimated by a map and matching it to wheel odometry information. The experimental results in the final run of the Tsukuba Challenge 2015 showed that the mobile robot traveled autonomously until the 600 m point of the course, where the occupancy grid map ended.

Development of Autonomous Mobile Robot Based on Accurate Map in the Tsukuba Challenge 2014

<div class=""abs_img""> <img src=""[disp_template_path]/JRM/abst-image/00270004/04.jpg"" width=""300"" /> Navigation method for mobile robots</div> We describe a navigation method for autonomous mobile robots and detail knowledge obtained through Tsukuba Challenge 2014 trial runs. The challenge requires robots to navigate autonomously 1.4 km in an urban area and to search for five persons in three areas. Accurate maps are important tools in localization on complex courses in autonomous outdoor navigation. We constructed an occupancy grid map using laser scanners, gyro-assisted odometry and a differential global positioning system (DGPS). In this study, we use maps as a graphical interface. Namely, by using maps, we give environmental information, untravelable low objects such as curb stones, and areas in nonsearches for “target” persons. For the purpose of increasing the map reusability, we developed a waypoint editor, which can modify waypoints on maps to fit a course to a situation. We also developed a velocity control method that the robot uses to follow pedestrians and other robot by keeping safety distance on the course. As a result, our robot took part five of seven official trial runs to get to the goal. This indicates that the autonomous navigation method was stable in the Tsukuba Challenge 2014 urban environment. </span>

Motion planning of autonomous mobile robots by iterative dynamic programming

We propose a new offline motion planning method for autonomous mobile robots. To minimize traveling time, a smooth path and a time-optimal velocity profile should be generated under kinematic and dynamic constraints. In this study, we develop an effective and practical method to generate a good solution with lower computation time. The initial path is obtained from a Voronoi diagram and spline function, and is improved by iteratively changing via-points. We apply a dynamic programming algorithm to change the via-points, and a Hermite interpolation to generate a smooth trajectory. Simulation results are presented to verify the performance of the proposed method.

Development of the Autonomous Mobile Robot for Target-Searching in Urban Areas in the Tsukuba Challenge 2013

This paper describes a navigation method for autonomous mobile robots and the knowledge obtained through trial runs conducted during the Tsukuba Challenge 2013 whose main tasks were autonomous navigation by robots to a goal and searching for target persons in several urban areas. Accurate maps are an important tool in localization on complex courses. We constructed occupancy grid map making method using laser scanners, gyro-assisted odometry and a DGPS. In trial runs, robots detect target parsons two ways – one involving color detection in images and the other involving laser scanner intensity data. The major problem with these methods is misdetection. To minimize this, we mask areas in which target persons should not exist on occupancy grid maps. Target candidates detected in masked areas are rejected, which indicates the possibility of using accurate occupancy grid maps as a user-friendly graphical interface. This paper focuses on the localization method, the target detection method and autonomous navigation knowledge in common space through the challenge.

Obstacle Displacement Prediction for Robot MotionPlanning and Velocity Changes

This paper introduces a new path-motion planning method for autonomous mobile robot which should move safely in unknown Dynamic environment. The environment may have numbers of obstacles of arbitrary shape and obstacles are allowed to move. We describe our approach to solve the motion-planning problem, using neural networks-based technique .The neural network is used to model the obstacles motion and predict their movements. According to one step ahead prediction of obstacle's trajectory, a rule-based technique for avoiding obstacles by adjusting the robot's velocity is suggested .This sensor based online method gives a safe but near optimal path. Simulation examples of generated path with proposed techniques will be presented and show the efficiency of the method. used to know the one step ahead and final destination of the obstacle. The prediction was combined to a POMDP method to control robot movement. In another work a probabilistic model of uncertainty is used in (6). The planning algorithm is based on an extension of the Rapidly-exploring Random Tree algorithm, where the obstacles trajectory and the probability of collision are explicitly taken into account. The algorithm is used in a partial motion planner, and the probability of collision is updated in real-time. The proposed method in (7) combines a dynamic occupancy grid with the Probabilistic Velocity Obstacle (PVO). The velocity space was considered and, under the hypothesis of linear constant velocity of the obstacles, the probability of collision was estimated for each possible linear velocity of the robot. The limits of the perception system, such as sensor range and occlusions, and the uncertainties on position and velocity estimation, contribute directly to the computation of the probability of collision. In all of these works because of inclusion of robot and obstacles' velocity in the formulation, the complexity of solution increases. We choose not to include the speed of the robot, or include speed actions in the action set and In the formulation of the problem. We prefer to use robot or obstacle displacement instead, to make ease in computation. This choice would further decrease the complexity of solution.

Variable-resolution Velocity Roadmap Generation Considering Safety Constraints for Mobile Robots

This research develops a new roadmap method for autonomous mobile robots based on variable-resolution partitioning of continuous state space. Unlike conventional roadmaps which include position information only, the proposed roadmap also includes velocity information. Each node of the proposed roadmap consists of a fixed position and a range of velocity values, where velocity ranges are determined by variable-resolution partitioning of velocity space. An ordered pair of nodes are connected by a directed link if any combination of velocity values within the ranges represented by the nodes produce a trajectory satisfying a set of safety constraints. In this manner, an executable trajectory connecting arbitrary starting node and destination node is obtained by applying a graph search technique on the proposed roadmap. The proposed method is evaluated through simulations.

Self-Supervised Online Long-Range Road Estimation in Complicated Urban Environments

In this paper, we propose a long-range road estimation method for autonomousmobile robots in unstructured urban environments. Near-range road surface conditions are estimated by using remission value as reflectivity of a laser scanner. Graph cut algorithm is applied to estimate road region robustly also in complicated environments. Moreover, we propose a novel image segmentation method to estimate long-range road surface. A compact texture/color feature is integrated with level-set method to estimate precise road boundaries robustly. Our proposed image segmentation approach gives better performance compared with standard classification approach. Finally, we run our autonomous mobile robot in “Tsukuba Challenge 2009” and our university campus, and experimental results have shown a marked increase accuracy in road estimation over standard methods.

STEREOVISION-BASED FUZZY OBSTACLE AVOIDANCE METHOD

This work presents a stereovision-based obstacle avoidance method for autonomous mobile robots. The decision about the direction on each movement step is based on a fuzzy inference system. The proposed method provides an efficient solution that uses a minimum of sensors and avoids computationally complex processes. The only sensor required is a stereo camera. First, a custom stereo algorithm provides reliable depth maps of the environment in frame rates suitable for a robot to move autonomously. Then, a fuzzy decision making algorithm analyzes the depth maps and deduces the most appropriate direction for the robot to avoid any existing obstacles. The proposed methodology has been tested on a variety of self-captured outdoor images and the results are presented and discussed.

Smooth Path Planning Method for Autonomous Mobile Robots Using Cardinal Spline

We propose a smooth path planning method for autonomous mobile robots. Due to nonholonomic constraints by obstacle avoidance, the smooth path planning is a complicated one. We generate smooth path that is considered orientation of robot under nonholonomic constraints. The proposed smooth planning method consists of two steps. Firstly, the initial path composed of straight lines is obtained from V-graph by Dijkstra's algorithm. Then the initial path is transformed by changing the curve. We apply the cardinal spline into the stage of curve generation. Simulation results show a performance of proposed smooth path planning method.

동적프로그래밍을 이용한 자율이동로봇의 동작계획

We propose a motion planning method for autonomous mobile robots. In order to minimize traveling time, a smooth path and a time optimal velocity profile should be generated under kinematic and dynamic constraints. In this paper, we develop an effective and practical method to generate a good solution with lower computation time. The initial path is obtained from voronoi diagram by Dijkstra's algorithm. Then the path is improved by changing the graph and path simultaneously. We apply the dynamic programming algorithm into the stage of improvement. Simulation results are presented to verify the performance of the proposed method.

CPU와 GPU의 병렬 처리를 이용한 고속 물체 인식 알고리즘 구현

This paper presents a fast feature extraction method for autonomous mobile robots utilizing parallel processing and based on OpenMP, SSE (Streaming SIMD Extension) and CUDA programming. In the first step on CPU version, the algorithms and codes are optimized and then implemented by parallel processing. The parallel algorithms are debugged to maintain the same level of performance and the process for extracting key points and obtaining dominant orientation with respect to key points is parallelized. After extraction, a parallel descriptor via SSE instructions is constructed. And the GPU version also implemented by parallel processing using CUDA based on the SIFT. The GPU-Parallel descriptor achieves an acceleration up to five times compared with the CPU-Parallel descriptor, but it shows the lower performance than CPU version. CPU version also speed-up the four and half times compared with the original SIFT while maintaining robust performance.

확장 칼만 필터를 이용한 로봇의 실내위치측정

본 논문에서는 Inertial Navigation System (INS)와 Ultrasonic-SATellite (U-SAT)의 센서융합을 기반으로 100mm 이하의 정밀위치측정 시스템을 보여준다. INS는 자이로와 두 개의 엔코더로 구성되고, U-SAT는 네 개의 송신기와 한 개의 수신기로 구성하였다. 구성된 센서들은 정밀한 정밀위치측정을 위하여 Extended Kalman Filler (EKF)를 통해 센서들을 융합하였다. 위치측정의 성능을 증명하기 위해 본 논문에서는 로봇이 0.5 m/s의 속도로 주행한 실제 데이터(직진, 곡선)와 시뮬레이션을 통한 실험을 하였으며, 실험에 사용된 위치측정방법은 일반적인 센서융합과 INS 데이터만을 칼만 필터에 이용한 센서융합을 비교하였다. 시뮬레이션과 실제 데이터를 통해 실험한 결과, INS 데이터만을 칼만 필터에 이용한 센서융합이 더 정밀함을 확인할 수 있었다. This paper is presented an accurate localization scheme for mobile robots based on the fusion of ultrasonic satellite (U-SAT) with inertial navigation system (INS), i.e., sensor fusion. Our aim is to achieve enough accuracy less than 100 mm. The INS consist of a yaw gyro, two wheel-encoders. And the U-SAT consist of four transmitters, a receiver. Besides the localization method in this paper fuse these in an extended Kalman filter. The performance of the localization is verified by simulation and two actual data(straight, curve) gathered from about 0.5 m/s of driving actual driving data. localization methods used are general sensor fusion and sensor fusion through Kalman filter using data from INS. Through the simulation and actual data studies, the experiment show the effectiveness of the proposed method for autonomous mobile robots.

자율이동로봇을 위한 동적 경로 계획 방법

We propose a new path planning method for autonomous mobile robots. To maximize the utility of mobile robots, the collision-free shortest path should be generated by on-line computation. In this paper, we develop an effective and practical method to generate a good solution by lower computation time. The initial path is obtained from skeleton graph by Dijkstra`s algorithm. Then the path is improved by changing the graph and path dynamically. We apply the dynamic programming algorithm into the stage of improvement. Simulation results are presented to verify the performance of the proposed method.