Real-Time Robot Path Planning via a Distance-Propagating Dynamic System with Obstacle Clearance

Willms, Allan R.; Yang, Simon X.

doi:10.1109/tsmcb.2008.921002

Cited by 62 publications

(43 citation statements)

References 22 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Yang and Meng developed this idea initially for robot planning [13] and then for a path planning with enhanced obstacle avoidance [14]. In last years the algorithms based on [11] are evolved by the addition of penalty function [15] or a modified pulse-coupled neural network model [16]. In the present work, the total input u i of the generic i -th neuron is…”

Section: Definition Of the Path Priority And Coming Back: The Neuralmentioning

confidence: 99%

Design of UAV for Surveillance Purposes

Cheli

Ripamonti

Vendramelli

2015

Special Topics in Structural Dynamics, Volume 6

View full text Add to dashboard Cite

Two main algorithms are presented to use an UAV for surveillance purposes. A very fast algorithm for the scan of an unknown area has been implemented and tested: it permits to scan a domain for the definition of layout, boundaries, obstacles : : : Once that the area has been acquired, a second algorithm is used to monitor the regions of interest in an efficient way. A neural network has been built in order to choose the shortest path to reach a determined point, giving the drone the possibility to avoid unexpected obstacles. Finally these two algorithms has been tested to verify their accuracy and speed. IntroductionOver the last years, Unmanned Aerial Vehicles (UAV) have been applied in several interesting fields. The improvement and diffusion of control strategies both in terms of vibration suppression/stability [1] and path following [4] allowed to extend their application field. In this paper we propose to use a quadcopter for private, both domestic and industrial, surveillance purposes. The work begins with the implementation of an algorithm to scan an empty area: the UAV moves freely into given boundaries that have been identified from a sonar or laser camera, having the ability to avoid every kind of obstacle. Complete coverage path planning methods are many in literature. Already at the end of the 80s Lumelsky and Stepanov gave the idea of a complete sensor-based methods [5]. Neumann de Carvalho, Vidal, Viera, Ribeiro implemented a complete coverage path planning algorithm for a cleaning robot, but in their case the map of the area was a priori known [6]. In [7] Yang and Lao propose to scan the entire area by the implementation of a neural network.In this work we propose a simple and fast algorithm using the information received by the sensors mounted on the drone to scan the unknown area: this is filled with sparse obstacles (fixed or moving), added randomly all over the feasible surface. Our algorithm is thus able to identify boundaries and obstacles, and to avoid them.Moreover, pursuing the idea of security, the UAV should be forced to come back, after a given time, on regions that have been already scanned. Many articles has been written on this goal, achieving the result with genetic algorithms [8] and fuzzy logic approaches [9].However we focused our attention on the neural network approach, which seems the best compromise between speed and complexity requests, and which is a strengthened method for that kind of problems. One of the first attempts to apply a neural network in an industrial environment was proposed by Rivals, Canvas, Peronnaz, Dreyfus in [10], solving a complex automotive control problem using dynamical neural network models. Then Glasius, Komoda, Gielen in [11] tried to face a problem of path planning using a topologically organized neural network of a Hopifield type with nonlinear analog neurons. In terms of obstacle avoidance, a neural network model learning from human driving data is used by Djugash, Hammer in [12].Therefore, a pseudo-neural network was added to the mai...

show abstract

Section: Definition Of the Path Priority And Coming Back: The Neuralmentioning

confidence: 99%

Design of UAV for Surveillance Purposes

Cheli

Ripamonti

Vendramelli

2015

Special Topics in Structural Dynamics, Volume 6

View full text Add to dashboard Cite

show abstract

“…Recently, they further developed a grid-based algorithm via a distancepropagating dynamic system [29]. The algorithm is similar to the D* algorithm, but it does not maintain a sorted queue of points to update.…”

Section: Related Work On Dynamic Path Planningmentioning

confidence: 99%

“…Focusing on robot path planning in uncertain environments in which any changes such as the appearance and disappearance of one or more obstacles can be detected by robot sensors [34], the D* method [22] and its variants [23][24][25][26]29] use grids to represent the environments. However, moving obstacles can be described more easily using obstacle vertices.…”

Section: Motivations Of This Workmentioning

confidence: 99%

Dynamic robot path planning using an enhanced simulated annealing approach

Miao

Tian

2013

Applied Mathematics and Computation

113

View full text Add to dashboard Cite

“…Willms and Yang [18] proposed a dynamic system for real-time AUV path planning. They further developed a grid-based algorithm for real-time AUV path planning via a distance-propagating dynamic system in [18].…”

Section: Intelligent Automation and Soft Computing 16mentioning

confidence: 99%

A Heuristic Field Navigation Approach for Autonomous Underwater Vehicles

Miao

Huang

2014

Intelligent Automation & Soft Computing

View full text Add to dashboard Cite

As an effective path planning approach, Potential Field Method has been widely used for Autonomous Underwater Vehicles (AUVs) in underwater probing projects. However, the complexity of the realistic environments (e.g. the three dimensional environments rather than two dimensional environments, and limitations of the sensors in AUVs) have limited most of the current potential field approaches, in which the approaches can only be adapted to theoretic environments such as 2D or static environments. A novel heuristic potential field approach (HPF) incorporating a heuristic obstacle avoidance method is proposed in this paper for AUVs path planning in three dimensional environments which have dynamic targets. The contributions of this paper are: (1) The approach is able to provide solutions for more realistic and difficult conditions (such as three dimensional unknown environments and dynamic targets) rather than hypothetic environments (flat 2D known static environments); (2) The approach results in less computation time while giving better trade-offs among simplicity, far-field accuracy, and computational cost. The performance of the HPF is compared with previous published Simulated Annealing (SA) and Genetic Algorithm (GA) based methods. They are analyzed in several environments. The performance of the heuristic potential field approach is demonstrated through case studies not only to be effective in obtaining the optimal solution but also to be more efficient in processing time for dynamic path planning.

show abstract

Real-Time Robot Path Planning via a Distance-Propagating Dynamic System with Obstacle Clearance

Cited by 62 publications

References 22 publications

Design of UAV for Surveillance Purposes

Design of UAV for Surveillance Purposes

Dynamic robot path planning using an enhanced simulated annealing approach

A Heuristic Field Navigation Approach for Autonomous Underwater Vehicles

Contact Info

Product

Resources

About