Complex Path Planning Research Articles

3D Voxel-based Path Planning for AVs in Dynamic Complex Environments

Abstract. With the rapid advancement of science and technology, autonomous driving technology has been widely applied in various fields such as the automotive industry, intelligent warehousing, and emergency rescue. Traditional 2D path planning has limitations in dealing with the complex and dynamic environments of the real world, making it difficult to meet the high precision and complex path planning requirements of autonomous vehicles. With the development of data acquisition technology, large-scale point cloud data has become easily accessible, which can better extract the three-dimensional complex of the environment. Nevertheless, the unstructured nature and vast amount of point cloud data make path planning on it extremely challenging. Voxel models can effectively compress point cloud data and provide neighboring topological structures. In view of this, we propose a voxel-based framework for the path planning of autonomous vehicles in dynamic and complex 3D environments, which involves converting point cloud data into voxels and extracting navigation spaces. Subsequently, deep reinforcement learning techniques are utilized to achieve obstacle avoidance and navigation on the voxel map. It is expected that this framework will contribute to the development of 3D path planning and enhance the utilization of point cloud data in the navigation field.

基于势场蚁群算法的农业仓库物流搬运机器人路径优化研究

In the layout of modern agricultural warehouse logistics handling industry, it is an inevitable way to realize industrial upgrading by replacing people with mobile robots. Aiming at the problems that the existing obstacle avoidance control algorithm of agricultural handling robot is easy to fall into local optimal solution, and the operation process of agricultural warehouse logistics handling robot is prone to collision, the obstacle avoidance control of agricultural warehouse logistics handling robot is studied, and a control algorithm based on improved potential field ant colony is proposed. The moving trajectory of the agricultural warehouse logistics handling robot during the handling process is studied, and the spatial kinematics equation of the robot is given. The ant colony algorithm is used to optimize the classical artificial potential field algorithm to improve the global optimization ability and balance the interaction between gravity and repulsion. In the aspect of local area obstacle avoidance of agricultural storage and handling robots, the artificial potential field is optimized twice based on the strategy gradient algorithm. By analyzing the probability of the next action command, the randomness of the travel path selection when multiple robots work at the same time is improved. After testing, the path of the proposed control algorithm is the shortest, and under the condition of complex path planning, the number of collisions between robots is also significantly less than that of the traditional obstacle avoidance control algorithm. The practical application can meet the needs of improving the efficiency of warehouse logistics management.

Path Planning Method for Manipulators Based on Improved Twin Delayed Deep Deterministic Policy Gradient and RRT*

This paper proposes a path planning framework that combines the experience replay mechanism from deep reinforcement learning (DRL) and rapidly exploring random tree star (RRT*), employing the DRL-RRT* as the path planning method for the manipulator. The iteration of the RRT* is conducted independently in path planning, resulting in a tortuous path and making it challenging to find an optimal path. The setting of reward functions in policy learning based on DRL is very complex and has poor universality, making it difficult to complete the task in complex path planning. Aiming at the insufficient exploration of the current deterministic policy gradient DRL algorithm twin delayed deep deterministic policy gradient (TD3), a stochastic policy was combined with TD3, and the performance was verified on the simulation platform. Furthermore, the improved TD3 was integrated with RRT* for performance analysis in two-dimensional (2D) and three-dimensional (3D) path planning environments. Finally, a six-degree-of-freedom manipulator was used to conduct simulation and experimental research on the manipulator.

Research on dynamic obstacle avoidance and complex path planning strategies based on ROS robots

Research on dynamic obstacle avoidance and complex path planning strategies based on ROS robots

A Machine Learning-Based Approach for Multi-AGV Dispatching at Automated Container Terminals

The dispatching of automated guided vehicles (AGVs) is essential for efficient horizontal transportation at automated container terminals. Effective planning of AGV transportation can reduce equipment energy consumption and shorten task completion time. Multiple AGVs transport containers between storage blocks and vessels, which can be regarded as the supply sides and demand points of containers. To meet the requirements of shipment in terms of timely and high-efficient delivery, multiple AGVs should be dispatched to deliver containers, which includes assigning tasks and selecting paths. A contract net protocol (CNP) is employed for task assignment in a multiagent system, while machine learning provides a logical alternative, such as Q-learning (QL), for complex path planning. In this study, mathematical models for multi-AGV dispatching are established, and a QL-CNP algorithm is proposed to tackle the multi-AGV dispatching problem (MADP). The distribution of traffic load is balanced for multiple AGVs performing tasks in the road network. The proposed model is validated using a Gurobi solver with a small experiment. Then, QL-CNP is used to conduct experiments with different sizes. The other algorithms, including Dijkstra, GA, and PSO, are also compared with the QL-CNP algorithm. The experimental results demonstrate the superiority of the proposed QL-CNP when addressing the MADP.

Hyper-Redundant Manipulators for Operations in Confined Space: Typical Applications, Key Technologies, and Grand Challenges

In this article, we review the state of the art in hyper-redundant manipulators for applications in confined space such as <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">on</small> -orbit services. With their multiple degrees of freedom and slender links, hyper-redundant manipulators can offer superior dexterity and excellent operability. They can traverse freely, manipulate objects flexibly, and conform to curvilinear paths accurately in confined spaces. The by-design separation of the mechanical and electrical parts in these manipulators also offers inherent structural compliance and miniaturization. Due to the elastic characteristics of driving cables, hyper-redundant manipulators have both stiffness and flexibility. In this article, the overviews of the current state of the art in this field are provided from the perspectives of both typical applications and key technologies. We detailed the relevant studies on the configuration, obstacle avoidance, path planning, and control technologies for hyper-redundant manipulators and highlight the use of these studies in the development of practical applications. Furthermore, we propose several aspects that need to be further studied, namely efficient inverse kinematics solution, strong coupled dynamics modeling, variable stiffness control, and multiobjective trajectory optimization. Breakthroughs in these areas will provide valuable solutions for complex path planning and control of hyper-redundant manipulators. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>

Robot path planner based on deep reinforcement learning and the seeker optimization algorithm

Path planning is one of the key technologies for mobile robot applications. However, the traditional robot path planner has a slow planning response, which leads to a long navigation completion time. In this paper, we propose a novel robot path planner (SOA+A2C) that produces global and local path planners with the seeker optimization algorithm (SOA) and the advantage actor-critic (A2C) algorithm, respectively. In addition, to solve the problems of poor convergence performance when training deep reinforcement learning (DRL) agents in complex path planning tasks and path redundancy when metaheuristic algorithms, such as SOA, are used for path planning, we propose the incremental map training method and path de-redundancy method. Simulation results show that first, the incremental map training method can improve the convergence performance of the DRL agent in complex path planning tasks. Second, the path de-redundancy method can effectively alleviate path redundancy without sacrificing the search capability of the metaheuristic algorithm. Third, the SOA+A2C path planner is superior to the Dijkstra & dynamic window approach (Dijkstra+DWA) and the Dijkstra & timed elastic band (Dijkstra+TEB) path planners provided by the robot operating system (ROS) in terms of path length, path planning response time, and navigation completion time. Therefore, the developed SOA+A2C path planner can serve as an effective tool for mobile robot path planning.

Kinematic and dynamic analysis of an omnidirectional mobile platform driven by a spherical wheel

Abstract. The increased use of spherical wheels has allowed mobile robots to have a higher degree of maneuverability, less complex path planning and less complex control schemes. The geometry and design of the mobile robot are the principal attributes that guarantee an omnidirectional motion. Furthermore, the platform uses an active spherical wheel and four passive spherical wheels to get the best stability when the robot uses a terminal element (Kärcher). The proposed model has been designed to improve the omnidirectional motion issues, such as vibration into the platform or lack of punctual contact between the wheel and the floor, compared to mobile robots using Mecanum wheels and more than one active wheel; due to the design concept, all the mathematical formulations, kinematics and dynamics presents how the models are validated with computer simulations.

Spot-welding path planning method for the curved surface workpiece of body-in-white based on a memetic algorithm

Aiming at the problem of complex path planning in the processing of curved surface workpieces of body-in-white, a hybrid path planning method based on a memetic algorithm is proposed. The method is divided into two parts: welding sequence planning and welding path planning between weld points. By establishing the kinematic model of a spot welding robot based on the pipper criterion and z-y-z Euler angle solution method, the motion constraints of path optimization are analyzed. Under the framework of the memetic algorithm, the improved A-star algorithm with redundant node deletion and a post-smoothing process is used to obtain the smooth collision-free optimal path set between weld points and to construct the objective function of travelling all weld points with the shortest path length and highest smoothness. The multiobjective elitist-simulated annealing genetic algorithm (MESAGA) is used to achieve the welding sequence planning of all weld points. The variable neighborhood search method improves the mutation operator; the elitist strategy is introduced to improve the probability of elitist individual crossover and mutation operation, and a simulated annealing algorithm is used to jump out of local search to obtain the global optimal solution. According to the motion constraints, the joint space path is obtained by the optimal path in Cartesian space. Simulation analysis results demonstrate that the hybrid path planning method based on the memetic algorithm can effectively optimize the path of spot welding robots and lay the foundation for control and trajectory planning during welding processes.

A Bioinspired Soft Robot Combining the Growth Adaptability of Vine Plants with a Coordinated Control System.

Tip-extending soft robots, taking flexible film or rubber as body material and fluid pressure as input power, exhibit excellent advantages in constrained and cluttered environments for detection and manipulation. However, existing soft continuum robots are of great challenges in achieving multiple, mutually independent, and on-demand active steering over a long distance without precise steering control. In this paper, we introduce a vine-like soft robot made up of a pressurized thin-walled vessel integrated with the high controllability of a control system with multiple degrees of freedom in three dimensions. Moreover, steering and kinematic models to relate the steering angle and robot length to the location of the robot tip are provided, and a dynamic finite element model for analyzing the motion of the spatial consecutive steering is established. We demonstrate the abilities of disinfection of the robot moving in a long and tortuous pipeline and detection in a multi-obstacle constrained environment. It is established that the robot exhibits great advantages in active consecutive steering over a long distance, high controllability in completing more complex path planning, and significant ability of carrying operational tools for ventilation pipeline disinfection and multi-obstacle detection. The bionic soft robot shows great promise for use in environment sensing, target detecting, and equipment servicing.

Robotic path planning for non-destructive testing – A custom MATLAB toolbox approach

The requirement to increase inspection speeds for non-destructive testing (NDT) of composite aerospace parts is common to many manufacturers. The prevalence of complex curved surfaces in the industry provides motivation for the use of 6 axis robots in these inspections. The purpose of this paper is to present work undertaken for the development of a KUKA robot manipulator based automated NDT system. A new software solution is presented that enables flexible trajectory planning to be accomplished for the inspection of complex curved surfaces often encountered in engineering production. The techniques and issues associated with conventional manual inspection techniques and automated systems for the inspection of large complex surfaces were reviewed. This approach has directly influenced the development of a MATLAB toolbox targeted to NDT automation, capable of complex path planning, obstacle avoidance, and external synchronization between robots and associated external NDT systems. This paper highlights the advantages of this software over conventional off-line-programming approaches when applied to NDT measurements. An experimental validation of path trajectory generation, on a large and curved composite aerofoil component, is presented. Comparative metrology experiments were undertaken to evaluate the real path accuracy of the toolbox when inspecting a curved 0.5 m2 and a 1.6 m2 surface using a KUKA KR16 L6-2 robot. The results have shown that the deviation of the distance between the commanded TCPs and the feedback positions were within 2.7 mm. The variance of the standoff between the probe and the scanned surfaces was smaller than the variance obtainable via commercial path-planning software. Tool paths were generated directly on the triangular mesh imported from the CAD models of the inspected components without need for an approximating analytical surface. By implementing full external control of the robotic hardware, it has been possible to synchronise the NDT data collection with positions at all points along the path, and our approach allows for the future development of additional functionality that is specific to NDT inspection problems. For the current NDT application, the deviations from CAD design and the requirements for both coarse and fine inspections, dependent on measured NDT data, demand flexibility in path planning beyond what is currently available from existing off-line robot programming software.

Design and Testing of a 2-DOF Ball Drive

Omnidirectional mobile robots offer interesting features for industrial and service applications, in particular, when operating in tight spaces. Compared to car-like nonholonomic vehicles, they provide a higher degree of maneuverability, and often require less complex path planning and control schemes. Three different types of holonomic wheels that enable omnidirectional motion have been proposed in literature: universal, Mecanum, and ball wheel mechanisms. A problem commonly associated with the first two wheel types is that they induce vibrations in the system due to the discontinuous contact points. In this article, a ball wheel mechanism with superior features including slip measurement, free-wheel modus and attrition sensing is presented. The first prototype was built using additive manufacturing. The requirements for the design and possible improvements for future versions are discussed. Based on the presented ball wheel drive, a design for an omnidirectional mobile robot platform driven by three redundant ball wheel units is proposed. The velocity kinematic model of this mobile base is also addressed. Moreover, motion planning for an individual ball drive is demonstrated by means of an online trajectory generation scheme. The pseudocode of the trajectory planning algorithm implemented in LabVIEW is then presented. Finally, the motion characteristics of the ball drive mechanism are tested and its functionality is evaluated in detail. Measurements obtained from these tests show that the slip between the ball wheel and the ground can be estimated quite accurately. Hence, it is expected that these improved dead-reckoning estimates will result in a higher positioning accuracy of the final base.