Robot Obstacle Research Articles

HYBRID COMMUNICATION NETWORK OF MOBILE ROBOT AND QUAD-COPTER

This paper introduces the design and development of QMRS (Quadcopter Mobile Robotic System). QMRS is a real-time obstacle avoidance capability in Belarus-132N mobile robot with the cooperation of quadcopter Phantom-4. The function of QMRS consists of GPS used by Mobile Robot and image vision and image processing system from both robot and quad-copter and by using effective searching algorithm embedded inside the robot. Having the capacity to navigate accurately is one of the major abilities of a mobile robot to effectively execute a variety of jobs including manipulation, docking, and transportation. To achieve the desired navigation accuracy, mobile robots are typically equipped with on-board sensors to observe persistent features in the environment, to estimate their pose from these observations, and to adjust their motion accordingly. Quadcopter takes off from Mobile Robot, surveys the terrain and transmits the processed Image terrestrial robot. The main objective of research paper is to focus on the full coordination between robot and quadcopter by designing an efficient wireless communication using WIFI. In addition, it identify the method involving the use of vision and image processing system from both robot and quadcopter; analyzing path in real-time and avoiding obstacles based-on the computational algorithm embedded inside the robot. QMRS increases the efficiency and reliability of the whole system especially in robot navigation, image processing and obstacle avoidance due to the help and connection among the different parts of the system.

Hybrid position/virtual-force control for obstacle avoidance of wheeled robots using Elman neural network training technique

The hybrid force position control algorithm based on neural network is considered for a class of robot system with nonlinear uncertainties. Compared with previous work, not only the steady-state performance but also the transient-state performance is considered. Firstly, in order to relax the control design dependent on detailed system information, a fast hybrid position/virtual-force controller is presented to build a virtual-force field between the obstacles and robot. The virtual force is the control parameter, which is set to maintain an expected distance between obstacles and the robot with unknown nonlinear and parameter uncertainty. Secondly, in order to alleviate the computation burden of parameter learning, and enhance the dynamic mapping of network ability, the Elman neural network is introduced. The output signal come from hybrid position/virtual-force controller is fed back to Elman neural network. Furthermore, since uncertainties of robot dynamics and obstacle location information, Elman neur...

Obstacle Avoidance Mobile Robot With Ultrasonic Sensors

Abstract The robot that can move (mobile robot) is required for observation in difficult circumstances which is difficult to be performed by humans such as extreme temperature, cramped, dark and so on. Robot which is needed, is able to move on its own and can avoid obstacles. Implementation tools through experiments is performed in the laboratory. To determine the direction of the turn is based on the measurement data from the sensor ping ultrasonic range finder, then Arduino will adjust the speed of a DC motor to generate the left and right turn. The test results show mobile robot can move itself and is able to avoid obstacles. When the mobile robot obstacle is stuck in the center with left-right-front, it requires quite a long time to come out.

経路生成形レギュレータによる通過可能地点を考慮した四輪車両の走行制御

In uneven terrain such as landfill, there are civil engineering structures like drainage ditches, bumps, and embankments, which might be obstacles for car-like robot to traverse. If the structures have passable points, the robot can pass through there without collision, and reach to their goal point. To realize it, the robot navigation needs to achieve multiple objectives like obstacle avoidance and goal arrival. In this paper, we propose a navigation method using a path-generating regulator (PGR) to mix up a straight-line tracking for obstacle avoidance and origin convergence for goal arrival. The objectives for the navigation are represented as target orientation angles respectively, and they are mixed with nesting weighted sum. Results of numerical simulation show that the robot implemented with the proposed method is able to avoid the structures, and pass through a passable point, and converge to the origin.

CNN-Based Vision Model for Obstacle Avoidance of Mobile Robot

Exploration in a known or unknown environment for a mobile robot is an essential application. In the paper, we study the mobile robot obstacle avoidance problem in an indoor environment. We present an end-to-end learning model based Convolutional Neural Network (CNN), which takes the raw image obtained from camera as only input. And the method converts directly the raw pixels to steering commands including turn left, turn right and go straight. Training data was collected by a human remotely controlled mobile robot which was manipulated to explore in a structure environment without colliding into obstacles. Our neural network was trained under caffe framework and specific instructions are executed by the Robot Operating System (ROS). We analysis the effect of the datasets from different environments with some marks on training process and several real-time detect experiments were designed. The final test result shows that the accuracy can be improved by increase the marks in a structured environment and our model can get high accuracy on obstacle avoidance for mobile robots.

A Multi-objective Optimization Behavior Fusion Avoidance Method for Snake-like Rescue Robot

The obstacle avoidance path planning of rescue robot has been the key problem of autonomous navigation for rescue robot. Most of the existing path planning algorithms is aimed at the optimization of a particular target, often resulting in deadlock or oscillation in order to obtain the optimal solution or the optimal path. Therefore, using the multi-objective optimization theory, this paper presents a multi-objective optimization dynamic obstacle avoidance algorithm based on interval weights, the fusion process of obstacle avoidance process is divided into three seed action, by giving the behavior function of different weights, the output rate of real-time dynamic change of different action. This is not to obtain the optimal solution or the optimal path at the current moment, but to obtain only the most efficient solution or the most satisfactory path at the current moment. Experiments show that the algorithm can effectively improve the flexibility and security of the obstacle avoidance process under the premise of ensuring the real-time and robustness of the search and rescue robot obstacle avoidance process.

不確実な環境下の移動ロボットへ向けたロバストモデル予測制御の性能評価

This paper presents the performance evaluation of robust model predictive control (robust MPC) for a mobile robot. The mobile robot is affected by stationary or moving obstacles and exogenous disturbances, which are road surface slipperiness, fluid resistance under water and current disturbance. Since these disturbances make it difficult to accurately control the trajectory of the mobile robot, robustness is required in the control framework. The robust MPC is one of the methods for mobile robot control. Several previous studies about the robust MPC have mainly focused on Gaussian noise. We conduct a simulation to test mobile robot obstacle avoidance under three different non-Gaussian noise environments, and confirm that the robust MPC is effective given the exogenous disturbances of affecting the mobile robot.

The Design and Characterization of a Flexible Tactile Sensing Array for Robot Skin.

In this study, a flexible tactile sensing array based on a capacitive mechanism was designed, fabricated, and characterized for sensitive robot skin. A device with 8 × 8 sensing units was composed of top and bottom flexible polyethyleneterephthalate (PET) substrates with copper (Cu) electrodes, a polydimethylsiloxane (PDMS) dielectric layer, and a bump contact layer. Four types of microstructures (i.e., pyramids and V-shape grooves) atop a PDMS dielectric layer were well-designed and fabricated to enhance tactile sensitivity. The optimal sensing unit achieved a high sensitivity of 35.9%/N in a force range of 0–1 N. By incorporating a tactile feedback control system, the flexible sensing array as the sensitive skin of a robotic manipulator demonstrated a potential capability of robotic obstacle avoidance.

Cascade Neuro-Fuzzy Architecture Based Mobile- Robot Navigation and Obstacle Avoidance in Static and Dynamic Environments

Cascade Neuro-Fuzzy Architecture Based Mobile- Robot Navigation and Obstacle Avoidance in Static and Dynamic Environments

Mobile Robot Obstacle Avoidance Algorithms Based on Information Fusion of Vision and Sonar

In view of the problem of AS-R autonomous wheeled mobile robot obstacle avoidance, a rapid convergence of sonar and binocular stereovision sensor distance information in order to detect and avoid obstacle algorithm is proposed in this paper. The algorithm first uses binocular camera (CCD) to get three-dimensional image of the real environment, through the stereo matching and V-disparity method which is used to calculate disparity map, then obstacles is extracted by Hough lines detection algorithm, finally we will get information about obstacles and sonar return information with T-S fuzzy neural network fusion, then it will output walking controlled decisions. Experimental results proved that the algorithm is effective and practical.

Neural networks based reinforcement learning for mobile robots obstacle avoidance

This study proposes a new approach for solving the problem of autonomous movement of robots in environments that contain both static and dynamic obstacles. The purpose of this research is to provide mobile robots a collision-free trajectory within an uncertain workspace which contains both stationary and moving entities. The developed solution uses Q-learning and a neural network planner to solve path planning problems. The algorithm presented proves to be effective in navigation scenarios where global information is available. The speed of the robot can be set prior to the computation of the trajectory, which provides a great advantage in time-constrained applications. The solution is deployed in both Virtual Reality (VR) for easier visualization and safer testing activities, and on a real mobile robot for experimental validation. The algorithm is compared with Powerbot's ARNL proprietary navigation algorithm. Results show that the proposed solution has a good conversion rate computed at a satisfying speed.

Indoor Mobile Robot Navigation and Obstacle Avoidance Using a 3D Camera and Laser Scanner

Thanks to the developing sensor technology in mobile robot navigation and obstacle avoidance there are new and affordable solutions which can be used to accomplish smooth, safe and reliable robot movement in an indoor environment. A laser scanner is a commonly used sensor for detecting obstacles as well as for navigation, but a laser scanner is unable to detect all the different obstacles and terrain features by itself. In this article complementary sensors are examined, on a real mobile robot platform. Communication between the sensors and the controller and the basic control possibilities are also discussed. Finally, an advertising mobile robot is described.

Method for six-legged robot stepping on obstacles by indirect force estimation

Adaptive gaits for legged robots often requires force sensors installed on foot-tips, however impact, temperature or humidity can affect or even damage those sensors. Efforts have been made to realize indirect force estimation on the legged robots using leg structures based on planar mechanisms. Robot Octopus III is a six-legged robot using spatial parallel mechanism(UP-2UPS) legs. This paper proposed a novel method to realize indirect force estimation on walking robot based on a spatial parallel mechanism. The direct kinematics model and the inverse kinematics model are established. The force Jacobian matrix is derived based on the kinematics model. Thus, the indirect force estimation model is established. Then, the relation between the output torques of the three motors installed on one leg to the external force exerted on the foot tip is described. Furthermore, an adaptive tripod static gait is designed. The robot alters its leg trajectory to step on obstacles by using the proposed adaptive gait. Both the indirect force estimation model and the adaptive gait are implemented and optimized in a real time control system. An experiment is carried out to validate the indirect force estimation model. The adaptive gait is tested in another experiment. Experiment results show that the robot can successfully step on a 0.2 m-high obstacle. This paper proposes a novel method to overcome obstacles for the six-legged robot using spatial parallel mechanism legs and to avoid installing the electric force sensors in harsh environment of the robot’s foot tips.

Advanced Fuzzy Potential Field Method for Mobile Robot Obstacle Avoidance.

An advanced fuzzy potential field method for mobile robot obstacle avoidance is proposed. The potential field method primarily deals with the repulsive forces surrounding obstacles, while fuzzy control logic focuses on fuzzy rules that handle linguistic variables and describe the knowledge of experts. The design of a fuzzy controller—advanced fuzzy potential field method (AFPFM)—that models and enhances the conventional potential field method is proposed and discussed. This study also examines the rule-explosion problem of conventional fuzzy logic and assesses the performance of our proposed AFPFM through simulations carried out using a mobile robot.

Robot Obstacle Avoidance Learning Based on Mixture Models

We briefly surveyed the existing obstacle avoidance algorithms; then a new obstacle avoidance learning framework based on learning from demonstration (LfD) is proposed. The main idea is to imitate the obstacle avoidance mechanism of human beings, in which humans learn to make a decision based on the sensor information obtained by interacting with environment. Firstly, we endow robots with obstacle avoidance experience by teaching them to avoid obstacles in different situations. In this process, a lot of data are collected as a training set; then, to encode the training set data, which is equivalent to extracting the constraints of the task, Gaussian mixture model (GMM) is used. Secondly, a smooth obstacle-free path is generated by Gaussian mixture regression (GMR). Thirdly, a metric of imitation performance is constructed to derive a proper control policy. The proposed framework shows excellent generalization performance, which means that the robots can fulfill obstacle avoidance task efficiently in a dynamic environment. More importantly, the framework allows learning a wide variety of skills, such as grasp and manipulation work, which makes it possible to build a robot with versatile functions. Finally, simulation experiments are conducted on a Turtlebot robot to verify the validity of our algorithms.

Using Laser Range Finder Obstacle Avoidance and Using TLD Positioning System of Mobile Robot

Robot self-localization and obstacle avoidance has been one of the important topics in robotics. The sensing system which is more mature and using a laser range finder (LRF). But the biggest drawback is the LRF detection range is a plane, And for some high reflectivity of the object, will produce incorrect reflection data. So when the obstacle is not the detection range, or due to high reflectance data will generate an error and the positioning of the robot obstacle avoidance function error. This paper is the use of TLD (Tracking-Learning-Detection) image recognition system, to assist LRF do positioning and obstacle avoidance. And this imaging system can also be used while the robot with object tracking functions

Path planning for mobile robots using Bacterial Potential Field for avoiding static and dynamic obstacles

In this paper, optimal paths in environments with static and dynamic obstacles for a mobile robot (MR) are computed using a new method for path planning. The proposed method called Bacterial Potential Field (BPF) ensures a feasible, optimal and safe path. This novel proposal makes use of the Artificial Potential Field (APF) method with a Bacterial Evolutionary Algorithm (BEA) to obtain an enhanced flexible path planner method taking all the advantages of using the APF method, strongly reducing its disadvantages. Comparative experiments for sequential and parallel implementations of the BPF method against the classic APF method, as well as with the Pseudo-Bacterial Potential Field (PBPF) method, and with the Genetic Potential Field (GPF) method, all of them based on evolutionary computation to optimize the APF parameters, were achieved. A simulation platform that uses an MR realistic model was designed to test the path planning algorithms. In general terms, it was demonstrated that the BPF outperforms the APF, GPF, and the PBPF methods by reducing the computational time to find the optimal path at least by a factor of 1.59. These results have a positive impact in the ability of the BPF path planning method to satisfy local and global controllability in dynamic complex environments, avoiding collisions with objects that will interfere the navigation of the MR.

Движение мобильного робота по горизонтальным, наклонным и вертикальным поверхностям при наличии возмущений и подвижных препятствий

Mobile robot's motion control on different uneven surfaces under the influence of the external forces in unidentified environment has been analyzed. The mobile robotic platform consists of two parts - the external one and internal one. The relative movement of these parts causes movement of the robotic platform. The robot has pneumatic power source and a set of suction caps for different walls. The environment may include various moving and static obstacles which robot should avoid while moving. The robotic platform has its safe zone defined by robot's and obstacles' speed limits to prevent a crash. Any moving obstacle has its own trajectory and overall dimensions, which could be calculated by processing the data from the vision system. The vision system of the robot consists of a set of sensors: a laser scanner, an ultrasonic sensor and a camera. The robot's control system receives complex data from the sensors and calculates the linear and angular velocities of the robotic platform and the nearest obstacles, and, using its database, decides what behavior model should be applied. Different situations of the robot's and obstacles' relative positions with various values of the relative speed were analyzed. The strategy of the roundabout ways uses the data from the robot's sensors. The motion control algorithms for detouring of the moving and static obstacles were proposed. They envision different situations, which can happen on a wall while the robot moves to the point of destination.

1P1-K04 画像認識と走行経験に基づく車両型自律移動ロボットのための走破可能な障害物の認識

In this paper, we propose a method to recognize traversable obstacles for autonomous mobile robots based on image recognition and motion information. First, we perform data acquisition to gather terrain images and vertical acceleration signal. In order to extract correlation, we compute Canonical Correlation Analysis between image and running features. Using extracted data association, we estimate load of the robot from only image features. Finally, we achieved recognition of traversable obstacles from estimated load.

Prediction of motion over traversable obstacles for autonomous mobile robot based on 3D reconstruction and running information

Prediction of motion over traversable obstacles for autonomous mobile robot based on 3D reconstruction and running information