The Improved A* Obstacle Avoidance Algorithm for the Plant Protection UAV with Millimeter Wave Radar and Monocular Camera Data Fusion

Huang, Xin; Dong, Xiaopeng; Ma, Jing; Liu, Kuan; Ahmed, Shibbir; Lin, Jianhua; Qiu, Baijing

doi:10.3390/rs13173364

Cited by 24 publications

(6 citation statements)

References 51 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other types of environment processing techniques such as the Otsu algorithm are used when an image of the environment is used as an input to an obstacle avoidance algorithm [19]. The Otsu algorithm for instance converts the input image to a binary representation of the environment [12]. This study will focus on the metric environment model, specifically, a branch of metric representation referred to as the grid map metric representation.…”

Section: Related Work On Obstacle Avoidancementioning

confidence: 99%

“…Obstacle avoidance is a technique used by unmanned aerial vehicles (UAVs) to avoid collisions while in flight. The UAVs must avoid collisions in three dimensions in this setting [12], using millimeter wave radar and monocular camera data fusion techniques amongst many other sensing methods. The unmanned surface vehicles (USVs), on the other hand, avoid collisions in two dimensions using algorithms like the extended Kalman filter (EKF) [13] and multiple variants of sensor data fusion, state estimators or observers, controllers, and control objectives [14].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Mobile Robots with Dynamic Obstacle Avoidance

Ali,

Das

2023

2023 IEEE 3rd International Conference on Sustainable Energy and Future Electric Transportation (SEFET)

View full text Add to dashboard Cite

Robots with autonomous navigation capabilities have become increasingly popular after the advances in robotic automation, particularly in the area of pathfinding algorithms. These algorithms enable robots to safely traverse through complex environments with both stationary and moving obstacles. Applications of this field range from data acquisition to surveys of hazardous situations and transportation by industrial robots. The most commonly utilized approach for two-dimensional obstacle avoidance is grid-based pathfinding algorithms. These methods function by initially generating a grid consisting of nodes and edges based on the environment. In this paper, we explore an implementation of a variation of the A* pathfinding algorithm on a 15x15 grid. The A* algorithm was chosen because it guarantees finding the optimal route between starting and ending points. A* is a grid-based algorithm that falls under the category of search-based algorithms. The Maximum Velocity Obstacle (MVO) algorithm undergoes rigorous testing to evaluate its performance, and we examine how the simulation input parameters influence the algorithm's effectiveness. The experimental results indicate that the MVO algorithm is an efficient and reliable solution for dynamic obstacle avoidance in a grid-based setting. Moreover, this study demonstrates that the algorithm can be further optimized by using more advanced techniques such as combining it with existing pathfinding algorithms, like artificial neural networks. This would enable the robot to adapt to unpredictable environments in future research.

show abstract

Section: Related Work On Obstacle Avoidancementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Mobile Robots with Dynamic Obstacle Avoidance

Ali,

Das

2023

2023 IEEE 3rd International Conference on Sustainable Energy and Future Electric Transportation (SEFET)

View full text Add to dashboard Cite

show abstract

“…Despite various developed CCPP algorithms, the special operation mode makes them not perfectly appropriate for AUH's navigation control strategy. The existence of an obstacle is perceived by the distance information given by a horizontally mounted single beam range sonar/echo sounder (as can be seen in Figure 2), and it obviously distinguishes from other robots, on which LiDAR [23], infrared distance sensor, ultrasonic sensor [24], millimeter wave radar [25], camera, and multi-beam sonar [26], etc. are frequently used.…”

Section: Introductionmentioning

confidence: 99%

A Complete Coverage Path Planning Approach for an Autonomous Underwater Helicopter in Unknown Environment Based on VFH+ Algorithm

Ma,

Zou,

2024

JMSE

View full text Add to dashboard Cite

An Autonomous Underwater Helicopter (AUH) is a disk-shaped, multi-propelled Autonomous Underwater Vehicle (AUV), which is intended to work autonomously in underwater environments. The near-bottom area sweep in unknown environments is a typical application scenario, in which the complete coverage path planning (CCPP) is essential for AUH. A complete coverage path planning approach for AUH with a single beam echo sounder, including the initial path planning and online local collision avoidance strategy, is proposed. First, the initial path is planned using boustrophedon motion. Based on its mobility, a multi-dimensional obstacle sensing method is designed with a single beam range sonar mounted on the AUH. The VFH+ algorithm is configured for the heading decision-making procedure before encountering obstacles, based on their range information at a fixed position. The online local obstacle avoidance procedure is simulated and analyzed with variations of the desired heading direction and corresponding polar histograms. Finally, several simulation cases are set up, simulated and compared by analyzing the heading decision in front of different obstacle situations. The simulation results demonstrate the feasibility of the complete coverage path planning approach proposed, which proves that AUH completing a full coverage area sweep in unknown environments with a single beam sonar is viable.

show abstract

“…The target was then recognized using a classification network that was described by the time-frequency spectrum and textural attributes of the ROI picture. Huang et al presented an effective UAV path planning algorithm based on this calibration method through dynamic heuristic functions, search point optimization, and inflection point optimization [38]. The aforementioned calibration methods assume that the range and angle accuracy of the MMW radar is sufficient to achieve calibration accuracy.…”

Section: Introductionmentioning

confidence: 99%

A high-accuracy calibration method for fusion systems of millimeter-wave radar and camera

Wang¹,

Wang²,

Zhou³

2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

Multi-sensor information fusion is widely used in the field of unmanned aerial vehicles (UAV) obstacle avoidance flight, particularly in millimeter-wave radar (MMW) and camera fusion systems. Calibration accuracy plays a crucial role in fusion systems. The low-angle measurement accuracy of the MMW radar usually causes large calibration errors. To reduce calibration errors, a high-accuracy calibration method based on a region of interest (ROI) and an artificial potential field was proposed in this paper. The ROI was selected based on the initial calibration information andimage. An artificial potential fieldthe MMW radar’s angle measurement error range from thewas established using the pixels of the ROI. Two moving points were initially set at the left and right ends of the ROI initially. The potential forces of the two moving points are different because the pixels of the obstacle and the background are different in the image. The two moving points were iteratively moved towards each other according to the force until their distance was less than the iteration step. The new calibration point is located in the middle of the final position of the two moving points. In contrast to the existing calibration methods, the proposed method avoids the limitations of low angle measurement accuracy by using image pixels. The experimental results show that the calibration errors decrease by 83.95% and 75.79%, which is significantly improved compared to the traditional methods and indicates the efficiency of the proposed method.

show abstract

The Improved A* Obstacle Avoidance Algorithm for the Plant Protection UAV with Millimeter Wave Radar and Monocular Camera Data Fusion

Cited by 24 publications

References 51 publications

Mobile Robots with Dynamic Obstacle Avoidance

Mobile Robots with Dynamic Obstacle Avoidance

A Complete Coverage Path Planning Approach for an Autonomous Underwater Helicopter in Unknown Environment Based on VFH+ Algorithm

A high-accuracy calibration method for fusion systems of millimeter-wave radar and camera

Contact Info

Product

Resources

About