Trajectory Planning Amidst Moving Obstacles: Path-Velocity Decomposition Revisited

This paper describes a new method of pathplanning for multiple robots in unknown environments. The method, called Space D*, is based on two algorithms: the D*, which is an incremental graph search algorithm, and the Space Colonization algorithm, previously used to simulate crowd behaviors. The path-planning is achieved through the exchange of information between the robots. So decentralized, each robot performs its path-planning, which provides an obstacle-free path with the least number of robots around. The major contribution of the proposed method is that it generates paths in spacious environments facilitating the control of robots and thus presenting itself in a viable way for using in areas populated with multiple robots. The results obtained validate the approach and show the advantages in comparison with using only the D* method.

show abstract

“…Planning collision-free motions for autonomous robots located in environments with obstacles is one of the main problems of robotics [9,15,16].…”

Section: Introductionmentioning

confidence: 99%

Space D*

et al. 2012

View full text Add to dashboard Cite

show abstract

“…This constitutes a first-order approximation. In the path velocity decomposition, 31,32 the motion planning problem is divided into two stages: (1) planning a geometric path that avoids stationary obstacles, and (2) planning the velocity along this path to avoid obstacles. A problem arises when a moving obstacle stops on the planned path.…”

Section: Introductionmentioning

confidence: 99%

Collision course by transformation of coordinates and plane decomposition

Bendjilali

Belkhouche

2009

Robotica

View full text Add to dashboard Cite

This paper deals with the problem of collision course checking in a dynamic environment for mobile robotics applications. Our method is based on the relative kinematic equations between moving objects. These kinematic equations are written under polar form. A transformation of coordinates is derived. Under this transformation, collision between two moving objects is reduced to collision between a stationary object and a virtual moving object. In addition to the direct collision course, we define the indirect collision course, which is more critical and difficult to detect. Under this formulation, the collision course problem is simplified, and complex scenarios are reduced to simple scenarios. In three-dimensional (3D) settings, the working space is decomposed into two planes: the horizontal plane and the vertical plane. The collision course detection in 3D is studied in the vertical and horizontal planes using 2D techniques. This formulation brings important simplifications to the collision course detection problem even in the most critical and difficult scenarios. An extensive simulation is used to illustrate the method in 2D and 3D working spaces.

show abstract

“…He also showed that it might be necessary to speed up a trajectory to make it dynamically feasible. The reader can refer to Fraichard 1993, Fiorini and Shiller 1995, Fraichard 1998, Kuffner and Latombe 2000, Hsu et al 2002 for more details about the trajectory planning of robots moving in dynamic environments. obtaining accurate dynamic equations in some cases and the kinematic approaches might be more appropriate than the dynamic ones).…”

Section: Probabilistic Path Planning Approachesmentioning

confidence: 99%

Trajectory planning for industrial robot using genetic algorithms

Abu‐Dakka¹

View full text Add to dashboard Cite

En el nombre de Allah, el Misericordioso, el Compasivo(1) ¡Lee en el nombre de su Señor que ha creado! (2) Ha creado al hombre de un coágulo. ABSTRACTIn the last decades, many researches have been proposed concerning the path and trajectory planning for manipulators. Path and trajectory planning have important applications in many areas, for example industrial robotics, autonomous systems, virtual prototyping, and computer-aided drug design. On the other hand, the evolutionary algorithms have been applied in this plethora of fields, which motivates the author's interest on its application to the path and trajectory planning for industrial robots.In this work, an exhaustive search of the existing literature related to the thesis has been carried out, which has served to create a comprehensive database used to perform a detailed historical review of developments since its origins to the current state of the art and the latest trends.This thesis presents a new methodology that uses genetic algorithms to develop and evaluate path and trajectory planning algorithms. Problem-specific knowledge and heuristic knowledge are incorporated into encoding, evaluation and genetic operators of the genetic algorithm.This methodology introduces new approaches that aim at solve the problem of path planning and trajectory planning for industrial robotic systems operating in 3D environments with static obstacles. Therefore, two algorithms (somehow, they are similar, but with some variations) are created to solve the mentioned planning problems.Obstacles modeling have been done by using combinations of simple geometric objects (spheres, cylinders, and plans) which provide an efficient algorithm for collision avoidance. Trajectory Planning for Industrial Robots Using Genetic AlgorithmsPath planning algorithm is based on global genetic algorithms optimization techniques, which aim to minimize the sum of the distances between significant points of the robot along the path considering the restrictions to avoid collisions with obstacles. The path is composed of adjacent configurations obtained by an optimization technique using genetic algorithms, seeking to minimize a multiobjective function that involves the distance between significant points of the two adjacent configurations, and the distance from the points of the current configuration to the final one. An evaluation method is designed according to the problem presentation by defining individuals and genetic operators capable of providing efficient solutions to the problem. The result of this algorithm is the shortest path between two configurations given by the user.Trajectory planning algorithm is also based on genetic algorithms optimization techniques using the direct procedure. The algorithm is similar to the mentioned previously algorithm for path planning problem, but with some differences in the objective function and some details related to the conceptual difference between path and trajectory planning. The objective of this algorithm is to minimize the time required to mo...

show abstract

Trajectory Planning Amidst Moving Obstacles: Path-Velocity Decomposition Revisited

Cited by 8 publications

References 0 publications

Space D*

Space D*

Collision course by transformation of coordinates and plane decomposition

Trajectory planning for industrial robot using genetic algorithms

Contact Info

Product

Resources

About