Obstacle avoidance in mobile robot path planning represents an exciting field of robotics systems. There are numerous algorithms available, each with its own set of features. In this paper a Witch of Agnesi curve algorithm is proposed to prevent a collision by the mobile robot’s orientation beyond the obstacles which represents an important problem in path planning, further, to achieve a minimum arrival time by following the shortest path which leads to minimizing power loss. The proposed approach considers the mobile robot’s platform equipped with the LIDAR 360o sensor to detect obstacle positions in any environment of the mobile robot. Obstacles detected in the sensing range of the mobile robot are dealt with by using the Witch of Agnesi curve algorithm, this establishes the obstacle’s apparent vertices’ virtual minimum bounding circle with minimum error. Several Scenarios are implemented and considered based on the identification of obstacles in the mobile robot environment. The proposed system has been simulated by the V-REP platform by designing several scenarios that emulate the behavior of the robot during the path planning model. The simulation and experimental results show the optimal performance of the mobile robot during navigation is obtained as compared to the other methods with minimum power loss and also with minimum error. It’s given 96.3 percent in terms of the average of the total path while the Bezier algorithm gave 94.67 percent. While in experimental results the proposed algorithm gave 93.45 and the Bezier algorithm gave 92.19 percent.
A robot is a smart machine that can help people in their daily lives and keep everyone safe. the three general sequences to accomplish any robot task is mapping the environment, the localization, and the navigation (path planning with obstacle avoidance). Since the goal of the robot is to reach its target without colliding, the most important and challenging task of the mobile robot is the navigation. In this paper, the robot navigation problem is solved by proposed two algorithms using low-cost IR receiver sensors arranged as an array, and a robot has been equipped with one IR transmitter. Firstly, the shortest orientation algorithm is proposed, the robot direction is corrected at each step of movement depending on the angle calculation. secondly, an Active orientation algorithm is presented to solve the weakness in the preceding algorithm. A chain of the active sensors in the environment within the sensing range of the virtual path is activated to be scan through the robot movement. In each algorithm, the initial position of the robot is detected using the modified binary search algorithm, various stages are used to avoid obstacles through suitable equations focusing on finding the shortest and the safer path of the robot. Simulation results with multi-resolution environment explained the efficiency of the algorithms, they are compatible with the designed environment, it provides safe movements (without hitting obstacles) and a good system control performance. A Comparison table is also provided.
In this paper, a new algorithm called the virtual circle tangents is introduced for mobile robot navigation in an environment with polygonal shape obstacles. The algorithm relies on representing the polygonal shape obstacles by virtual circles, and then all the possible trajectories from source to target is constructed by computing the visible tangents between the robot and the virtual circle obstacles. A new method for searching the shortest path from source to target is suggested. Two states of the simulation are suggested, the first one is the off-line state and the other is the on-line state. The introduced method is compared with two other algorithms to study its performance.
Path-planning is a crucial part of robotics, helping robots move through challenging places all by themselves. In this paper, we introduce an innovative approach to robot path-planning, a crucial aspect of robotics. This technique combines the power of Genetic Algorithm (GA) and Probabilistic Roadmap (PRM) to enhance efficiency and reliability. Our method takes into account challenges caused by moving obstacles, making it skilled at navigating complex environments. Through merging GA’s exploration abilities with PRM’s global planning strengths, our GA-PRM algorithm improves computational efficiency and finds optimal paths. To validate our approach, we conducted rigorous evaluations against well-known algorithms including A*, RRT, Genetic Algorithm, and PRM in simulated environments. The results were remarkable, with our GA-PRM algorithm outperforming existing methods, achieving an average path length of 25.6235 units and an average computational time of 0.6881 seconds, demonstrating its speed and effectiveness. Additionally, the paths generated were notably smoother, with an average value of 0.3133. These findings highlight the potential of the GA-PRM algorithm in real-world applications, especially in crucial sectors like healthcare, where efficient path-planning is essential. This research contributes significantly to the field of path-planning and offers valuable insights for the future design of autonomous robotic systems.