Path Planning Research Articles

Recent progress, challenges and future propects of applied deep reinforcement learning : A practicial perspecive in path planning

Path planning is one of the most crucial elements in the field of robotics, such as autonomous driving, minimally invasive surgery and logistics distribution. This review begins by summarizing the limitations of conventional path planning methods and recent work on DRL-based path planning methods. Subsequently, the paper systematically reviews the construction of key elements of DRL methods in recent work, with the aim of assisting readers in comprehending the foundation of DRL research, along with the underlying logic and considerations from a practical perspective. Facing issues of sparse rewards and the exploration-exploitation balance during the practical training process, the paper reviews enhancement methods for training efficiency and optimization results in DRL path planning. In the end, the paper summarizes the current research limitations and challenges in practical path planning applications, followed by future research directions.

3D path planning for UAV based on A hybrid algorithm of marine predators algorithm with quasi-oppositional learning and differential evolution

3D path planning is a critical requirement for the autonomy of unmanned aerial vehicle (UAV) navigation systems. In this paper, we propose a novel approach, the differential evolution combined marine predators algorithm (DECMPA), specifically tailored to address the UAV 3D path planning problem in complex scenarios. To handle stringent constraints, DECMPA adopts a multi-step approach. Initially, it utilizes quasi-oppositional learning to generate a more uniformly distributed initial population. Throughout the iterative process, it probabilistically generates quasi-oppositional populations and merges them with existing populations, selecting the superior individuals for the next generation to mitigate local optima. Additionally, DECMPA integrates the variance, crossover, and selection processes of differential evolution into the marine predators algorithm iterations. The greedy selection of test and target vectors further accelerates population convergence. Numerical optimization experiments are conducted using the 10 and 20-dimensional CEC 2021 test suite. Compared to other algorithms, DECMPA exhibits superior solution accuracy and convergence speed, resulting in substantial performance enhancement, thus establishing itself as an efficient algorithm. Furthermore, the adoption of spherical vector coordinates in solution encoding ensures higher quality and facilitates the production of feasible solutions. To verify the effectiveness and practicality of the proposed algorithm, comprehensive path planning simulation experiments are conducted. DECMPA is compared against nine other state-of-the-art heuristic algorithms across six 3D scenarios of varying complexity. The experimental results demonstrate DECMPA’s superiority in terms of optimal cost acquisition, solution quality, and stability. In conclusion, DECMPA presents a promising solution for addressing the challenges of UAV 3D path planning in complex environments. Its innovative approach and superior performance underscore its potential for real-world application in autonomous UAV navigation systems.

An effective path planning approach for robot welding considering redundant kinematics

Robot welding with redundant kinematics demands precise coordination of the welding path and redundant axis motion for stable operation. This paper introduces an effective G3 continuous path planning approach for a 6-DOF friction stir welding robot, integrating redundant axis motion to enhance welding stability and quality. The method encompasses a two-pronged strategy: a five-axis path corner smoothing technique and a motion synchronization strategy. Initially, a robust toolpath preprocessing algorithm is presented to mitigate curvature extremities of the inserted smoothing curves within predefined error limits. Subsequently, leveraging G3 continuity criteria, a B-spline-based smoothing method is advanced for refining tool position and orientation paths, with an analytical determination of spline control points facilitated by an explicit smoothing error expression. An effective motion synchronization technique is then proposed, which formulates the tool position, tool orientation, and redundant axis path as explicit functions of the position path arc length. The effectiveness of the proposed method is demonstrated through simulations and experiments on a robot welding platform, with the integration of a jerk-continuous feedrate profile for smooth motion execution. The findings indicate a significant improvement in robotic welding quality by integrating the proposed path planning method with existing workpiece posture optimization techniques.

Underwater Multi-Target Node Path Planning in Hybrid Action Space: A Deep Reinforcement Learning Approach

Underwater Multi-Target Node Path Planning in Hybrid Action Space: A Deep Reinforcement Learning Approach

Optimization of Motion Planning for Quadrotor-Equipped Robotic Manipulators

The focus of the work is on optimizing motion planning for quadcopter-equipped robotic manipulators by integrating quadcopter design, modeling, and path planning for a robotic arm mounted on a quadcopter through MATLAB. Recently, quadcopters have also been used in many application fields with increased viability. This paper will attempt at bringing a complete framework that enhances the operational capabilities of quadcopters through optimized path planning algorithms. The approach will rely on obstacle avoidance techniques for safe operation with satisfactory efficiency in unstructured environments. Advanced algorithms such as Rapidly-exploring Random Trees and dynamic window approaches provide solutions to this challenge of redundancy in the path followed and adaptability in its surroundings. Simulations prove that the proposed optimization methods strongly improve the accuracy and efficiency of the path planned by the robotic arm as it adheres to the dynamic constraints imposed. This work can apply practical insight into many real-world fields such as logistics, surveillance, and search-and-rescue applications aside from contributing to the theoretical understanding of quadcopter dynamics.

Online penetration trajectory planning using blind areas of network radar system for an unmanned combat aerial vehicle

Purpose A densely distributed network radar system compensates for the disadvantages of sparse radars and poses a significant threat to low-altitude penetration by an unmanned combat aerial vehicle (UCAV). Unlike previous studies, this paper aims to consider radar blind areas and proposes a rapid online method for planning low-altitude penetration paths. Design/methodology/approach First, the optimization problem coupling digital elevation map (DEM), radar detection probability model and nonholonomic UCAV kinematic model is established. Second, an online solution framework of penetration path planning is constructed. An intervisibility method and map scaling are proposed to generate a detection probability map (DPM). Through completeness and consistency analysis, an adaptive hybrid A* algorithm with fast local replanning strategy is proposed to search a path that takes into account time-consuming, detection probability under nonholonomic constraints. Finally, three scenarios of multiple known, pop-up and vanished static radars are simulated using C++. The computational performance is compared and analyzed. Findings The results showed that the proposed online method can generate low-detection-probability penetration paths within subseconds. Originality/value This paper provides a new online method to plan UCAV penetration trajectory in military and academic contexts.

Study on Path Planning in Cotton Fields Based on Prior Navigation Information

Aiming at the operation scenario of existing crop coverage and the need for precise row alignment, the sowing prior navigation information of cotton fields in Xinjiang was used as the basis for the study of path planning for subsequent operations to improve the planning quality and operation accuracy. Firstly, the characteristics of typical turnaround methods were analyzed, the turnaround strategy for dividing planning units was proposed, and the horizontal and vertical operation connection methods were put forward. Secondly, the obstacle avoidance strategies were determined according to the traits of obstacles. The circular arc–linear and cubic spline curve obstacle avoidance path generation methods were proposed. Considering the dual attributes of walking and the operation of agricultural machinery, four kinds of operation semantic points were embedded into the path. Finally, path generation software was designed. The simulation and field test results indicated that the operation coverage ratio CR ≥ 98.21% positively correlated with the plot area and the operation distance ratio DR ≥ 86.89% when non-essential reversing and obstacles were ignored. CR and DR were negatively correlated with the number of obstacles when considering obstacles. When considering non-essential reversing, the full coverage of operating rows could be achieved, but DR would be reduced correspondingly.

Path Planning for Robots Combined with Zero-Shot and Hierarchical Reinforcement Learning in Novel Environments

Path planning for robots based on reinforcement learning encounters challenges in integrating semantic information about environments into the training process. In unseen or complex environmental information, agents often perform sub-optimally and require more training time. In response to these challenges, this manuscript pioneers a framework integrating zero-shot learning combined with hierarchical reinforcement learning to enhance agent decision-making in complex environments. Zero-shot learning enables agents to infer correct actions for previously unseen objects or situations based on learned semantic associations. Subsequently, the path planning component utilizes hierarchical reinforcement learning with adaptive replay buffer, directed by the insights gained from zero-shot learning, to make decisions effectively. Two parts are trained separately, so zero-shot learning is available in different and unseen environments. Through simulation experiments, we compare the traditional hierarchical reinforcement learning method with the proposed method. The results prove that this structure can make full use of environmental information to generalize across unseen environments and plan collision-free paths.

A Multigroups Cooperative Particle Swarm Algorithm for Optimization of Multivehicle Path Planning in Internet of Vehicles

A Multigroups Cooperative Particle Swarm Algorithm for Optimization of Multivehicle Path Planning in Internet of Vehicles

Recent developments in autonomous floor-cleaning robots: a review

Purpose Autonomous floor-cleaning robots (AFCRs) have become increasingly popular due to their ability to provide efficient and effective cleaning without the need for human intervention. These robots can perform various cleaning tasks, such as vacuum cleaning, mopping, scrubbing or sweeping, in domestic or industrial setups. As the use of floor-cleaning robots continues to grow, this paper aims to document key technological advancements. Design/methodology/approach The structure of the present work relies on published research articles excavated from general online research databases such as Google Scholar, Web of Science and Scopus. The authors use a variety of keywords and titles to search for research papers. Finally, 93 research articles are selected for review based on abstracts and key results that match AFCRs. Findings According to market trends, floor-cleaning robots dominate other cleaning areas. This review mainly focuses on five attributes of floor-cleaning robots: design and development of AFCR, complete coverage path planning, the application of machine learning (ML)/deep learning (DL), optimisation strategies for qualitative output and ethnographic studies. It also consists of discussions based on the results of reported technical works. Hence, AFCRs have dominated the market in the past decade and are likely to be more aggressive in the coming years. Originality/value To the best of the authors’ knowledge, only a survey article based on US-granted patents published in 2013 constitutes a review work in the research domain on AFCRs. In 2021, another review conducted a survey on the latest technological advancements in window-cleaning robots. It reviewed in detail the locomotion aspects, control mechanisms, adhesion mechanisms, sensors and actuators required for window-cleaning robots. In 2019, a comprehensive review was published on cleaning robots from a control strategy perspective for domestic applications. Therefore, the authors have crafted this review to understand the evolution of floor-cleaning robots in the past decade.

Multi-strategy cooperative enhancement dung beetle optimizer and its application in obstacle avoidance navigation.

Path planning is a crucial component of unmanned driving systems designed to address the challenge of autonomous navigation. This article introduces a novel approach called the multi-strategy cooperative enhanced dung beetle optimization algorithm (RCDBO) and applies it to dispose of path planning issues. Its primary aim is to mitigate the shortcomings of the fundamental dung beetle optimization algorithm (DBO), namely, its tendency to prematurely converge to local optima and its limited global planning capability. Initially, population initialization leverages Bernoulli-based chaotic mapping to enhance diversity and ensure uniform randomness, thereby improving both the quality of initial solutions and optimization efficiency. Subsequently, a random walk strategy is employed to perturb the rolling behavior of the dung beetle population during the initial stage, thus mitigating potential algorithmic local stagnation. Finally, adopting a vertical and horizontal crossover strategy introduces perturbations to the current best value of the dung beetle population, thereby enhancing the DBO method's global optimization capability during the later stages of evolution. The RCDBO method was evaluated against several well-established swarm intelligence algorithms using twelve benchmark test functions, the CEC2021 test suite, the Wilcoxon rank-sum test, and the Friedman test, to rigorously assess its feasibility. Additionally, the effectiveness of each strategy within the RCDBO framework was validated, and the algorithm's capability to achieve an optimal balance between global exploration and local exploitation was systematically analyzed through the CEC2021 test suite. Furthermore, in path planning simulation experiments targeting maps of varying sizes and complexities, the RCDBO algorithm, compared to the basic DBO algorithm, results in shorter planned path lengths. In simpler map environments, it exhibits fewer turning points and smoother paths, indicating that the RCDBO algorithm also possesses certain advantages in addressing path-planning challenges.

Collision Avoidance Path Planning for Automated Vehicles Using Prediction Information and Artificial Potential Field

With the advancement of autonomous driving systems, the need for effective emergency avoidance path planning has become increasingly important. To enhance safety, the predicted paths of surrounding vehicles anticipate risks and incorporate them into avoidance strategies, enabling more efficient and stable driving. Although the artificial potential field (APF) method is commonly employed for path planning due to its simplicity and effectiveness, it can suffer from the local minimum problem when using gradient descent, causing the vehicle to become stuck before reaching the target. To address this issue and improve the efficiency and stability of path planning, this study proposes integrating prediction data into the APF and optimizing the control points of the quintic Bézier curve using sequential quadratic planning. The validity of the proposed method was confirmed through simulation using IPG CarMaker 12.0.1 and MATLAB/Simulink 2022b.

Anti-Collision Path Planning and Tracking of Autonomous Vehicle Based on Optimized Artificial Potential Field and Discrete LQR Algorithm

Anti-Collision Path Planning and Tracking of Autonomous Vehicle Based on Optimized Artificial Potential Field and Discrete LQR Algorithm

Improved DDPG algorithm-based path planning for unmanned surface vehicles

As a promising mode of water transportation, unmanned surface vehicles (USVs) are used in various fields owing to their small size, high flexibility, favorable price, and other advantages. Traditional navigation algorithms are affected by various path planning issues. To address the limitations of the traditional deep deterministic policy gradient (DDPG) algorithm, namely slow convergence speed and sparse reward and punishment functions, we proposed an improved DDPG algorithm for USV path planning. First, the principle and workflow of the DDPG deep reinforcement learning (DRL) algorithm are described. Second, the improved method (based on the USVs kinematic model) is proposed, and a continuous state and action space is designed. The reward and punishment function are improved, and the principle of collision avoidance at sea is introduced. Dynamic region restriction is added, distant obstacles in the state space are ignored, and the nearby obstacles are observed to reduce the number of algorithm iterations and save computational resources. The introduction of a multi-intelligence approach combined with a prioritized experience replay mechanism accelerates algorithm convergence, thereby increasing the efficiency and robustness of training. Finally, through a combination of theory and simulation, the DDPG DRL is explored for USV obstacle avoidance and optimal path planning.

Research on Path Planning of Agricultural UAV Based on Improved Deep Reinforcement Learning

Traditional manual or semi-mechanized pesticide spraying methods often suffer from issues such as redundant coverage and cumbersome operational steps, which fail to meet current pest and disease control requirements. Therefore, there is an urgent need to develop an efficient pest control technology system. This paper builds upon the Deep Q-Network algorithm by integrating the Bi-directional Long Short-Term Memory structure to propose the BL-DQN algorithm. Based on this, a path planning framework for pest and disease control using agricultural drones is designed. This framework comprises four modules: remote sensing image acquisition via the Google Earth platform, task area segmentation using a deep learning U-Net model, rasterized environmental map creation, and coverage path planning. The goal is to enhance the efficiency and safety of pesticide application by drones in complex agricultural environments. Through simulation experiments, the BL-DQN algorithm achieved a 41.68% improvement in coverage compared with the traditional DQN algorithm. The repeat coverage rate for BL-DQN was 5.56%, which is lower than the 9.78% achieved by the DQN algorithm and the 31.29% of the Depth-First Search (DFS) algorithm. Additionally, the number of steps required by BL-DQN was only 80.1% of that of the DFS algorithm. In terms of target point guidance, the BL-DQN algorithm also outperformed both DQN and DFS, demonstrating superior performance.

Performance Evaluation of Various Path Planning Methods for Robotics and Computational Geometry

INTRODUCTION: In integrating Spiral Coverage into Cellular Decomposition, which combines structured grid-based techniques with flexible, quick spiral traversal, time efficiency is increased.OBJECTIVES: In the field of robotics and computational geometry, the study proposes a comparative exploration of two prominent path planning methodologies—Boustrophedon Cellular Decomposition and the innovative Spiral Coverage. Boustrophedon coverage has limitations in time efficiency due to its back-and-forth motion pattern, which can lead to lengthier coverage periods, especially in congested areas. Nevertheless, it is useful in some situations. It is critical to address these time-related issues to make Boustrophedon algorithms more useful in practical settings. METHODS: The research centres on achieving comprehensive cell coverage, addressing the complexities arising from confined spaces and intricate geometries. While conventional methods emphasise route optimization between points, the coverage path planning approach seeks optimal paths that maximize coverage and minimize associated costs. This study delves into the theory, practical implementation, and application of Spiral Coverage integrated with established cellular decomposition techniques.RESULTS: Through comparative analysis, it illustrates the advantages of spiral coverage over boustrophedon coverage in diverse robotics and computational applications. The research highlights Spiral Coverage's superiority in terms of path optimization, computational efficiency, and adaptability, proposing a novel perspective into cell decomposition. The methodology integrates the Spiral Coverage concept, transcending traditional techniques reliant on grids or Voronoi diagrams. Rigorous evaluation validates its potential to enhance path planning, exemplifying a substantial advancement in robotics and computational geometry.CONCLUSION: Our findings show that spiral coverage is on an average 45% more efficient than conventional Boustrophedon coverage. This paper set the basis for the future work on how different algorithms can traverse different shapes more efficiently.

A Study to Investigate the Role and Challenges Associated with the Use of Deep Learning in Autonomous Vehicles

The application of deep learning in autonomous vehicles has surged over the years with advancements in technology. This research explores the integration of deep learning algorithms into autonomous vehicles (AVs), focusing on their role in perception, decision-making, localization, mapping, and navigation. It shows how deep learning, as a part of machine learning, mimics the human brain’s neural networks, enabling advancements in perception, decision-making, localization, mapping, and overall navigation. Techniques like convolutional neural networks are used for image detection and steering control, while deep learning is crucial for path planning, automated parking, and traffic maneuvering. Localization and mapping are essential for AVs’ navigation, with deep learning-based object detection mechanisms like Faster R-CNN and YOLO proving effective in real-time obstacle detection. Apart from the roles, this study also revealed that the integration of deep learning in AVs faces challenges such as dataset uncertainty, sensor challenges, and model training intricacies. However, these issues can be addressed through the increased standardization of sensors and real-life testing for model training, and advancements in model compression technologies can optimize the performance of deep learning in AVs. This study concludes that deep learning plays a crucial role in enhancing the safety and reliability of AV navigation. This study contributes to the ongoing discourse on the optimal integration of deep learning in AVs, aiming to foster their safety, reliability, and societal acceptance.

Path Planning Approaches in Multi‐robot System: A Review

ABSTRACTThe essential factor in developing multi‐robot systems is the generation of an optimal path for task completion by multiple robots. To ensure effective path planning, this paper studies the recent publications and provides a detailed review of the path planning approaches to avoid collisions in uncertain environments. In this article, path‐planning approaches for multiple robots are categorized primarily into classical, heuristic, and artificial intelligence‐based methods. Among the heuristic approaches, bio‐inspired approaches are mostly employed to optimize the classical approaches to enhance their adaptability. The articles are analyzed based on static and dynamic scenarios, real‐time experiments, and simulations involving hybrid solutions. The increasing focus on using hybrid approaches in dynamic environments is found mostly in the papers employing heuristic and AI‐based approaches. In real‐time applications, AI‐based approaches are highly implemented in comparison to heuristic and classical approaches. Moreover, the findings from this review, highlighting the strengths and drawbacks of each algorithm, can help researchers select the appropriate approach to overcome the limitations in designing efficient multi‐robot systems.

Multi-Task Agent Hybrid Control in Sparse Maps and Complex Environmental Conditions

With the rapid development of space exploration technology, the detection of extraterrestrial bodies has become increasingly important. Among these, path planning and target recognition and positioning technologies are particularly critical for applications in intelligent agents with low computational power operating in complex environments. This paper presents a novel approach to path planning on low-resolution lunar surface maps by introducing an improved A* algorithm with an adaptive heuristic function. This innovation enhances robustness in environments with limited map accuracy and enables paths that maintain maximum distance from obstacles. Additionally, we innovatively propose the Dynamic Environment Target Identification and Localization (DETIL) algorithm, which identifies unknown obstacles and employs spatiotemporal clustering to locate points of interest. Our main contributions provide valuable references for the aerospace industry, particularly in lunar exploration missions. The simulation results demonstrate that the improved A* algorithm reduces the maximum elevation difference by 55% and the maximum cumulative elevation difference by 68% compared to the traditional A* algorithm. Furthermore, the DETIL algorithm’s obstacle identification component successfully recognizes all the obstacles along the path, and its spatiotemporal clustering improves the average number of target discoveries by 152% over the conventional DBSCAN clustering approach.

Vehicle-drone collaborative distribution path planning based on neural architecture search under the influence of carbon emissions

Vehicle-drone collaborative distribution path planning based on neural architecture search under the influence of carbon emissions