Real-time Obstacle Avoidance Algorithm Research Articles

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.

Real-time obstacle avoidance algorithm and coordination motion strategy for a redundant dual-arm robot

Real-time obstacle avoidance algorithm and coordination motion strategy for a redundant dual-arm robot

Real-time obstacle avoidance algorithm based on pigeon-inspired optimization

Real-time obstacle avoidance algorithm based on pigeon-inspired optimization

An Automatic Collision Avoidance Algorithm for Multiple Marine Surface Vehicles

Abstract In recent years, unmanned surface vehicles have been widely used in various applications from military to civil domains. Seaports are crowded and ship accidents have increased. Thus, collision accidents occur frequently mainly due to human errors even though international regulations for preventing collisions at seas (COLREGs) have been established. In this paper, we propose a real-time obstacle avoidance algorithm for multiple autonomous surface vehicles based on constrained convex optimization. The proposed method is simple and fast in its implementation, and the solution converges to the optimal decision. The algorithm is combined with the PD-feedback linearization controller to track the generated path and to reach the target safely. Forces and azimuth angles are efficiently distributed using a control allocation technique. To show the effectiveness of the proposed collision-free path-planning algorithm, numerical simulations are performed.

2P1-G09 近接センサを利用したリアルタイム障害物回避アルゴリズムの比較

We compared real time obstacle avoidance algorithm which is using an approach sensor. We made Khatib's artificial potential approach and Kamoi's CPFS algorithm the comparative subject. We compared the collision number of times and arrival time based on each algorithm in the various operational environment. As a result, the potential approach generated a process at high speed by the simple operational society. On the other hand the CPFS algorithm could find a solution in an environment that a robot is surrounded. And also, an obstacle avoidance experiment was made by an experimental robot equipped with proximity sensors. As a result of the experiment, the same result was obtained mostly with a simulation experiment.

REAL-TIME OBSTACLE AVOIDANCE FOR AN UNDERACTUATED FLAT-FISH TYPE AUTONOMOUS UNDERWATER VEHICLE IN 3D SPACE

This paper discusses a real-time obstacle avoidance algorithm and its implementation for an underactuated flat-fish type autonomous underwater vehicle (AUV) in 3D space. The algorithm has been developed using multi-point potential field (MPPF) method and its real-time testing is carried out using hardware-in-loop (HIL) simulations. In MPPF method, a region of predefined radius on a hemisphere in the positive x-axis around the bow of an AUV is discretized into equiangular points with centre as the current position. By determining the point at which the minimum total potential exists, the vehicle can be moved towards that point. Here the analytical gradient of the total potential function is not calculated as it is not essentially required for moving the vehicle to the next position. The MPPF method is interfaced with dynamic model of an underactuated flat-fish type AUV and it is tested and verified using HIL simulation tool. The details of the dynamics of AUV, MPPF method and its implementation, development of HIL test bench and the simulation results are presented in this paper. The results show that the proposed MPPF method is very effective for obstacle avoidance in 3D space and can be used in the real-time control of the AUV.

037 A real-time obstacle avoidance algorithm for teleoperated vehicles

037 A real-time obstacle avoidance algorithm for teleoperated vehicles

A Real-Time Obstacle Avoidance Algorithm for Teleoperated Vehicles

In this paper, we describe a potential based algorithm for real-time obstacle avoidance, dedicated to teleoperated vehicles in unknown envirOnments. The first part shows the arguments which lead us to develop this algorithm and its embedding in the overall navigation system. We then present the type of environment representation used (occupancy grid), and describe the navigation algorithm. Finally, we discuss results obtained in real environments

A Real-time Algorithm for Obstacle Avoidance of Autonomous Mobile Robots

SUMMARYA real-time obstacle avoidance algorithm is proposed for autonomous mobile robots. The algorithm is sensor-based and consists of a H-mode and T-mode. The algorithm can deal with a complicated obstacle environment, such as multiple concave and convex obstacles. It will be shown that the algorithm is more efficient and more robust than other sensor-based algorithms. In addition, the algorithm will guarantee a solution for the obstacle avoidance problem. Since the algorithm only takes up a small computational time, it can be implemented in real time.

Real-Time Obstacle Avoidance with Reference Generation Algorithm using Piecewise Polynomials.

This paper presents a real time obstacle avoidance algorithm with the reference generator using piecewise polynomials. The algorithm consists of three steps. At the first step, by using the future information of path, the interaction point of the pilot point and obstacles are checked. At the second step, the intermittent point data for the trajectory generator are generated not to collide with the obstacles, where the collision point is projected on an arbitrary point on the circumference at a distance from the obstacles. At the third step, using the new data a collision free path is generated by the reference generator using piecewise polynomials. Some results of computer simulation are shown to evaluate the effectiveness of the proposed method.