Obstacle Position Research Articles

Optimal navigation for AGVs: A soft actor–critic-based reinforcement learning approach with composite auxiliary rewards

In this paper, we address the problem of real-time navigation and obstacle avoidance for automated guided vehicles (AGVs) in dynamic environments, which is a primary research area in collaborative control systems for AGVs. To overcome the computational inefficiency of recalculating optimal paths every time, we propose an improved Soft Actor–Critic (SAC)-based reinforcement learning methodology. This methodology utilizes a novel composite auxiliary reward structure and sum-tree prioritized experience replay (SAC-SP) to achieve real-time optimal feedback control. First, we formulate the navigation task as a Markov Decision Process that considers both static and dynamic obstacles. To accelerate the active learning of AGVs, we propose a novel strategy that uses composite auxiliary rewards. Next, we train the AGVs using the proposed SAC-SP methodology to handle real-time navigation with the composite auxiliary reward structure. The well-trained policy network can generate effective on-board optimal feedback actions given obstacle positions, targets, and AGV states. Simulation experiments demonstrate that our proposed method can steer AGVs to the destination with high robustness to original conditions and various obstacle restrictions, generating optimal feedback actions in the shortest amount of time.

Advanced numerical analysis of convective rarefied flows in microchannels: Studying the impact of multiple obstacle arrangements through LBM modeling

The investigation of fluid flow and forced convective heat transfer in microchannels with square barriers is the focus of this study. The positioning of obstacles was varied in three cases: at the top wall, bottom wall, and symmetrically distributed on both sides of the microchannel wall. The thermal Lattice Boltzmann Method in conjunction with the Double Distribution Function and Bhatnagar–Gross–Krook approach was used for simulation through computer code in Python. Slip velocity and temperature jump were considered in the boundary conditions for the walls of the microchannel and obstacles. The results demonstrate that the rarefaction effect, placement of barriers, and choice of square obstacles significantly impact fluid flow and heat transfer. An increase in Knudsen numbers (Kn) leads to a decrease in temperature and velocity. The presence of obstructions on both sides of the microchannel walls reduces the fluid’s velocity and cools the fluid at the microchannel’s exit. The third case, with obstacles on both sides, presents a practical approach for reducing the fluid’s temperature at the exit, resulting in the lowest level of skin friction (Cf) and a reduction in the Nusselt number (Nu). The proposed configurations can be utilized to enhance the geometry of microchannels and for cooling purposes in small-scale devices and systems with miniature mechanical and electrical components. The study’s findings suggest that the placement of obstacles at the bottom or on both sides, depending on the need for best cooling on both sides or only at the top to reduce material consumption, can achieve low temperature at the exit of a rectangular microchannel.

Localization of robots under two-dimensional indoor conditions

In the 21st century, driven by the vigorous development of science and technology, intelligent services are developing under a unprecedented speed. With the progress of new science and new technology, robots have made a qualitative leap in artificial intelligence, sensing hardware equipment and other aspects. The emergence of mobile robot has replaced many ineffective mechanical labor and liberated a large number of labor. However, in reality, the environment of the moving robot is relatively complex, with many dynamic obstacles and environmental terrain bending, so a reasonable and efficient path planning can greatly save the traveling time of the mobile robot. At the same time, if the mobile robot accurately find the position of its own body and the position of obstacles, it can reach the target safely. Therefore, it is a useful research topic to study the positioning and mapping methods and the path planning method in the navigation technology of moving robot. This article mainly discuss some popular methods of localization under two-dimensional and demonstrate the weakness.

RLSS: real-time, decentralized, cooperative, networkless multi-robot trajectory planning using linear spatial separations

Trajectory planning for multiple robots in shared environments is a challenging problem especially when there is limited communication available or no central entity. In this article, we present Real-time planning using Linear Spatial Separations, or RLSS: a real-time decentralized trajectory planning algorithm for cooperative multi-robot teams in static environments. The algorithm requires relatively few robot capabilities, namely sensing the positions of robots and obstacles without higher-order derivatives and the ability of distinguishing robots from obstacles. There is no communication requirement and the robots’ dynamic limits are taken into account. RLSS generates and solves convex quadratic optimization problems that are kinematically feasible and guarantees collision avoidance if the resulting problems are feasible. We demonstrate the algorithm’s performance in real-time in simulations and on physical robots. We compare RLSS to two state-of-the-art planners and show empirically that RLSS does avoid deadlocks and collisions in forest-like and maze-like environments, significantly improving prior work, which result in collisions and deadlocks in such environments.

Online updating of obstacle positions when intercepting a virtual target

People rely upon sensory information in the environment to guide their actions. Ongoing goal-directed arm movements are constantly adjusted to the latest estimate of both the target and hand’s positions. Does the continuous guidance of ongoing arm movements also consider the latest visual information of the position of obstacles in the surrounding? To find out, we asked participants to slide their finger across a screen to intercept a laterally moving virtual target while moving through a gap that was created by two virtual circular obstacles. At a fixed time during each trial, the target suddenly jumped slightly laterally while still continuing to move. In half the trials, the size of the gap changed at the same moment as the target jumped. As expected, participants adjusted their movements in response to the target jump. Importantly, the magnitude of this response depended on the new size of the gap. If participants were told that the circles were irrelevant, changing the gap between them had no effect on the responses. This shows that obstacles’ instantaneous positions can be considered when visually guiding goal-directed movements.

Automated target detection methodology for drill head sensor systems

A stepped-frequency continuous-wave radar system has been designed and integrated into a drill head for use on midrange horizontal directional drills. Data from the forward-looking radar are acquired, processed, and displayed in near real time. A unique, computationally efficient target detection algorithm has been developed and tested to predict the position of potential obstacles in front of the drill head. This method is called derivative imaging, and it provides distance to target and radial offset information such that the drill operator may respond accordingly. Application to traditional ground-penetrating radar systems is also demonstrated.

Obstacle Detection and Anti-Collision Robot Using Ultrasonic Sensor

Obstacle detection can be considered central and paramount in designing mobile robots. This technique enables mobile robots equipped with sensors to transverse and maneuver freely in an environment preventing damage as a result of a collision with obstacles in its path. Several systems with different approaches have been developed for the anti-collision of a robot with obstacles. The approach to Sensor selection, path planning, and navigation processes determines the operation of such a system and differs from one another. This paper presents a low-cost ultrasonic distance sensor for obstacle detection to enhance anti-collision in mobile robot navigation. The system is designed with the C/C++ programming of the Arduino software (IDE) and implemented on the ATMega 2560 Microcontroller of the Arduino board. An ultrasonic sensor detects an obstacle and sends the data collected to the controller which directs the motor driver to stop or move the robot while following a visible predefined path (blackline) embedded in the ground and detected with the help of an IR sensor placed beneath the robot. Experimental results with varied obstacle positions show a decent performance scoring 96.4% accuracy at a 50cm distance to the obstacle.

Path Planning Method for Underground Survey Robot in Dangerous Scenarios

Over the past 20 years, there has been a growing demand for autonomous exploration of underground environments such as tunnels, urban underground corridors, and complex cave environments. With the development of robotics, dangerous tasks that used to be done by humans have been replaced by underground survey robots. To avoid obstacles in the process of robot work, path planning technology has become one of the important components of underground survey robot. The underground survey robot not only needs to move in the plane, but also needs to climb along the pipe. However, the existing research is mostly two-dimensional plane, which cannot be directly applied to the underground exploration robot. Firstly, this paper compares the existing research and chooses Dijkstra algorithm for three-dimensional implementation. After that, the environment map is established, and the position of obstacles faced by the robot was set for simulation verification. Simulation results show the effectiveness of the proposed algorithm.

Obstacle Avoidance Based on Stereo Vision Navigation System for Omni-directional Robot

This paper addresses the problem of obstacle avoidance in mobile robot navigation systems. The navigation system is considered very important because the robot must be able to be controlled from its initial position to its destination without experiencing a collision. The robot must be able to avoid obstacles and arrive at its destination. Several previous studies have focused more on predetermined stationary obstacles. This has resulted in research results being difficult to apply in real environmental conditions, whereas in real conditions, obstacles can be stationary or moving caused by changes in the walking environment. The objective of this study is to address the robot’s navigation behaviors to avoid obstacles. In dealing with complex problems as previously described, a control system is designed using Neuro-Fuzzy so that the robot can avoid obstacles when the robot moves toward the destination. This paper uses ANFIS for obstacle avoidance control. The learning model used is offline learning. Mapping the input and output data is used in the initial step. Then the data is trained to produce a very small error. To support the movement of the robot so that it is more flexible and smoother in avoiding obstacles and can identify objects in real-time, a three wheels omnidirectional robot is used equipped with a stereo vision sensor. The contribution is to advance state of the art in obstacle avoidance for robot navigation systems by exploiting ANFIS with target-and-obstacles detection based on stereo vision sensors. This study tested the proposed control method by using 15 experiments with different obstacle setup positions. These scenarios were chosen to test the ability to avoid moving obstacles that may come from the front, the right, or the left of the robot. The robot moved to the left or right of the obstacles depending on the given Vy speed. After several tests with different obstacle positions, the robot managed to avoid the obstacle when the obstacle distance ranged from 173 – 150 cm with an average speed of Vy 274 mm/s. In the process of avoiding obstacles, the robot still calculates the direction in which the robot is facing the target until the target angle is 0.

Research on Obstacle Avoidance Control of Multiple UAV Formation based on Genetic Algorithm

The UAV (Unmanned Aerial Vehicle) group cooperative formation flight technology has the advantages of wide coverage, large activity radius, strong overall search ability and high efficiency of the aircraft group. Therefore, it is suitable for various complex tasks in the military field such as battlefield environment reconnaissance, tactical attack and cooperative search. This paper proposes a consistency control strategy based on GA (Genetic Algorithm) and applies it to multi-UAV formation obstacle avoidance, which can effectively solve the collision between UAVs and between UAV formation and obstacles. Demodulate the received ground desired control command, and introduce an additional auxiliary traction acceleration through GA to avoid the local optimal solution. The auxiliary traction acceleration is related to the speed and relative position of UAV and obstacles. It can be used as a disturbance to solve the local optimal solution, and also as an auxiliary acceleration to improve the speed of avoiding moving obstacles. Finally, the rapid formation and obstacle avoidance of UAV fleet during flight are realized, and the survivability of the fleet in the battlefield environment is improved.

Path Following and Avoiding Obstacle for Mobile Robot Under Dynamic Environments Using Reinforcement Learning

Obstacle avoidance for mobile robot to reach the desired target from a start location is one of the most interesting research topics. However, until now, few works discuss about working of mobile robot in the dynamic and continuously changing environment. So, this issue is still the research challenge for mobile robots. Traditional algorithm for obstacle avoidance in the dynamic, complex environment had many drawbacks. As known that Q-learning, the type of reinforcement learning, has been successfully applied in computer games. However, it is still rarely used in real world applications. This research presents an effectively method for real time dynamic obstacle avoidance based on Q-learning in the real world by using three-wheeled mobile robot. The position of obstacles including many static and dynamic obstacles and the mobile robot are recognized by fixed camera installed above the working space. The input for the robot is the 2D data from the camera. The output is an action for the robot (velocities, linear and angular parameters). Firstly, the simulation is performed for Q-learning algorithm then based on trained data, The Q-table value is implemented to the real mobile robot to perform the task in the real scene. The results are compared with intelligent control method for both static and dynamic obstacles cases. Through implement experiments, the results show that, after training in dynamic environments and testing in a new environment, the mobile robot is able to reach the target position successfully and have better performance comparing with fuzzy controller.

Collision avoidance and path planning for mobile robots based on state estimation approach

Planning a collision-free path while preserving processing time and minimizing cost function has been considered a significant challenge in developing an Autonomous Mobile Robot (AMR). Various optimization techniques for avoiding obstacles and path planning problems have been proposed recently. But, the computation time for executing these techniques is comparatively higher and has lesser accuracy. In this paper, the State Estimation Obstacle Avoidance (SEOA) algorithm has been proposed for estimating the position and velocity of both of the wheels of the AMR. Moreover, this algorithm has been also applied in path planning for reaching the destination point in minimum computational time. Five different positions of static obstacle are demonstrated in a real time static environment where the proposed SEOA algorithm has been compared with state-of-the-art path planning algorithms such as A* and VFH. The simulation results demonstrate that the proposed algorithm takes lesser computational time to generate the collision free path when compared to other mentioned algorithms.

Scheme of Operation for Multi-Robot Systems with Decision-Making Based on Markov Chains for Manipulation by Caged Objects

This paper presents the design of a new control scheme for a group of omnidirectional robots in a multi-robot system operating in an environment with obstacles. The control scheme uses a decision agent based on discrete-time Markov chains and takes into account the state of the system, obstacle positions, and geometries to manipulate targets, providing robustness against measurement uncertainties. The decision process is dynamic, with state information updating at each time step and tasks being executed based on the hierarchy determined by quadratic hierarchical programming. The system’s stability in the mean-square sense is analyzed through the study of a closed-loop stochastic system, and the effectiveness of the proposed control scheme is demonstrated through numerical simulations, including a comparative analysis with a finite-state machine decision agent.

Factors affecting air distribution in air conditioning air supply room based on SUPG finite element and zero equation

To simulate the indoor air distribution accurately and quickly, this paper proposed a turbulence calculation model based on the zero-equation model and the SUPG finite element method. The optimal calculation parameters were investigated. The effects of air outlet positions, Reynolds numbers, and obstacle positions on indoor air distribution were studied. The results show that the ranges of Reynolds numbers which satisfy the summer and winter demands of indoor air velocity as the outlet at the right down position are larger than those when the outlet locates left down. When the air outlet locates at the left down position, the velocity non-uniformity coefficients are less than those under the other two conditions. Regardless of whether the air outlet is at the left or right position, the obstacle in the middle of a room can lead to worse velocity uniformity when air velocities in the working zone can meet the velocity demand.

Obstacle's effects and their location inside the square cavity on the thermal performance of Cu–Al2O3/H2O hybrid nanofluid

AbstractThe current study focuses on the effect of obstacles and their positioning within the square cavity (L = H) on heat exchange. This work considers heating the cavity's bottom wall to a steady, high temperature. The top wall of the cavity is adiabatic, while the two vertical side walls are cooled. Four cases are explored under these conditions: the first case is a square‐shaped cavity holding a square‐shaped obstacle h = l = 0,15 L, while the other three cases, respectively, each include two, three, and four square obstacles. The cavity was filled with Cu–Al2O3/H2O hybrid nanofluid with a volume fraction φ = 0.03. Numerical results for laminar and stationary flow regimes with Rayleigh numbers 104 ≤ Ra ≤ 106. The finite volume approach solves the governing equations numerically. The findings show that the number of square obstacles within the square‐shaped cavity significantly impacts heat exchange and hybrid nanofluid flow. The second example, with two square obstacles, improves heat exchange more than other cases with one to four barriers. In the second example, the obstacle location at the plane Y = 0.25H is suitable and helps boost heat transmission of the hybrid nanofluid. The ideal obstacle position in the fourth scenario, which has four square barriers, is at the plane Y = 0.75H.

A ROS-based hybrid algorithm for the UAV path planning problem

PurposeIt is possible with classical path planning algorithms to plan a path in a static environment if the instant position of the vehicle is known and the target and obstacle positions are constant. In a dynamic case, these methods used for the static environment are insufficient. The purpose of this study is to find a new method that can provide a solution to the four-rotor unmanned aerial vehicle (UAV) path planning problem in static and dynamic environments.Design/methodology/approachAs a solution to the problem within the scope of this study, there is a new hybrid method in which the global A* algorithm and local the VFH+ algorithm are combined.FindingsThe performance of the designed algorithm was tested in different environments using the Gazebo model of a real quadrotor and the robot operating system (ROS), which is the widely used platform for robotic applications. Navigation stacks developed for mobile robots on the ROS platform were also used for the UAV, and performance benchmarks were carried out. From the proposed hybrid algorithm, remarkable results were obtained in terms of both planning and implementation time compared to ROS navigation stacks.Originality/valueThis study proposes a new hybrid approach to the path planning problem for UAVs operating in both static and dynamic environments.

Preliminary study for permeability adjustment of triaxial porous ceramic media obtained by binder jetting

Among the oil reservoirs types are those constituted by sandstone-type rocks, representing 60 % of the existing reservoirs. Properties such as porosity and permeability are critical in understanding the flow of fluids inside these rocks, especially for implementing advanced oil recovery technologies (Enhanced Oil Recovery - EOR), which seek to recover/extract as much as possible oil from these rocks. Additive Manufacturing (AM) by binder jetting is a promising alternative for obtaining porous media with properties similar to those of natural rocks. This study hypothesized that obtaining a permeability tailoring of triaxial ceramic porous media is possible by planning their internal filling configurations and subsequent fabrication by AM. Therefore, an algorithm was developed that allowed obtaining and manipulating geometric, dimensional, and spatial positions of obstacles inside the porous medium to make them promote or restrict the flow. After the sintering process, the results showed the method's applicability to obtaining porous ceramic media with different permeabilities. It was possible to get permeability changes by alternating the degree of packing of the internal structures. For the parameters tested, values between 7.73 ± 1.5 mD and 75.71 ± 0.90 mD were found, which are values similar to those commonly found in rocks from petroleum and gas reservoirs.

Effect of obstacle location on hydrogen dispersion in a hydrogen fuel cell bus with natural and mechanical ventilation

Hydrogen leakage in hydrogen fuel cell buses can cause danger to the public. Cuboid space finite element models are established to study the effect of obstacle positions on the hydrogen dispersion behaviour under no ventilation, natural ventilation and mechanical ventilation by monitoring the hydrogen concentration along the line and on the iso-surface. The effect of the obstacle on the hydrogen dispersion behaviour is enhanced with the reduction of the distance from the obstacle to the leakage location. In the space with no ventilation, the effect of the obstacle on hydrogen dispersion varies with the dispersion phase. In the naturally ventilated space, the concentration of hydrogen on the side with an obstacle is higher than that on the side without any obstacles; thus, the presence of the obstacle is not conducive to hydrogen exiting the compartment. In the mechanically ventilated space, the effect of the obstacle on hydrogen dispersion is more pronounced. Specifically, the hydrogen concentration on the side with no obstacles is 2–3 times that on the side with an obstacle, so the obstacle is conducive to hydrogen exiting. The obstacle is recommended to be in the focus of the related hydrogen leakage behaviour study.

Intelligent SLAM Algorithm Fusing Low-Cost Sensors at Risk of Building Collapses

When firefighters search inside a building that is at risk of collapse due to abandonment or disasters such as fire, they use old architectural drawings or a simple monitoring method involving a video device attached to a robot. However, using these methods, the disaster situation inside a building at risk of collapse is difficult to detect and identify. Therefore, we investigate the generation of digital maps for a disaster site to accurately analyze internal situations. In this study, a robot combined with a low-cost camera and two-dimensional light detection and ranging (2D-lidar) traverses across a floor to estimate the location of obstacles while drawing an internal map of the building. We propose an algorithm that detects the floor and then determines the possibility of entry, tracks collapses, and detects obstacles by analyzing patterns on the floor. The robot’s location is estimated, and a digital map is created based on Hector simultaneous localization and mapping (SLAM). Subsequently, the positions of obstacles are estimated based on the range values detected by 2D-lidar, and the position of the obstacles are identified on the map using the map update method in semantic SLAM. All equipment are implemented using low-specification devices, and the experiments are conducted using a low-cost robot that affords near-real-time performance. The experiments are conducted in various actual internal environments of buildings. In terms of obstacle detection performance, almost all obstacles are detected, and their positions identified on the map with a high accuracy of 89%.

Improving Thermal Efficiency of Solar Air Collector by Creating Turbulent Flow Using New Baffles Combinations

The study shows an experimental investigation for a solar air collector with a single pass by adding rectangular baffles for different positions inside the channel. The aim of this study is to improve the thermal efficiency for this collector, and that through testing four cases of baffles positions (mode 1, 2, 3, 4). The study was done under different operating conditions by changing the mass flow rates and positions of baffles. The results show the effectiveness of the baffles in improving the efficiency of the collector, The study also proved that the baffles positions affect thermal efficiency, where the greatest efficiency was recorded in the fourth mode and then in the positioning of obstacles at the middle of the channel for the mode 2 and the mode 4 with a percentage of 76.61 and 90.9, at mass flow rate m=0.0522 kg/s, while the pressure drop was very high in the mode 4, and after that the mode 2. Through the conditions of the study and taking into account all the results; we can say that the best case was mode 2.