Search results

The purpose of this paper is to improve the performance of the genetic algorithm-based compliant robot path planning (GACRPP) in complex dynamic environment by proposing an improved bidirectional rapidly exploring random tree (Bi-RRT)-based population initialization method.

To achieve GACRPP in complex dynamic environment with high performance, an improved Bi-RRT-based population initialization method is proposed. First, the grid model is adopted to preprocess the working space of mobile robot. Second, an improved Bi-RRT is proposed to create multi-cluster connections between the starting point and the goal point. Third, the backtracking method is used to generate the initial population based on the multi-cluster connections generated by the improved Bi-RRT. Subsequently, some comparative experiments are implemented where the performances of the improved Bi-RRT-based population initialization method are compared with other population initialization methods, and the comparison results of the improved genetic algorithm (IGA) combining with the different population initialization methods are shown. Finally, the optimal path is further smoothed with the help of the technique of quadratic B-spline curves.

It is shown in the experiment results that the improved Bi-RRT-based population initialization method is capable of deriving a more diversified initial population with less execution time and the IGA combining with the proposed population initialization method outperforms the one with other population initialization methods in terms of the length of optimal path and the execution time.

In this paper, the Bi-RRT is introduced as a population initialization method into the GACRPP problem. An improved Bi-RRT is proposed for the purpose of increasing the diversity of initial population. To characterize the diversity of initial population, a new notion of breadth is defined in terms of Hausdorff distance between different paths.

The purpose of this paper is to present a new nested rapidly‐exploring random tree (RRT) algorithm for fault tolerant motion planning of robotic manipulators.

Another RRT algorithm is nested within the general RRT algorithm. This second nested level is used to check whether the new sampled node in the first nested level is fault tolerant. If a solution can be found in the second nested RRT, the reduced manipulator after failures at the new sampled node can still fulfill the remaining task and this new sampled node is added into the nodes of RRT in the first level. Thus, the nodes in the first level RRT algorithm are all fault tolerant postures. The final trajectory joined by these nodes is also obviously fault tolerant. Besides fault tolerance, this new nested RRT algorithm also can fulfill some secondary tasks such as improvement of dexterity and obstacle avoidance. Sufficient simulations and experiments of this new algorithm on fault tolerant motion planning of robotic manipulators are implemented.

It is found that the new nested RRT algorithm can fulfill fault tolerance and some other secondary tasks at the same time. Compared to other existing fault tolerant algorithms, this new algorithm is more efficient.

The paper presents a new nested RRT algorithm for fault tolerant motion planning.

The goal of this research is to develop a dynamic step path planning algorithm based on the rapidly exploring random tree (RRT) algorithm that combines Q-learning with the Gaussian distribution of obstacles. A route for autonomous vehicles may be swiftly created using this algorithm.

The path planning issue is divided into three key steps by the authors. First, the tree expansion is sped up by the dynamic step size using a combination of Q-learning and the Gaussian distribution of obstacles. The invalid nodes are then removed from the initially created pathways using bidirectional pruning. B-splines are then employed to smooth the predicted pathways.

The algorithm is validated using simulations on straight and curved highways, respectively. The results show that the approach can provide a smooth, safe route that complies with vehicle motion laws.

An improved RRT algorithm based on Q-learning and obstacle Gaussian distribution (QGD-RRT) is proposed for the path planning of self-driving vehicles. Unlike previous methods, the authors use Q-learning to steer the tree's development direction. After that, the step size is dynamically altered following the density of the obstacle distribution to produce the initial path rapidly and cut down on planning time even further. In the aim to provide a smooth and secure path that complies with the vehicle kinematic and dynamical restrictions, the path is lastly optimized using an enhanced bidirectional pruning technique.

The purpose of this study is to solve the problem of path planning and path tracking in the automatic parking assistant system.

This paper first uses the method of reverse driving to confirm few control points based on the constraints of the construction of the vehicle and the environment information, then a reference path with free-collision and continuous curvature is designed based on the Bézier curve. According to the principle of the discrete linear quadratic regulator (LQR), a tracking controller that combines feedforward control and feedback control is designed.

Finally, simulation analysis are carried out in Simulink and CARSIM. The results show that the proposed method can obtain a better path tracking effect when the parking space size is appropriate.

According to the principle of the discrete LQR, a tracking controller that combines feedforward control and feedback control is designed.

The purpose of this paper is to develop a real-time trajectory planner with optimal maneuver for autonomous vehicles to deal with dynamic obstacles during parallel parking.

To deal with dynamic obstacles for autonomous vehicles during parking, a long- and short-term mixed trajectory planning algorithm is proposed in this paper. In long term, considering obstacle behavior, A-star algorithm was improved by RS curve and potential function via spatio-temporal map to obtain a safe and efficient initial trajectory. In short term, this paper proposes a nonlinear model predictive control trajectory optimizer to smooth and adjust the trajectory online based on the vehicle kinematic model. Moreover, the proposed method is simulated and verified in four common dynamic parking scenarios by ACADO Toolkit and QPOASE solver.

Compared with the spline optimization method, the results show that the proposed method can generate efficient obstacle avoidance strategies, safe parking trajectories and control parameters such as the front wheel angle and velocity in high-efficient central processing units.

It is aimed at improving the robustness of automatic parking system and providing a reference for decision-making in a dynamic environment.

This paper aims to use the redundancy of a 7-DOF (degree of freedom) serial manipulator to solve motion planning problems along a given 6D Cartesian tool path, in the presence of geometric constraints, namely, obstacles and joint limits.

This paper describes an explicit expression of the task submanifolds for a 7-DOF redundant robot, and the submanifolds can be parameterized by two parameters with this explicit expression. Therefore, the global search method can find the feasible path on this parameterized graph.

The proposed planning algorithm is resolution complete and resolution optimal for 7-DOF manipulators, and the planned path can satisfy task constraint as well as avoiding singularity and collision. The experiments on Motoman SDA robot are reported to show the effectiveness.

This algorithm is still time-consuming, and it can be improved by applying parallel collision detection method or lazy collision detection, adopting new constraints and implementing more effective graph search algorithms.

Compared with other task constrained planning methods, the proposed algorithm archives better performance. This method finds the explicit expression of the two-dimensional task sub-manifolds, so it’s resolution complete and resolution optimal.

The purpose of this study is to solve the problems of poor stability and high energy consumption of the dynamic window algorithm (DWA) for the mobile robots, a novel enhanced dynamic window algorithm is proposed in this paper.

The novel algorithm takes the distance function as the weight of the target-oriented coefficient, and a new evaluation function is presented to optimize the azimuth angle.

The jitter of the mobile robot caused by the drastic change of angular velocity is reduced when the robot is closer to the target point. The simulation results show that the proposed algorithm effectively optimizes the stability of the mobile robot during operation with lower angular velocity dispersion and less energy consumption, but with a slightly higher running time than DWA.

A novel enhanced dynamic window algorithm is proposed and verified. According to the experimental result, the proposed algorithm can reduce the energy consumption of the robot and improves the efficiency of the robot.

Multi-robots simultaneously coverage and tracking (SCAT) is the problem of simultaneously covering area and tracking targets, which is essential for many applications, such as delivery service, environment monitor, traffic surveillance, crime monitor, anti-terrorist mission and so on. The purpose of this paper is to improve the performance of detected target quantity, coverage rate and less deadweight loss by designing a self-organized method for multi-robots SCAT.

A self-organized reciprocal control method is proposed, coupling task assignment, tracking and covering, equipped with collision-avoiding ability naturally. First, SCAT problem is directly modeled as optimal reciprocal coverage velocity (ORCV) in velocity space. Second, the preferred velocity is generated by calculating the best velocity to the center of some robot detected targets. ORCV is given by adjusting the velocity relative to neighbor robots’ toward in optimal coverage velocity (OCV); it is proven that OCV is collision-free assembly. Third, some corresponding algorithms are designed for finding optimal velocity under two situations, such as no detected targets and empty ORCV.

The simulation results of two cases for security robots show that the proposed method has detected more targets with less deadweight loss and decision time and no collisions anytime.

In this paper, a self-organized reciprocal control method is proposed for multi-robots SCAT problem, which is modeled in velocity space directly, different to the traditional method modeling in configuration space. What is more, this method considers the reciprocal of robots that contributes to the better accomplishment of SCAT cooperatively.