Autonomous Mobile Robot System Research Articles

Improved KNN Scan Matching for Local Map Classification in Mobile Robot Localisation Application

Localisation is essential for autonomous mobile robot system enabling it to locate itself within its environment. One method to perform localisation is to use scan matching with iteration closest point (ICP) algorithm. However, typical ICP may be prone to inaccuracies in localisation and mapping due to problems associated with laser range data limitation such as overshoot data and blank data. This paper presents the improvement to the above problem by the inclusion of a threshold to the KNN scan matching algorithm during iteration process. The threshold is a percentage of nearest point of incoming input with respected to reference point. Threshold values of 0%, 70% and 90% were tested, and improvements of the classification performance were observed with the increase in the threshold values, with the latter achieving 100% accuracy. This work shows that the use of threshold in scan matching may improve the accuracy of local map classification.

Incorporating Trust and Self-Confidence Analysis in the Guidance and Control of (Semi)Autonomous Mobile Robotic Systems

We propose a trust and self-confidence-based autonomy allocation strategy to automatically choose between manual and autonomous control of (semi)autonomous mobile robots in guidance and navigation tasks. We utilize a performance-centric, computational trust and self-confidence model and automated autonomy allocation strategy, developed in our earlier work (H. Saeidi and Y. Wang, “Trust and self-confidence based autonomy allocation for robotic systems,” in Proc. 54th IEEE Conf. Decis. Control , 2015, pp. 6052–6057.), based on objective and unbiased performance measures for the human and the robot. A set of robot simulations with a human-in-the-loop is conducted for a teleoperated unmanned aerial vehicle tracking task. The results demonstrate that our allocation strategy can capture human autonomy allocation pattern with an accuracy of 64.05%. We also show that the strategy can improve the overall robot performance by 11.76% and reduce operator's workload by 10.07% compared to a manual allocation. Moreover, compared to a performance maximization strategy, our strategy is 23.42% more likely to be accepted and generally preferred and trusted by the participants. Furthermore, we design a decision pattern correction algorithm based on nonlinear model predictive control to help a human operator gradually adapt to a modified allocation pattern for improved overall performance.

Shape formation by programmable particles

Shape formation is a basic distributed problem for systems of computational mobile entities. Intensively studied for systems of autonomous mobile robots, it has recently been investigated in the realm of programmable matter. Namely, it has been studied in the geometric Amoebot model, where the anonymous entities, called particles, operate on a hexagonal tessellation of the plane and have limited computational power (they have constant memory), strictly local interaction and communication capabilities (only with particles in neighboring nodes of the grid), and limited motorial capabilities (from a grid node to an empty neighboring node); their activation is controlled by an adversarial scheduler. Recent investigations have shown how, starting from a well-structured configuration in which the particles form a (not necessarily complete) triangle, the particles can form a large class of shapes. This result has been established under several assumptions: agreement on the clockwise direction (i.e., chirality), a sequential activation schedule, and randomization (i.e., particles can flip coins). In this paper we provide a characterization of which shapes can be formed deterministically starting from any simply connected initial configuration of $n$ particles. As a byproduct, if randomization is allowed, then any input shape can be formed from any initial (simply connected) shape by our algorithm, provided that $n$ is large enough. Our algorithm works without chirality, proving that chirality is computationally irrelevant for shape formation. Furthermore, it works under a strong adversarial scheduler, not necessarily sequential. We also consider the complexity of shape formation in terms of both the number of rounds and of moves performed by the particles. We prove that our solution has a complexity of $O(n^2)$ rounds and moves: this number of moves is also asymptotically optimal.

Field research of drag-and-traction characteristics of mobile robotic system in coastal zone

Measurement results of drag-and-traction characteristics of autonomous mobile robotic system (AMRS) for coastal zones monitoring designed in NSTU n.a. R.E. Alekseev are given in this article. Description of the tests, equipment for measuring drag and resistance to motion force are presented. Experimental values of the measured forces are given and theoretical and experimental data are compared for chassis with wheeled and track-modular running gears.

Socio-realistic optimal path planning for indoor realtime autonomous mobile robot navigation

An autonomous mobile robotic navigation system consists of many modules which work co-ordinately and concurrently. The most important module is the realistic and optimal path planning algorithm (ROPPA) through which the overall system improves it performance. Many algorithms have been developed and deployed for data structures, and computer games are partially modified for use in real time robotic environments. The major drawback of such modified algorithms is they are designed for unconstrained artificial environments where the robot's collision with a static obstacle or moving object is partially allowed. Many researchers successfully developed the path planning algorithm through improving the basic A* algorithm, such as D* lite, theta*, any angle path planning, and jump point search. In real environments one should seek the optimal path along with maintaining uniform safer distance with the objects or in-path obstacles. This paper describes the implementation and evaluation of a new realistic optimal path planning algorithm which follows the safer distance rule through exploring minimum workspace arena. Along with less memory overhead, the algorithm explores shortest final path with fewer sub-paths if they exist. The experimentation with different map sizes and obstacle densities clearly defines improvement in ROPPA over the other path planning methods.

Development of an easy teaching and simulation solution for an autonomous mobile robot system

Abstract With mass customized production becoming the mainstream, industries are shifting from large-scale manufacturing to flexible and customized production of small batch sizes. Agile manufacturing strategies adopted by SMEs are driving the usage of collaborative robots in today’s factories. Major challenges in the adoption of cobots in the industry are the lack of a highly trained workforce to program the robot to perform complex tasks and integration of robot systems to other smart devices in the factory. In addition, the teaching and simulation by non-robotics experts of many industrial collaborative robot systems like the KUKA LBR iiwa is a major challenge, since these systems are designed to be programmed by robot experts and not by shop floor workers or other nonexperts. This paper describes the research and development activities done for reducing the barriers in operation and ensure holistic integration of LBR iiwa cobot in the assembly on the example of the ESB Logistics Learning Factory. These include a visual programming solution for the easy teaching of various tasks. Robotics tasks are classified based on common robotics applications and application-specific blocks abstracting specific actions are implemented. A factory worker with no programming competency could create robot programs by combining these blocks using a Graphical User Interface. In addition, a simulation solution was developed to visualize, analyse, and optimize robotic workflow before deployment. An autonomous mobile robot is integrated with the LBR iiwa to improve reconfigurability and thus also the productivity. The system as a whole is controlled using an event-driven distributed control system. Finally, the capabilities of the system are analysed based on the design principles of Industrie 4.0 and potential future research ideas are discussed to further improve the system.

주차장 관리를 위한 ROS 기반 자율주행 이동로봇의 원격 제어 및 Visual SLAM에 관한 연구

Automation of the parking lot is required due to the labor cost burden and labor shortage. Because the developed parking lot management system (PLMS) is used in only billing the parked cars, the unmanned (PLMS) must be developed. In this paper, we proposed an autonomous mobile robot and control system for unmanned parking lot management. This robot monitors incidents as well as illegally parked vehicles while monitoring the parking lot information and the robot position is estimated by fusing the dead reckoning with inertial measurement unit. After application of the developed autonomous (PLMS) to the real parking lot, we confirmed the usefulness of the proposed PLMS.

Sliding Mode Controller for Trajectory Tracking Control of Autonomous Mobile Robot

Trajectory tracking control is an important issue in the field of autonomous mobile robot. In high speed and heavy load applications, the dynamic of autonomous mobile robot plays an important factor in allowing the robot to follow the desired trajectory path. However, the parameters attribute to robot dynamic are difficult to model and highly uncertain. One of the uncertainty factors is the load variation which changes the dynamic parameters of autonomous mobile robot. Meanwhile, Sliding Mode Control (SMC) is well known for its robustness against model uncertainties and disturbances. This paper is about design of dynamic controller based on SMC technique for trajectory tracking control of autonomous mobile robot system. The model of mobile robot is developed based on Pioneer 3-DX mobile robot. The trajectory tracking controller is divided into two parts, kinematic controller and dynamic controller. Stability of both dynamic and kinematic controller is verified using Lyapunov stability theory. The performance of trajectory tracking control for proposed dynamic controller based on SMC technique is compared against dynamic controller based on Proportional-Integral-Derivative (PID) technique with and without the presence of dynamic uncertainties. Simulation results show proposed dynamic controller based on SMC technique give better performance in trajectory tracking control in comparison to PID.

Localization System for Autonomous Mobile Robots Using Machine Learning Methods and Omnidirectional Sonar

In the past few years, the mobile robotics has presented a growth in the research field, due to its high application area. The robot localization and its displacement in an unknown environment are fundamental to its operation. Signal processing techniques, machine learning methods, and sensors assist in the environment mapping, localization, and displacement of the mobile robot in the environment. In this paper, five machine learning techniques used: Bayes, MLP, KNN, SVM and OPF. We have used the following evaluation metrics: accuracy, sensitivity, and specificity obtained through matrices of confusion. This paper has as certain objective the analysis of the machine learning methods for later use in an embedded system. The OPF method using Canberra distance obtained an accuracy of 98.13% and is, therefore, the most appropriate method to use on the proposed location system.

Deep spatiotemporal models for robust proprioceptive terrain classification

Terrain classification is a critical component of any autonomous mobile robot system operating in unknown real-world environments. Over the years, several proprioceptive terrain classification techniques have been introduced to increase robustness or act as a fallback for traditional vision based approaches. However, they lack widespread adaptation due to various factors that include inadequate accuracy, robustness and slow run-times. In this paper, we use vehicle-terrain interaction sounds as a proprioceptive modality and propose a deep long-short term memory based recurrent model that captures both the spatial and temporal dynamics of such a problem, thereby overcoming these past limitations. Our model consists of a new convolution neural network architecture that learns deep spatial features, complemented with long-short term memory units that learn complex temporal dynamics. Experiments on two extensive datasets collected with different microphones on various indoor and outdoor terrains demonstrate state-of-the-art performance compared to existing techniques. We additionally evaluate the performance in adverse acoustic conditions with high-ambient noise and propose a noise-aware training scheme that enables learning of more generalizable models that are essential for robust real-world deployments.

Development of an autonomous bridge deck inspection robotic system

AbstractThe threat to safety of aging bridges has been recognized as a critical concern to the general public due to the poor condition of many bridges in the United States. Currently, the bridge inspection is conducted manually, and it is not efficient to identify bridge condition deterioration in order to facilitate implementation of appropriate maintenance or rehabilitation procedures. In this paper, we report a new development of the autonomous mobile robotic system for bridge deck inspection and evaluation. The robot is integrated with several nondestructive evaluation (NDE) sensors and a navigation control algorithm to allow it to accurately and autonomously maneuver on the bridge deck to collect visual images and conduct NDE measurements. The developed robotic system can reduce the cost and time of the bridge deck data collection and inspection. For efficient bridge deck monitoring, the crack detection algorithm to build the deck crack map is presented in detail. The impact‐echo (IE), ultrasonic surface waves (USW), and electrical resistivity (ER) data collected by the robot are analyzed to generate the delamination, concrete elastic modulus, corrosion maps of the bridge deck, respectively. The presented robotic system has been successfully deployed to inspect numerous bridges in more than ten different states in the United States.

Navigation of non-holonomic mobile robot using neuro-fuzzy logic with integrated safe boundary algorithm

In the present work, autonomous mobile robot (AMR) system is intended with basic behaviour, one is obstacle avoidance and the other is target seeking in various environments. The AMR is navigated using fuzzy logic, neural network and adaptive neuro-fuzzy inference system (ANFIS) controller with safe boundary algorithm. In this method of target seeking behaviour, the obstacle avoidance at every instant improves the performance of robot in navigation approach. The inputs to the controller are the signals from various sensors fixed at front face, left and right face of the AMR. The output signal from controller regulates the angular velocity of both front power wheels of the AMR. The shortest path is identified using fuzzy, neural network and ANFIS techniques with integrated safe boundary algorithm and the predicted results are validated with experimentation. The experimental result has proven that ANFIS with safe boundary algorithm yields better performance in navigation, in particular with curved/irregular obstacles.

Autonomous Mobile Robotic System for Environment Monitoring in a Coastal Zone

Definition of optimum conditions for monitoring coastal zones, especially for the places which are poorly provided with supervision, belongs to one of important tasks of the forecast of marine natural disasters. The project includes the development of technology for monitoring and forecasting the state of environment of a coastal zone by autonomous mobile robotic system (AMRS). The structural composition of the robotic complex for coastal zone monitoring is presented. The special modular design of the AMRS chassis for functioning in various climatic and landscape conditions is described. Information of monitoring system, positioning system, meteorological system, vehicle control and obstacles detection system is also given within the paper. The results of the first field tests of the AMRS on the coast of the Okhotsk Sea are presented.

屋内外をシームレスに走行が可能なロボット及びナビゲーションシステムに関する研究

In recent years, not only industrial robot used in the manufacturing site, the use of a service robot for performing alternate or supplementary work of humans is increasingly robot. So we aim to build the system of mobile service robot with a seamless navigable sensor integrated system regardless of the indoor and outdoor for Large Scale facility using the internal sensor and external sensor, environment map information, the indoor positioning system. In this research, using the rotary encoder to the internal sensor, and using the LRF to external sensor, using the IMES for positioning system to develop an autonomous mobile robot system. We report the results of the evaluation by the running experiment.

Trajectory Planning and Collision Avoidance Algorithm for Mobile Robotics System

The field of autonomous mobile robotics has recently gained many researchers’ interests. Due to the specific needs required by various applications of mobile robot systems, especially in navigation, designing a real time obstacle avoidance and path following robot system has become the backbone of controlling robots in unknown environments. Therefore, an efficient collision avoidance and path following methodology is needed to develop an intelligent and effective autonomous mobile robot system. This paper introduces a new technique for line following and collision avoidance in the mobile robotic systems. The proposed technique relies on the use of low-cost infrared sensors, and involves a reasonable level of calculations, so that it can be easily used in real-time control applications. The simulation setup is implemented on multiple scenarios to show the ability of the robot to follow a path, detect obstacles, and navigate around them to avoid collision. It also shows that the robot has been successfully following very congested curves and has avoided any obstacle that emerged on its path. Webots simulator was used to validate the effectiveness of the proposed technique.

Map-based navigation and control of mobile robots with surveillance cameras

Recent research study on obstacle detection and path planning in unknown environments has been identified as a key issue in the development of autonomous mobile robotic systems. This paper presents a path planning and control strategy for blind robots in indoor environments. In particular, a systematic approach is employed to convert 3D and 2D navigation maps from a 3D sparse map established by a scout robot equipped with onboard vision using a VSLAM (visual simultaneous localisation and mapping) algorithm. Based on the navigation map, desired trajectory can be planned for a blind robot to reach the target. An effective image-based control law is proposed to drive the blind robot to follow the planned trajectory with real-time monocular camera vision. The proposed navigation and control system has been validated by simulations and experiments with a blind robot using a 3D sparse map and real-time vision from surveillance cameras.

Hybrid Autonomous Sensor-Based Recognition Fuzzy Mobile Robot System Designs

The autonomous stratagem combines the concepts of traveling salesman problems (TSP), radio frequency identification (RFID), E-compass wireless networks sensors and the evolutional particle swarm optimization (PSO) to identify the optimal routing paths in the dynamic indoor space. A desired the setting lot as soon as possible. Four active RFID tags amounted in the rectangle type environments and indication of E-compass are proposed to identify the robot position. The routing concept of the TSP is developed by the evolutionary PSO learning scheme to approach the valid routing-path of the mobile robot. The developed mobile robot system, with the proper number of fuzzy membership functions, simultaneously achieves the multiple objectives of avoiding obstacles by the selected shortest routing path.

自律型移動サッカーロボット"Braves-1"における制御システムの開発と検証

自律型移動サッカーロボット"Braves-1"における制御システムの開発と検証

1A1-J02 自律移動ロボットフレームワークの提案とRTミドルウェアへの実装

1A1-J02 自律移動ロボットフレームワークの提案とRTミドルウェアへの実装

Mobile Robot Navigation Techniques Using Potential Field Method in Unknown Environments

In this paper, a navigation system for autonomous mobile robots that move into unknown environments based on artificial potential field is presented. The robot moves to a predefined target point while detects and maps every encounter object using its artificial monocular vision system based on intrinsic camera parameters. During navigation, every obstacle is associated with a repulsive field depending on the distance and relative position to the robot, while the target point has an attractive field. Combining those values of potential field defines the direction of the next step of the robot. The results reported are showing the behavior of the method in three scenarios, avoiding obstacles, going through a narrow corridor and escaping from a minimum local trap.