Obstacle Avoidance Algorithm Research Articles

Dual-game based UAV swarm obstacle avoidance algorithm in multi-narrow type obstacle scenarios

Due to the advantages of rapid deployment, flexible response and strong invulnerability, unmanned aerial vehicle (UAV) swarm has been widely applied in collaborative warfare and emergency communication. However, UAV swarm in complex environments is prone to chaotic collapse due to obstructions. A UAV swarm obstacle avoidance system model for multi-narrow type obstacles is established. Due to the fact that only one UAV is allowed to pass through each small hole at any given moment, addressing the issue of congestion caused by swarming effects becomes crucial in addition to managing the competitive allocation of multiple UAVs to multiple holes. Aiming at this problem, a dual-game real-time obstacle avoidance scheme is proposed for UAV swarm with multi-narrow type obstacle scenarios, which divides the flight process of the UAV swarm into two stages: maintaining the flight state of the UAV swarm unchanged when no obstacles are encountered, and implementing matching separation and motion state switching by means of dual-game strategy when facing multi-narrow type obstacles, ultimately achieving orderly passage after multiple rounds of games. For the proposed scheme, a dual-game based Flocking (DGF) obstacle avoidance algorithm is proposed. Specifically, the motion state of each UAV obtained from the game is parameterized and integrated with the Flocking algorithm to calculate the motion control input for each UAV. The solution is iteratively obtained until the UAV swarm completes the obstacle avoidance. Simulation results demonstrate that the proposed DGF algorithm not only enables smooth obstacle avoidance for the UAV swarm in multi-narrow type obstacle scenarios, but also effectively resolves the internal chaos problem in the UAV swarm, thereby preventing rigid collisions.

Multi-AUV Control Method Based on Inverse Optimal Control of Integrated Obstacle Avoidance Algorithm

Under complex underwater conditions, multiple AUVs work in one area and they need to cooperate for complicated missions. In this study, a design method was applied for multiple autonomous underwater vehicles (AUVs) that are distributed in an area and suddenly receive a command. Using this method, the AUVs work according to their own state and reach the target while avoiding obstacles automatically in the process of collection. A new optimal control method is proposed that achieves the consensus of multiple AUVs as well as offering obstacle avoidance capability with minimal control effort. A non-quadratic obstacle avoidance cost function was constructed from the perspective of inverse optimal control. The distributed analytic optimal control law depends only on the local information that can be generated by the communication topology, which guarantees the proposed behavior, so that the control law does not require information from all AUVs. A simulation and an experiment were performed to verify the consensus and obstacle avoidance effect.

Analysis of Pure-pursuit Algorithm Parameters for Nonholonomic Mobile Robot Navigation in Unstructured and Confined Space

This research analyses Pure-pursuit algorithm parameters for nonholonomic mobile robot navigation in unstructured and constrained space. The simulation-based experiment is limited to the mobile robot arrangement. The Look Ahead Distance parameter is adjusted so the mobile robot can navigate the predefined map closely following the waypoints. The optimal Look Ahead Distance value is combined with the VFH+ algorithm for obstacle avoidance. The method is enhanced by adding the λ weight so the robot returns to its waypoints after avoiding an obstacle. The investigation reveals that λ influences the mobile robot’s capacity to return to its predetermined waypoints after avoiding an obstacle. Based on the simulation experiment, the optimal LAD value is 0.2m, and the optimal λ value is 0.8.

Research on collision avoidance simulation for autonomous underwater vehicles using ant colony optimization algorithm

Autonomous Underwater Vehicles (AUVs) are increasingly crucial in exploiting and exploring marine resources. Route building and obstacle avoidance are the core technologies that help this device perform aquatic processes. Collision avoidance methods use acoustic sensors and sonar systems to help detect targets, but these devices have difficulty seeing at short distances. This article proposes a method to simulate the autonomous process of a Remotely Operated Vehicle (ROV) or AUV in a virtual environment based on several path planning and obstacle avoidance algorithms. At the same time, the author used sonar data and optimization algorithms in the route construction process to address the limitations of AUVs and ROVs and the influence of the marine environment. Finally, through Unity 3D software, simulate the underwater operation of the AUV and check the algorithm results.

Research on Obstacle Detection and Avoidance of Autonomous Underwater Vehicle Based on Forward-Looking Sonar.

Due to the complexity of the ocean environment, an autonomous underwater vehicle (AUV) is disturbed by obstacles when performing tasks. Therefore, the research on underwater obstacle detection and avoidance is particularly important. Based on the images collected by a forward-looking sonar on an AUV, this article proposes an obstacle detection and avoidance algorithm. First, a deep learning-based obstacle candidate area detection algorithm is developed. This algorithm uses the You Only Look Once (YOLO) v3 network to determine obstacle candidate areas in a sonar image. Then, in the determined obstacle candidate areas, the obstacle detection algorithm based on the improved threshold segmentation algorithm is used to detect obstacles accurately. Finally, using the obstacle detection results obtained from the sonar images, an obstacle avoidance algorithm based on deep reinforcement learning (DRL) is developed to plan a reasonable obstacle avoidance path of an AUV. Experimental results show that the proposed algorithms improve obstacle detection accuracy and processing speed of sonar images. At the same time, the proposed algorithms ensure AUV navigation safety in a complex obstacle environment.

A new algorithm for obstacle avoidance and tracing applied to wall painting robots

A new algorithm for obstacle avoidance and tracing applied to wall painting robots

Forward-Looking Sonar-Based Stream Function Algorithm for Obstacle Avoidance in Autonomous Underwater Vehicles

Autonomous Underwater Vehicles (AUVs) have emerged as pivotal tools for intricate underwater missions, spanning seafloor exploration to meticulous inspection of subsea infrastructures such as pipelines and cables. Although terrestrial obstacle avoidance paradigms exhibit proficiency, their efficacy diminishes in aquatic environments due to the nuanced challenges and distinct dynamics inherent to marine realms and AUV maneuvering. This paper presents an advanced obstacle avoidance algorithm for AUVs based on a stream function framework. Central to this approach is the utilization of a stream function, further nuanced by a radial histogram that serves as the defining cost function. This work also encapsulates constraints related to the maximum allowed path curvature, ensuring enhanced path optimization. Comprehensive simulation results validate the robustness and adaptability of the introduced strategy, evincing its capacity to outline both practicable and optimal evasion trajectories across diverse operational contexts.

A Motion Planning Method for Robots Based on DMPs and Modified Obstacle-Avoiding Algorithm

This paper addresses the motion planning of the manipulator in task space. To improve the overall trajectory performance, a special motion planning method based on DMPs (Dynamic Movement Primitives) and the modified obstacle-avoiding algorithm is proposed. The proposed method solves the problems of trajectory jitter and inability to avoid obstacles in some scenarios, which are faced by the scheme of steering angle. Besides, it improves the retention of teaching intentions, reduces the loss of free space, and helps the system adapt to the dynamic environment. At the theoretical level, the convergence of the target state has been proved using Lyapunov stability theory-based analysis. The availability of the proposed method is validated and analyzed by performing a series of numerical simulations and Baxter robot experiments. The results indicate that the proposed method can provide reliable solutions for motion planning. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —From the perspective of demonstration learning, this paper aims to elevate the motion planning of the manipulator in task space, especially in improving the obstacle avoidance performance. The existing DMPs-based motion planning algorithm uses the scheme of steering angle to achieve obstacle avoidance, and the obstacle is regarded as a mesh of points on the boundary. The obstacle-avoiding performance is limited. How to combine the obstacle-avoiding algorithm with the DMPs-based motion planning algorithm more effectively, so as to simultaneously achieve retaining teaching intentions as much as possible, still faces challenges. This paper designs a modified obstacle-avoiding algorithm, which solves the problems of trajectory jitter and inability to avoid obstacles in some circumstances, and improves the retention of teaching intentions. The modified obstacle-avoiding algorithm is also applied to the dynamic environment. The proposed method satisfies Lyapunov stability theory-based analysis, and the experiments on Baxter robot verify the feasibility.

Trajectory generation of rotary cranes based on A* algorithm and time-optimization for obstacle avoidance and load-sway suppression

Trajectory generation of rotary cranes based on A* algorithm and time-optimization for obstacle avoidance and load-sway suppression

ROS-Based Food Delivery System

Abstract: More people prefer to dine out nowadays, after having to spend many months in their homes due to the COVID-19 pandemic. The food and beverage industry has to revolutionise its way of serving customers in order to remain sustainable to the growing population. This project aims at the designing of a robot that delivers food to a table in a restaurant and returns back to the kitchen for the next order. Even though it is challenging to design a robot, doing so reduces the wastage of resources in restaurants. Multiple algorithms have been developed for the robot, which allow it to deliver food safely. The mobile robot follows a point to point algorithm and an obstacle avoidance algorithm in the fixed grid environment. The robot has been simulated in Gazebo, with the help of Construct Sim.

Multi‐narrow type obstacle avoidance algorithm for UAV swarm based on game theory

AbstractA Flocking obstacle avoidance algorithm based on the extensive game with perfect information is proposed for the blockage problem of UAV swarm in front of multi‐narrow type obstacles. The two UAVs closest to the target are selected as participants of the game, and the game tree is defined to determine the combination of the motion strategies of the two UAVs to obtain the payoff matrix. Determine the subgame perfect Nash equilibrium to get the optimal strategy, and give the UAVs different motion states respectively so as to ensure that the UAVs can successfully pass multi‐narrow type obstacles. Simulation results demonstrate that the proposed algorithm has a higher over‐hole rate in the case of the multi‐narrow type obstacle compared to the static game‐based Flocking obstacle avoidance algorithm.

A Low-Altitude Obstacle Avoidance Method for UAVs Based on Polyhedral Flight Corridor

UAVs flying in complex low-altitude environments often require real-time sensing to avoid environmental obstacles. In previous approaches, UAVs have usually carried out motion planning based on primitive navigation maps such as point clouds and raster maps to achieve autonomous obstacle avoidance. However, due to the huge amount of data in these raw navigation maps and the highly discrete map information, the efficiency of solving the UAV’s real-time trajectory optimization is low, making it difficult to meet the demand for efficient online motion planning. A flight corridor is a series of unobstructed continuous areas and has convex properties. The flight corridor can be used as a simple parametric representation to characterize the safe flight space in the environment, and used as the cost of the collision term in the trajectory back-end optimization for trajectory solving, which can improve the efficiency of real-time trajectory solving and ensure flight safety. Therefore, this paper focuses on the construction of safe flight corridors for UAVs and autonomous obstacle avoidance algorithms for UAVs based on safe flight corridors, based on a rotary-wing UAV platform, and proposes a polyhedral flight corridor construction algorithm and realizes autonomous obstacle avoidance for UAVs based on the constructed flight corridors.

A novel collaborative path planning algorithm for 3-wheel omnidirectional Autonomous Mobile Robot

Collaboration of multiple mobile robots becomes important in situations where collaborative tasks are required. For this purpose, a method including obstacle detection based on collaborative path planning of multiple Autonomous Mobile Robots (AMRs) has been developed. This study ensures the usability of collaborative omnidirectional AMRs technologies in various fields. In the study, novel path planning and obstacle avoidance algorithms are developed for collaborative mobile robots with omnidirectional mobility. Essentially, these algorithms include motion planning performed by obstacle avoidance with two identical 3-wheel omnidirectional mobile robots (TWOMR). Numerical calculations of the collaborative algorithm have been performed after the kinematic calculations, and tested algorithms developed for the proposed model. As a result, it has been observed that the path planning and obstacle avoidance algorithms developed for collaborative omnidirectional AMRs successfully follow the Master robot in the most efficient trajectory without collision and it has been observed that the developed method works with high accuracy.

Collaborative obstacle avoidance algorithm and simulation of swarm robots with limited viewing angle

In this paper, the problem of collaborative obstacle avoidance of swarm robots with limited view angles is studied. In the case of limited view angles, the control model of swarm robots system is designed. The swarm robots can safely avoid a single static obstacle when the obstacle is within the robot’s visual angle. The main research result of this paper is to design a collaborative obstacle avoidance control algorithm for swarm robots, and subdivide the overall control algorithm into three sub algorithms: formation, obstacle avoidance and navigation. The condition of limited view angle is added to the collaborative obstacle avoidance control algorithm of swarm robots, and a control model of collaborative obstacle avoidance of swarm robots with limited view angle is constructed. Then based on the Simulink platform, the simulation is carried out in the case of static obstacle to verify the correctness and stability of the algorithm.

Research on Public Air Route Network Planning of Urban Low-Altitude Logistics Unmanned Aerial Vehicles

As urban populations continue to grow and road traffic congestion worsens, traditional ground logistics has become less efficient. This has led to longer logistics times and increased costs. Therefore, unmanned aerial vehicle (UAV) logistics has become increasingly popular. However, free-planned routes cannot meet the safety and efficiency requirements of urban airspace mobility. To address this issue, a public air route network for low-altitude logistics UAVs needs to be established in urban areas. This paper proposes a public route network planning method based on the obstacle-based Voronoi diagram and A* algorithm, as follows: Firstly, construct a city airspace grid model in which the characteristics of the airspace are mapped onto the grid map. Introduce an obstacle clustering algorithm based on DBSCAN to generate representative obstacle points as the Voronoi seed nodes. Utilize the Voronoi diagram to establish the initial route network. Then, conduct an improved path planning by employing the A* algorithm for obstacle avoidance in route edges that pass through obstacles. To ensure the safe operation of drones, set constraints on the route safety interval. This process will generate a low-altitude public air route network for urban areas. After considering the flight costs of logistics UAVs at different altitudes, the height for the route network layout is determined. Finally, the route network evaluation indicators are established. The simulation results demonstrate that compared with the city road network planning method and the central radial network planning method, the total route length is shortened by 7.1% and 9%, respectively, the airspace coverage is increased by 9.8% and 35%, respectively, the average network degree is reduced by 52.6% and 212%, respectively, and the average flight time is reduced by 19.4s and 3.7s, respectively. In addition, by solving the network model using the Dijkstra algorithm, when the energy cost and risk cost weights are 0.6 and 0.4, respectively, and the safety interval is taken as 15 m, the total path cost value of the planned trajectory is minimized.

Distributed formation control for groups of mobile robots using consensus algorithm

The increasing implementation of autonomous robots in industries and daily life demands the development of a robust control algorithm that enables robots to perform their tasks successfully. Critical tasks such as rescue missions and area exploration require robots to work cooperatively in a formation to accomplish the tasks quickly. Moreover, the existence of obstacles in the environment requires all the robots' to rapidly process environmental changes to maintain the formation pattern. Thus, this paper introduces a distributed robot formation control system using the consensus algorithm that enables a group of robots to establish and maintain formations using only the local information of the robots. Furthermore, an obstacle avoidance algorithm based on the distance and angle between robots and obstacles is introduced to ensure safe navigation for the group of robots. The algorithm's effectiveness is demonstrated by a multi-robot system with randomly generated starting positions and velocities, where it is shown that the robots can agree on the control variables and establish the required formation while also avoiding obstacles in the environment.

Distributed formation control for groups of mobile robots using consensus algorithm

The increasing implementation of autonomous robots in industries and daily life demands the development of a robust control algorithm that enables robots to perform their tasks successfully. Critical tasks such as rescue missions and area exploration require robots to work cooperatively in a formation to accomplish the tasks quickly. Moreover, the existence of obstacles in the environment requires all the robots' to rapidly process environmental changes to maintain the formation pattern. Thus, this paper introduces a distributed robot formation control system using the consensus algorithm that enables a group of robots to establish and maintain formations using only the local information of the robots. Furthermore, an obstacle avoidance algorithm based on the distance and angle between robots and obstacles is introduced to ensure safe navigation for the group of robots. The algorithm's effectiveness is demonstrated by a multi-robot system with randomly generated starting positions and velocities, where it is shown that the robots can agree on the control variables and establish the required formation while also avoiding obstacles in the environment.

Research on UAV Cluster Obstacle Avoidance Algorithm Based on Improved Artificial Potential Field Method

In view of the shortcomings of the traditional artificial potential field method for the obstacle avoidance of the UAV cluster, this paper solves the safety problem of obstacle avoidance during the flight of the UAV group, introduces the relative speed repulsion force field between the UAV group and the dynamic obstacle, and builds a virtual force field to solve the obstacle avoidance problem of the Calculate the force between the drones according to the distance between the drones. The obstacle generates repulsive force on the drone, the target generates gravity on the drone, and the combined force of gravity and repulsion acts on the drone to control the drone to avoid obstacles. The paper aims to realize multi-UAV obstacle avoidance, and improves the artificial potential field method. Through the design of the formation of UAVs and the UAV obstacle avoidance algorithm, the obstacle avoidance of UAVs is carried out. The simulation results show that the improved artificial potential field can meet the safety, real-time and accessibility requirements of the path planning of the UAV under the dynamic change of targets and obstacles, and improve the tracking and obstacle avoidance speed of the UAV in the dynamic environment.

Development of an obstacle avoiding autonomous vehicle by using stereo depth estimation and artificial intelligence based semantic segmentation

In this study, an autonomous vehicle that can avoid obstacles has been developed by using stereo imaging systems and artificial intelligence applications together. An integrated stereo camera module and NVIDIA Jetson Nano developer kit were used as computer vision system. Checkerboard calibration was performed to prevent camera distortions. The images of the cameras were rectified and the difference costs between the left and right image pairs on the same epipolar plane were calculated. These difference costs were passed through the weighted least squares (WLS) filter, thus a depth map of the left camera image was created. The rectified left camera view was also processed by artificial intelligence-based semantic segmentation. Segmentation was carried out using a previously trained artificial intelligence network (SegNet). These semantic segmentation outputs were passed through the HSV color mask and a mask image was hereby obtained. Using the mask image; movable ground, obstacle, and background information was extracted. Useful data analysis was performed on the depth map and semantic segmentation outputs of the same frame. This information is transmitted to the 2-wheeled vehicle which is designed based on ROS that provides the movement, and decisions are made within the scope of the avoidance algorithm. This study’s novel contribution involves the integration of a passive depth sensing system and artificial intelligence based semantic segmentation, in tandem with a real-time obstacle avoidance algorithm that utilizes these combined technologies. Consequently, the autonomous vehicle is capable of making semantic inferences about its environment while effectively avoiding obstacles.

Dynamic Obstacle Avoidance and Path Planning through Reinforcement Learning

The use of reinforcement learning (RL) for dynamic obstacle avoidance (DOA) algorithms and path planning (PP) has become increasingly popular in recent years. Despite the importance of RL in this growing technological era, few studies have systematically reviewed this research concept. Therefore, this study provides a comprehensive review of the literature on dynamic reinforcement learning-based path planning and obstacle avoidance. Furthermore, this research reviews publications from the last 5 years (2018–2022) to include 34 studies to evaluate the latest trends in autonomous mobile robot development with RL. In the end, this review shed light on dynamic obstacle avoidance in reinforcement learning. Likewise, the propagation model and performance evaluation metrics and approaches that have been employed in previous research were synthesized by this study. Ultimately, this article’s major objective is to aid scholars in their understanding of the present and future applications of deep reinforcement learning for dynamic obstacle avoidance.