AgriPath: a robust multi-objective path planning framework for agricultural robots in dynamic field environments

Path planning is crucial for several applications, including those in industrial facilities, network traffic, computer games, and agriculture. Enabling automated path-planning methods in smart farms is essential to the future development of agricultural technology. Path planning is divided into global and local planners. Global planners are divided into different types and use well-known grid-based and sampling-based algorithms. In this paper, we propose an algorithm suitable for smart farms in combination with simultaneous localization and mapping (SLAM) technology. The characteristics of the grid-based Dijkstra algorithm, the grid-based A* algorithm, the sampling-based rapidly exploring random tree (RRT) algorithm, and the sampling-based RRT* algorithm are discussed, and an algorithm suitable for smart farms is investigated through field tests. We hypothesized path planning for an agricultural harvesting robot, a spraying robot, and an agricultural transport robot, and conducted experiments in environments with static and dynamic obstacles. In addition, the set parameters are validated experimentally. The Shapiro–Wilk test is used to confirm the shape of the normal distribution, and the analysis of variance (ANOVA) and Kruskal–Wallis test are performed to confirm the significance of the experimental results. Smart farms aim to minimize crop damage; thus, it is vital to reach the goal point accurately rather than quickly. Based on the results, we determined that the A* algorithm is suitable for smart farms. The results also open the possibility of reaching the correct destination in the shortest time when working in smart farms.

This study investigates the Rapidly-exploring Random Tree (RRT) algorithm's efficacy in mobile robot navigation, focusing on intelligent path planning amidst dynamic, high-dimensional environments. While RRT's foundational principles facilitate quick exploration of state spaces, its adaptability to evolving conditions and compatibility with advanced sensing technologies remain underexplored. This research delves into the RRT's core functionalities and extends its analysis to various enhanced iterations like RRT* and I-RRT*, showcasing their increased efficiency in real-world applications such as autonomous vehicle navigation and robotic manipulator path planning. The paper critically assesses the RRT's algorithmic structure, emphasizing its strategic growth in uncharted territories and its application in navigating through environments laden with static and dynamic obstacles. Through a series of case studies, the paper illustrates the algorithm's real-time responsiveness and its ability to synthesize with genetic algorithms and neural networks for optimal path determination. Prospects of the RRT algorithm are explored, suggesting its integration with AI and machine learning to augment path planning intelligence. The study posits that such integration will lead to more robust and adaptive navigational strategies, catering to the intricate demands of modern automated systems. Concluding, this research elucidates the RRT algorithm's current state, potential enhancements, and future trajectory, offering a pivotal reference for the development of more sophisticated autonomous navigation systems.

BackgroundThe widespread adoption of plant protection robots has brought intelligent technology and agricultural machinery into deep integration. However, with advances in robotic autonomy, the energy that robots can carry remains limited due to constraints on battery capacity and weight. This limitation restricts the robots’ ability to perform tasks continuously over extended periods.MethodsTo address the challenges of achieving low energy consumption and efficiency in path planning for plant protection robots operating in mountainous environments, a multi-objective path optimization approach was developed. This approach combines the improved A* algorithm with the Improved Whale Optimization Algorithm (A*-IWOA), utilizing a 2.5D elevation grid map. First, an energy consumption model was created to account for the robot’s energy use on slopes, based on its kinematic and dynamic models. Then, an improved A* search method was established by expanding to an 8-domain diagonal distance search and introducing a cost function influenced by cross-product decision values. Using the robot’s motion trajectory as a constraint, the IWOA algorithm was applied to optimize the vector cross-product factor (p) by dynamically adjusting population positions and inertia weights, to minimize both energy consumption and path curvature. Finally, in simulation and orchard scenarios, the application effects of the proposed algorithm were evaluated and compared against notable variants of the A* algorithm using the robot ROS 2 operating system.ResultsThe experimental results show that the proposed algorithm substantially reduces the travel distance and enhances both path planning and computational efficiency. The improved approach meets the driving accuracy and energy consumption requirements for plant protection robots operating in mountainous environments.DiscussionThis algorithm offers significant advantages in terms of computational accuracy, convergence speed, and efficiency. Moreover, the resulting paths satisfy the stringent energy consumption and path planning requirements of robots in unstructured mountain terrain. This improved algorithm could also be replicated and applied to other fields, such as picking robots, factory inspection robots, and complex industrial environments, where robust and efficient path planning is required.

With the rapid development of industrial automation, increasing attention has been attracted to path planning for industrial robots in complex environments. Traditional path-planning methods are limited when dealing with high-dimensional spaces and dynamic obstacles, so more efficient algorithms need to be explored. Rapidly-exploring Random Trees (RRT) as a sampling- based path planning method, has been widely applied in the field of industrial robotics due to their computational efficiency and adaptability. This paper aims to review the research progress of industrial robot path planning based on the Rapidly-exploring Random Trees (RRT), analyze its strengths and limitations in various application scenarios, and explore future development directions. This study systematically evaluates the performance of RRT-based path planning algorithms, including RRT*, RRT-Connect, and other improved versions, by analyzing their four core components: random sampling, tree expansion, obstacle collision checking, and path retrieval. The focus is on the three key indicators: real-time obstacle avoidance capability in dynamic environments, path search efficiency in high-dimensional space, and optimization effect in different application scenarios. Research indicates that RRT-based algorithms demonstrate high efficiency in path searching within complex environments, particularly excelling in nonholonomic constraints and high-dimensional spaces. However, they still exhibit limitations in path smoothness and computational resource consumption, necessitating integration with other optimization methods to further enhance performance. The RRT series of algorithms provide effective solutions for path planning in industrial robots, yet they still require optimization for specific scenarios in practical applications. Future research should focus on further improvements in real-time performance, path quality, and computational efficiency to meet the demands of industrial automation.

Unmanned Aerial Vehicles (UAVs) are being integrated into a wide range of indoor and outdoor applications. In this light, robust and efficient path planning is paramount. An extensive literature review showed that the A* and Rapidly{Exploring Random Tree (RRT) algorithms and their variants are the most promising path planning algorithms candidates for 3D UAV scenarios. These two algorithms are tested in different complexity 3D scenarios consisting of a box and a combination of vertical and horizontal plane obstacles with apertures. The path length and generation time are considered as the performance measures. The A* with a spectrum of resolutions, the standard RRT with different step{ size constraints, RRT without step size constraints and the Multiple RRT (MRRT) with various seeds are implemented and their performance measures compared. Results confirm that all algorithms are able to generate a path in all scenarios for all resolutions, step sizes and seeds considered, respectively. Overall A*'s path length is more optimal and generation time is shorter than RRT projecting A* as a better candidate for online 3D path planning of UAVs.

Objective: This study aims to improve the classical Rapidly-exploring Random Trees (RRT) algorithm, commonly used in robotic path planning. The classical algorithm often generates suboptimal paths due to its reliance on random exploration. Enhancements are proposed to increase pathfinding efficiency and applicability in multi-dimensional environments. Methods: An improved RRT algorithm was developed by introducing a target-biased tree expansion strategy and optimizing step sizes based on algorithmic principles and operational scales. Simulations were performed in two-dimensional (2D) and three-dimensional (3D) environments to evaluate its efficiency. Key performance metrics, including path length, computational time, and total number of explored points, were analyzed and compared with the traditional RRT. Simulations with dynamic obstacles were also performed in 2D environments in order to validate the performance of the improved algorithm in complicated and realistic situations. Results: The improved algorithm consistently generated shorter paths and reduced computational time compared to the classical RRT. For both 2D and 3D simulations, the success rate of finding optimized paths significantly increased, demonstrating enhanced adaptability in various environments. Conclusion: The proposed improvements address the limitations of the traditional RRT algorithm, providing a practical and effective solution for robotic path planning in static and multi-dimensional environments. These advancements contribute to the development of more efficient path-planning methods in robotics.

Path planning is one of the fundamental problems in robotics. Due to the advancement in technology, the application of mobile robots has increased in recent years, not only in the field of robotics, but also in other domains such as computational biology, computer animation and aerospace. Path planning in high dimensional environments for mobile robots is known to be computationally challenging, but since the introduction of the sampling-based planning algorithms such as rapidly exploring random tree (RRT) and probabilistic roadmap (PRM), solving high dimensional path planning problems has became easier. In this paper, we present a mesh-based RRT path planning approach. Connecting RRT tree nodes on a nonplanar surface mesh requires the computation of geodesics, shortest length paths on the mesh, which can create a high computational load. The proposed method reduces the number and length of geodesics on the mesh. Simulation results show that this method finds a feasible path faster than the basic RRT on the mesh.

As an important field of robot research, robot path planning has been studied extensively in the past decades. A series of path planning methods have been proposed, such as A* algorithm, Rapidly-exploring Random Tree (RRT), Probabilistic Roadmaps (PRM). Although various robot path planning algorithms have been proposed, the existing ones are suffering the high computational cost and low path quality, due to numerous collision detection and exhausting exploration of the free space. In addition, few robot path planning methods can automatically and efficiently generate path for a new environment. In order to address these challenges, this paper presents a new path planning algorithm based on the long-short term memory (LSTM) neural network and traditional RRT. The LSTM-RRT algorithm first creates 2D and 3D environments and uses the traditional RRT algorithm to generate the robot path information, then uses the path information and environmental information to train the LSTM neural network. The trained network is able to promptly generate new path for randomly generated new environment. In addition, the length of the generated path is further reduced by geometric relationships. Hence, the proposed LSTM-RRT algorithm overcomes the shortcomings of the slow path generation and the low path quality using the traditional RRT method.

This paper proposes an optimal path planning algorithm for mobile robots based on Particle Swam Optimization with an Aging Leader and Challengers (ALC-PSO) and Rapidly-exploring Random Tree (RRT), it improved algorithm of ALC-PSO to imitate concept of RRT root node grown into goal point in path planning, and add Danger Degree Map to avoid obstacles, this method is not only overcome the drawback for particle swam optimization which is easy to fall into local optimization in robotic path planning and the basic Rapidly-exploring Random Tree path planning in avoiding the premature convergence problem, but also improve both of algorithm which can't plan in dynamic environment. From the results of simulations, we show that this algorithm can improve the stability of RRT path planning in dynamic environment, and ensure that the path is almost optimal.

Path planning for indoor Mobile robot based on deep learning

HighlightsA branch accessibility simulation was performed for robotic pruning of apple trees.A virtual tree environment was established using a kinematic manipulator model and an obstacle model.Rapidly-exploring random tree (RRT) was combined with smoothing and optimization for improved path planning.Effects on RRT path planning of the approach angle of the end-effector and cutter orientation at the target were studied.Abstract. Robotic pruning is a potential solution to reduce orchard labor and associated costs. Collision-free path planning of the manipulator is essential for successful robotic pruning. This simulation study investigated the collision-free branch accessibility of a six rotational (6R) degrees of freedom (DoF) robotic manipulator with a shear cutter end-effector. A virtual environment with a simplified tall spindle tree canopy was established in MATLAB. An obstacle-avoidance algorithm, rapidly-exploring random tree (RRT), was implemented for establishing collision-free paths to reach the target pruning points. In addition, path smoothing and optimization algorithms were used to reduce the path length and calculate the optimized path. Two series of simulations were conducted: (1) performance and comparison of the RRT algorithm with and without smoothing and optimization, and (2) performance of collision-free path planning considering different approach poses of the end-effector relative to the target branch. The simulations showed that the RRT algorithm successfully avoided obstacles and allowed the manipulator to reach the target point with 23 s average path finding time. The RRT path length was reduced by about 28% with smoothing and by 25% with optimization. The RRT smoothing algorithm generated the shortest path lengths but required about 1 to 3 s of additional computation time. The lowest coefficient of variation and standard deviation values were found for the optimization method, which confirmed the repeatability of the method. Considering the different end-effector approach poses, the simulations suggested that successfully finding a collision-free path was possible for branches with no existing path using the ideal (perpendicular cutter) approach pose. This study provides a foundation for future work on the development of robotic pruning systems. Keywords: Agricultural robotics, Collision-free path, Manipulator, Path planning, Robotic pruning, Virtual tree environment.

An improved RRT* algorithm for robot path planning based on path expansion heuristic sampling

Intelligent tennis picking robots can effectively improve the efficiency of tennis training and competition, and reduce manual labor intensity. However, the real-time tracking of targets in existing intelligent robot path planning is poor and susceptible to becoming entrenched in local optimal solutions. Therefore, this study proposes an intelligent tennis ball picking robot path planning method that integrates a twin network object tracking algorithm. In terms of target tracking, a hybrid attention mechanism is introduced, which utilizes a transformer structure to achieve hierarchical feature fusion. In terms of path planning, this study combines an improved rapidly-exploring random trees with an artificial potential field ant colony algorithm to enhance the obstacle avoidance capability of robot path planning. Among them, the hybrid attention mechanism enhances local feature extraction and reduces the influence of occlusion by combining grouped convolution transformation and spatially gated embedding. Additionally, the Transformer structure improves tracking accuracy by capturing the global context relationship. In path planning, the improved bidirectional rapidly-exploring random tree algorithm is enhanced through sector constraint sampling to improve search efficiency. The artificial potential field ant colony algorithm optimizes the obstacle avoidance ability and path smoothness. The results showed that in the training dataset, the accuracy of the proposed target tracking algorithm was as high as 0.981, which was 5.40–25.56% higher than existing algorithms such as SiamFC, MORT, SiamRPN, MeMOT, and FROG MOT. In both test datasets, the expected average overlap values were 0.405 and 0.437. The path planning length and time of the proposed method were 42.07 m and 56.12 s, significantly lower than other methods. This indicates that the research method can provide accurate target position information for robots, optimize path planning, and improve the efficiency of picking up tennis balls. This method provides an effective solution for target tracking and path planning of intelligent tennis ball picking robots in complex environments and has important practical application value.

Sampling-based search algorithms such as Rapidly-Exploring Random Trees (RRT) have been utilized for mobile robot path planning and motion planning in high dimensional continuous spaces. This paper presents a path planning method for a planetary exploration rover in rough terrain. The proposed method exploits the framework of a sampling-based search, the optimal RRT (RRT*) algorithm. The terrain geometry used for planning is composed of point cloud data close to continuous space captured by a light detection and ranging (LIDAR) sensor. During the path planning phase, the proposed RRT*algorithm directly samples a point (node) from the LIDAR point cloud data. The path planner then considers the rough terrain traversability of the rover during the tree expansion process of RRT*. This process improves conventional RRT*in that the generated path is safe and feasible for the rover in rough terrain. In this paper, simulation study on the proposed path planning algorithm in various real terrain data confirms its usefulness.

This research aims to create a simulator for solving the global path planning of mobile robots. Various sampling-based methods such as Rapidly-exploring Random Tree (RRT), RRT*, and Fast-RRT, along with other derivative algorithms, have been widely used to solve path-planning problems in mobile robots. The level of computational efficiency, path optimality, and the ability to adapt to variant environments are some of the issues that still arise, although these techniques have shown good results in many cases. Although the existing solutions are innovative, comparison between the existing methods is still difficult due to significant differences in convergence speed, implementation complexity, and quality of the resulting paths. This makes choosing the most suitable method for a particular application difficult. The simulator uses sampling-based path planning algorithms such as RRT*, Fast RRT*, RRT*-Smart, informed-RRT*, and Honey Bee Mating Optimization-based Fast-RRT*. With this simulator, users can easily compare the performance of each algorithm and see the characteristics and efficiency of each algorithm in various situations. By running all methods through this simulator, the user can easily compare the methods based on convergence speed and optimality. Therefore, it will effectively help users understand robot navigation, improve the quality of learning, and promote the development of path-planning technology for mobile robots.