An efficient Genetic Algorithm for the global robot path planning problem

Alnasser, Sarah; Bennaceur, Hachémi

doi:10.1109/dictap.2016.7544008

Cited by 18 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Differently in [37], the authors modify A * path planning to make the search more efficient in large graph structures. In [38], a genetic algorithm is provided to find a global path in a grid environment. In [39], a CNN method is used on planetary images to derive a global path for interplanetary rovers.…”

Section: A Related Workmentioning

confidence: 99%

Temporal Graph Traversals Using Reinforcement Learning With Proximal Policy Optimization

2020

View full text Add to dashboard Cite

Graphs in real-world applications are dynamic both in terms of structures and inputs. Information discovery in such networks, which present dense and deeply connected patterns locally and sparsity globally can be time consuming and computationally costly. In this paper we address the shortest path query in spatio-temporal graphs which is a fundamental graph problem with numerous applications. In spatiotemporal graphs, shortest path query classical algorithms are insufficient or even flawed because information consistency can not be guaranteed between two timestamps and path recalculation is computationally costly. In this work, we address the complexity and dynamicity of the shortest path query in spatio-temporal graphs with a simple, yet effective model based on Reinforcement Learning with Proximal Policy Optimization. Our solution simplifies the problem by decomposing the spatio-temporal graph in two components: a static and a dynamic sub-graph. The static graph, known and immutable, is efficiently solved with A * algorithm. The sub-graphs interconnecting the static graph have unknown dynamics and we address such issue by estimating the unknown dynamic portion of the graph as a Markov Chain which correlates the observations of the agents in the environment and the path to be followed. We then derive an action policy through Proximal Policy Optimization to select the local optimal actions in the Markov Process that will lead to the shortest path, given the estimated system dynamics. We evaluate the system in a simulation environment constructed in Unity3D. In partially structured and unknown environments, with variable environment parameters we've obtained an efficiency 75% greater than the comparable deterministic solution.

show abstract

Section: A Related Workmentioning

confidence: 99%

Temporal Graph Traversals Using Reinforcement Learning With Proximal Policy Optimization

2020

View full text Add to dashboard Cite

show abstract

“…Ismail et al (2008) have conducted a study in which an idea has been presented for the use of the genetic algorithm in mobile robot navigation, which enables the robot to generate a much-optimized path for reaching the target. Alnasser and Bennaceur (2016) have proposed a new form of genetic algorithm which has been designed for modelling and resolving the problems encountered in path planning. The suggested genetic algorithm makes use of a suitable solution portrayal and effective cross over operation shows a notable increase in the fitness function in various aspects of the motion of the mobile robot.…”

Section: Introductionmentioning

confidence: 99%

Design of a hybrid controller using genetic algorithm and neural network for path planning of a humanoid robot

Rath¹,

Parhi

Das

et al. 2020

IJIUS

View full text Add to dashboard Cite

PurposeTo navigate humanoid robots in complex arenas, a significant level of intelligence is required which needs proper integration of computational intelligence with the robot's controller. This paper describes the use of a combination of genetic algorithm and neural network for navigational control of a humanoid robot in given cluttered environments.Design/methodology/approachThe experimental work involved in the current study has been done by a NAO humanoid robot in laboratory conditions and simulation work has been done by the help of V-REP software. Here, a genetic algorithm controller is first used to generate an initial turning angle for the robot and then the genetic algorithm controller is hybridized with a neural network controller to generate the final turning angle.FindingsFrom the simulation and experimental results, satisfactory agreements have been observed in terms of navigational parameters with minimal error limits that justify the proper working of the proposed hybrid controller.Originality/valueWith a lack of sufficient literature on humanoid navigation, the proposed hybrid controller is supposed to act as a guiding way towards the design and development of more robust controllers in the near future.

show abstract

“…Una de las técnicas que sobresalen sobre otras en la planificación de caminos son las basadas en algoritmos genéticos, debido a su capacidad de explorar el espacio de búsqueda preservando la mejor solución ya encontrada. En los últimos años muchos planificadores de caminos basados en AG han sido implementados (Hsu & Liu, 2014), (Alnasser & Bennaceur, 2016). Una de las limitaciones presente en estos trabajos es que todos comienzan con una solución inicial aleatoria, o adoptan un método aleatorio para generar una solución inicial válida.…”

Section: Introductionunclassified

Planificación de caminos y trayectorias de una formación de robots autónomos

Pereyra

Araguás²,

Paina³

et al. 2020

AJEA

View full text Add to dashboard Cite

En este trabajo se presentan los últimos resultados en investigación en el marco de la tesis Planificación de caminos y trayectorias de una formación de robots autónomos. La planificación de camino consiste en encontrar un camino continuo que lleve a un robot desde su posición inicial a su destino, evitando colisiones con su entorno. Basado en el método de exploración del Algoritmo Genético Simple (AGS) y del algoritmo de búsqueda clásico A*, se propone un algoritmo híbrido de planificación de caminos para sistemas multirobots. Este algoritmo encuentra los caminos óptimos (o casi-óptimos) libres de colisiones de una formación de robots desde una configuración inicial a una configuración final teniendo en cuenta la posibilidad de separación y su posterior reunión. Los resultados de las simulaciones demuestran que el algoritmo es apto para ser utilizado en entornos complejos con obstáculos y para un sistema mutlirobots.

show abstract

An efficient Genetic Algorithm for the global robot path planning problem

Cited by 18 publications

References 10 publications

Temporal Graph Traversals Using Reinforcement Learning With Proximal Policy Optimization

Temporal Graph Traversals Using Reinforcement Learning With Proximal Policy Optimization

Design of a hybrid controller using genetic algorithm and neural network for path planning of a humanoid robot

Planificación de caminos y trayectorias de una formación de robots autónomos

Contact Info

Product

Resources

About