- Book Chapter
- 10.1201/b19544-9
Global concepts/challenges related to the control of intelligent mobile robots
- Mar 31, 2016
- Lounis Adouane
Global concepts/challenges related to the control of intelligent mobile robots
This paper presents a methodology of distributed control system design for autonomous cooperative control of intelligent mobile robots. Following the natural concept of control architecture evolution, a bottom-up approach for control system design is presented. First, microcomputer based intelligent device modules, such as multiple infrared range finding sensor modules, and odometry and locomotor control modules, are constructed as a device manager layer on a distributed multi-microcontroller network based hardware structure to detect walls and obstacles and to move around the surroundings of a two-wheeled mobile robot. Then functional control modules, such as landmark and obstacle recognition and localization, robot motion control are implemented based on the device layer. Environment features such as lines and corners are estimated using a set of range sensors and a vision sensor. Next, some intelligent behavior modules, such as wall following, obstacle rounding, and target seeking, and environment mapping are implemented as cooperative activities based on the functional control modules. Upon these hierarchical activity modules, a non-centralized control approach is applied to implement the autonomous coordination of concurrent activities among behavior modules for the high-level tasks such as sensory navigation in unknown environments. The system integration and implementation issues are discussed for the proposed approach.
Global concepts/challenges related to the control of intelligent mobile robots
Global concepts/challenges related to the control of intelligent mobile robots
Deep–adaptive fuzzy predictive navigation framework for stable and intelligent mobile robot control
Autonomous mobile robot navigation in dynamic and uncertain environments demands control architectures that are simultaneously robust, adaptive, and provably stable. This work introduces a hierarchical predictive navigation framework that combines adaptive fuzzy decision-making with forward-looking motion optimization and explicit stability constraints.Simulation studies conducted in static, mixed, and dynamic environments demonstrate that the proposed framework achieves approximately 30–40% higher average velocity, a 25–35 % reduction in traversal time, and 5–10 % lower energy consumption per unit distance compared with conventional fuzzy–potential field and optimization-tuned fuzzy navigation baselines. Across all evaluated scenarios, the robot maintained collision-free navigation and bounded control behavior. Selective human supervision was required in fewer than 10 % of operating intervals, reducing operator involvement while preserving safety.These results indicate that the proposed framework provides a quantitatively validated and interpretable alternative to existing fuzzy-based and predictive navigation approaches for autonomous mobile robots.
Read moreDevelopment of an Autonomous Mobile Overhead Traveling Crane with on-line Obstacle Recognition and Path-Planning Based on Obstacle Information-The Design of a Transfer Control System in Consideration of Oscillating Control
This paper is introduced to be the obstacle recognition, path planning and oscillating control for an automobile crane system on-line. We studied the autonomous mobile overhead traveling crane so for. In particular, the research of obstacle recognition, path plan and oscillating control is carried out. For on-line obstacle recognition, the obstacle recognition system using the ultrasonic sensor(USS) is built. And on-line partial obstacle recognition of the conveyance environment is carried out using this obstacle recognition system. For an on-line path planning, the path plan system which it could process with the information of transfer object position and the obstacle position that is recognized by obstacle recognition system in a short time was built. The feedback transfer control system in consideration of oscillating control is built. Finally, the usefulness of the system that these were integrated is proved by an experiment. Keywords-component; Automation, Mobile Robot, Overhead Traveling Crane, On-line Path Planning, Oscillating control. I. INTORODUCTION OF THIS PAPER An overhead traveling crane system has an advantage of selecting 3rd-dimentionally and freely a transfer path achieving a freedom thereof. Therefore, automation and autonomy thereof is desired to increase the operational freedom of FMS(Flexible Manufacturing System). In the present, the overhead traveling crane is mainly operated by an expert operator to ensure safety during transferring. The development of an autonomous mobile overhead traveling crane is necessary for problem of the lack of skillful operators or the problem of work efficiency. For the reason, the results of research about an autonomous mobile overhead traveling crane system are presented by us[1],[2],[4],[5]. In particular, our research for path planning was conducted from various points of view[1],[2],[4],[5]. In a past research, we has made an experimental apparatus of on overhead traveling crane shown in Fig.1, and an autonomous mobile traveling crane system with function of the obstacle recognition, path planning on-line and oscillation control has been constructed. In this visual and planning system, when there was the change of an obstacle conveying, it was necessary for the path plan to be handled in a short time and had a problem with on-line processing in a conventional study. And the path planning system is constructed[2], [4],[5]. We propose the path-planning system that can be quickly carried out with an easy algorithm on-line. The proposed online path planning system is built using two-dimensions pathplanning algorithm[3] to perform a three-dimensional path planning[4],[5]. In this proposed system, path planning can be derived by information of target position and any obstacle position that is recognized by an ultrasonic sensor (USS). This on-line path plan method performs a path plan by the partial information of a transportation environment recognized by USS of the obstacle recognition system during transfer. The path plan of the overhead traveling crane is constructed to the goal position by repeating a suggested process (algorithm). Furthermore, the inspection of the proposed path planning method was evaluated from a view point of a qualitative and a quantitative[5]. In the present condition, the transfer control system in consideration of oscillating control was a feed-forward control system which using the notch filter. Therefore this control system had the problem that oscillating control was not completed when there was remains vibration at the time of change of a path. In this paper, 2 degrees of freedom control system which added the feedback control system to the present control system are designed. And the purpose of this research is to verify the usefulness of the on-line obstacle avoidance of the proposed autonomous mobile overhead traveling crane system. 2nd International Symposium on Computer, Communication, Control and Automation (3CA 2013) © 2013. The authors Published by Atlantis Press 468 Fig. 2 Obstacle recognition system
Read moreDeep reinforcement learning multi-sensor based navigation and control
This thesis aims to explore a novel approach in the realm of autonomous mobile robot control. It endeavors to replace the classic mobile control structure, encompassing the control system, obstacle recognition, and avoidance, and trajectory planning, with a more advanced AI-based solution using Deep Reinforcement Learning (DRL). By embracing DRL, this research seeks to uncover innovative possibilities and evaluate its effectiveness across different difficulty levels and strategies for navigating the robots. One of the key contributions of this proposed method is its ability to perform learned data-fusion from multiple sensors, including visual inputs. By assimilating information from various sources, the AI-driven system gains a more comprehensive understanding of the environment, leading to more informed decision-making and improved navigation capabilities. To achieve this objective, a series of experiments were conducted in specially designed simulation environments, created specifically for this thesis. These carefully crafted environments, based on the Robocores Robot Trekking challenge, held in 2018 (ROBOCORE, 2018), allowed for the evaluation of different levels of complexity and required skills for successful navigation and control. The results from these experiments shed light on the trade-offs between computational resources and robots performances. As the difficulty level increases, the demand for more complex and computationally demanding resources becomes apparent to sustain a high level of performance. Additionally, the suitability of the proposed method covers diverse combinations of task complexity, severity of failure consequences, and hardware availability. The implementation of this AI-driven system using DRL showcases promising prospects for achieving more efficient and robust control of autonomous mobile robots. The findings presented in this thesis offer valuable insights for the advancement and deployment of autonomous DRL-based robotic systems in real-world scenarios. The ability to perform learned data-fusion from multi sensors (IMU, GPS and encoders) including visual inputs, consists in a significant step towards enhancing the perception and decision-making capabilities of autonomous robots in complex environments.
Read moreMotion Control of Mobile Robots—From Static Targets to Fast Drives in Moving Crowds
Motion control of vehicles under uncertain, noisy, and discontinuous positioning is essential in autonomous navigation in unknown environments. This article suggests two methods for motion control, where the initial parameters of the on-line control are physically explainable, the resulting trajectory as well as the control parameters are asymptotically converging and glitches in the localization are handled robustly. The differences to a known method based on Lyapunov functions are discussed theoretically as well as in terms of actual motion measurements. Physical experiments with landbound vehicles show the reliability and limitations of these different methods in setups employing static attractors, systematically moving targets and fast, unpredictable moving targets in highly dynamical environments. Mainly due to the physical meaning of the control parameters the adaptation to actual kinematics and dynamics is significantly simplified.
Read moreCooperative motion control method for humanoid robot based on SOCP
According to the characteristics of cooperative motion control of humanoid robot, a cooperative motion model of two humanoid robot in ball handling was deduced and a control method based on second order cone principle was introduced to maintain the stability in movement for multi-robot. By deducing constraints of stability in cooperative movement, an equation of SOCP was constructed, and the stability control problem was converted for solving equations of second order cone. Finally, the effectiveness of the proposed method is verified by simulation and experiment.
Read moreResearch of Obstacle Recognition Technology in Cross-Country Environment for Unmanned Ground Vehicle
Being aimed at the obstacle recognition problem of unmanned ground vehicles in cross-country environment, this paper uses monocular vision sensor to realize the obstacle recognition of typical obstacles. Firstly, median filtering algorithm is applied during image preprocessing that can eliminate the noise. Secondly, image segmentation method based on the Fisher criterion function is used to segment the region of interest. Then, morphological method is used to process the segmented image, which is preparing for the subsequent analysis. The next step is to extract the color featureS, color featureaand edge feature “verticality” of image are extracted based on the HSI color space, the Lab color space, and two value images. Finally multifeature fusion algorithm based on Bayes classification theory is used for obstacle recognition. Test results show that the algorithm has good robustness and accuracy.
Read moreIntelligent cooperative behavior control of multiple partner robots
Recently multi-agent systems have been discussed to realize a large size of distributed autonomous system. This paper proposes an intelligent control method of multiple partner robots as one of multi-agent systems. First of all, we discuss the current state of researches on the multi-agent systems. Next, to realize a formation behavior, we propose a multi-objective behavior coordination to realize formation behavior based on the integration of the intelligent control from the local viewpoint of individual intelligence and the spring model from the global viewpoint of collective intelligence. Finally, we discuss the effectiveness of the proposed method through several computer simulation results.
Read moreQuasi Time-Fuel Optimal Control Strategy for Dynamic Target Tracking
Time and fuel balance is an important topic in the dynamic tracking problem of unmanned systems. In this paper, we propose a quasi time-fuel optimal control strategy (QTFOC) to solve the dynamic tracking problem of a double integrator system, which is capable of multi-target switching tracking tasks, such as the multi-target strike of weapons and the rapid multi-target grabbing of robots on industrial assembly lines. Compared with the previous optimal control algorithms, the proposed controller retains the time-fuel optimal characteristic when switching among multiple dynamic targets, and overcomes the high-frequency oscillation problem by incorporating local linear control region and two nonlinear buffer areas. That is, when switching among multiple dynamic targets, the proposed control strategy enables the corresponding system to achieve desired transient performance and satisfactory steady-state performance simultaneously. In addition, the asymmetry of friction load is further explored, which affects the dynamic performance of the actual system. Extensive experiments based on the visual tracking turntable demonstrate the superiority and feasibility of the proposed method. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper was motivated by the problem of multi-target switching tracking, such as the multi-target strike of weapons with vision sensors and the rapid multi-target grabbing of robots on industrial assembly lines. In recent years, various algorithms have been developed for trajectory planning and tracking. However, it is still challenging for unmanned servo system to capture dynamic targets quickly due to the constrains of motion performance, energy, and computational power. In order to reduce the computational burden and obtain ideal response under various physical constraints, a quasi time-fuel optimal control strategy (QTFOC) with analytical solutions is proposed in this paper. First, the static target is extended to the dynamic target by further investigating the traditional time-fuel optimal control theory for double integrator system. Second, to deal with the oscillation problem caused by system disturbances, we incorporate buffer areas and local linear control region into the control algorithm, which makes the system more robust. Third, the system performance is further improved by analyzing the frictional load asymmetry. This algorithm requires small computational resources and can be implemented directly on microcontrollers such as STM32. The experimental results demonstrate the superiority of our proposed method in handling the multi-target switching tracking problem, which can also adjust the response speed weight, making the unmanned system perform better under different operating conditions. Furthermore, the proposed QTFOC can be extended to other unmanned systems, such as trajectory planning and motion control for unmanned vehicles and bionic robots.
Read more1313 距離と視覚センサの併用による自律移動ロボットの知的走行制御
1313 距離と視覚センサの併用による自律移動ロボットの知的走行制御
US reconfirms anti-dumping duties on Indian & Chinese carbazole violet
US reconfirms anti-dumping duties on Indian & Chinese carbazole violet
The use of modal logic in the task of self-learning intelligent robots
In this paper, the principal possibility of using modal logic in the tasks of self-learning of intelligent mobile robots operating in an unknown environment is considered. The methodology for creating a model of the intelligent mobile robot control system with a self-learning module is presented. The basic principles and concepts of modal logic are described. To substantiate the applicability of the selected apparatus, the problem of automatic control strategy formation based on dynamically replenished sensory information is considered. The experimental testing of the obtained model is carried out.
Read moreDesign of Intelligent Inventory Robot Control System and its Application Practice in Library Book Inventory
Book inventory is an important foundational work in library literature management. The library uses intelligent book inventory robots to automatically scan the books on the shelves, obtain detailed information about the books, quickly update the location information of the books, and facilitate readers to quickly find the corresponding books. At the same time, it can also facilitate library staff to organize books. This article proposes a design scheme for an intelligent book inventory robot control system, which mainly consists of a positioning and navigation module, a spatial movement module, a data acquisition module, a power management module, and a main control module. The book inventory robot combines positioning technology and RFID technology, which can accurately locate books in complex environments and achieve automatic book inventory. Through the example of using intelligent book inventory robots in libraries, analyze various factors that affect the efficiency and accuracy of intelligent book inventory robots, improve usage methods, and enhance usage effectiveness.
Read moreRobust design of vibration suppression control system for crane using sway angle observer considering friction disturbance
It is desirable for a container crane to operate smoothly and quickly. For this purpose, the control system of a container crane should be capable of antisway control for suppressing vibrations. A vision sensor system is often used to detect the sway angle. However, since a control system with a vision sensor has a delay time when determining the angle, it sometimes leads to deterioration of control performance owing to the delay time. In order to overcome this problem, this paper proposes a new antisway crane control system based on a dual‐state observer with sensor‐delay correction. However, because of nonlinear friction in the crane, the estimation accuracy achieved by using the observer is poor. To overcome this problem, this paper proposes a disturbance observer considering friction disturbance. The control performance and effectiveness of the proposed robust control system based on the estimated information are shown to be satisfactory by experimental results. © 2013 Wiley Periodicals, Inc. Electr Eng Jpn, 184(3): 36–46, 2013; Published online in Wiley Online Library (wileyonlinelibrary.com). DOI 10.1002/eej.22412
Read moreA self-secure system based on software-defined network
Software Defined Network (SDN) redefines and abstracts the functions of the control layer, forwarding layer, and application layer of network devices, making network device software programmable, better supporting dynamic control of network traffic, and making up for the natural defects of traditional networks. Now it has been adopted in many application fields. Therefore, the security of SDN has also received more and more attention. The research on self-secure SDN has become vital important. Self-secure SDN can ensure its own security, not only actively detect network attacks, but also effectively predict and defend attacks. This paper designs a self-secure system based on software-defined network. The system mainly includes three functional modules: 5G user classification, application identification and abnormal traffic detection. Through the system designed in this paper, we can not only view the traffic and user information of the network loaded with this software-defined network-based self-secure system, but also enable or disable these traffic and users. After testing, the system designed in this paper is of great help to the improvement of the security of a software-defined network.
Read more