A Fast Random Walk Approach to Find Diverse Paths for Robot Navigation

Palmieri, Luigi; Rudenko, Andrey; Arras, Kai O.

doi:10.1109/lra.2016.2602240

Cited by 14 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method uses the distance measurement between the goal point and the sampled states [44]. Fast random walk approach that determines diverse and efficient paths from different Homotopy class have also been proposed to improve robotic path planning [45].…”

Section: Collision Avoidance and Safetymentioning

confidence: 99%

The Effect of Obstacle Design Architectures on Randomly Ranging AGVs in a Shared Workspace

Chowdhury¹,

Singh²,

Kluse³

et al. 2021

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

Section: Collision Avoidance and Safetymentioning

confidence: 99%

The Effect of Obstacle Design Architectures on Randomly Ranging AGVs in a Shared Workspace

Chowdhury¹,

Singh²,

Kluse³

et al. 2021

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

“…Besides, the potential field method can make an instantaneous and smooth robot movement path without an additional controller, but it has a local minima problem that is caused by positions with zero force value where the robot or agent stops and cannot move any further [11,12]. There are some techniques to overcome the local minima problem, such as random walk [13,14] or backtracking. In the case of the random walk technique, it is impossible to predict the path or the processing time because of randomness.…”

Section: Introductionmentioning

confidence: 99%

Water Sink Model for Robot Motion Planning

Jeon

Jung

2019

Sensors

View full text Add to dashboard Cite

There are various motion planning techniques for robots or agents, such as bug algorithm, visibility graph, Voronoi diagram, cell decomposition, potential field, and other probabilistic algorithms. Each technique has its own advantages and drawbacks, depending on the number and shape of obstacles and performance criteria. Especially, a potential field has vector values for movement guidance to the goal, and the method can be used to make an instantaneous and smooth robot movement path without an additional controller. However, there may be some positions with zero force value, called local minima, where the robot or agent stops and cannot move any further. There are some solutions for local minima, such as random walk or backtracking, but these are not yet good enough to solve the local minima problem. In this paper, we propose a novel movement guidance method that is based on the water sink model to overcome the previous local minima problem of potential field methods. The concept of the water sink model is to mimic the water flow, where there is a sink or bathtub with a plughole and floating piece on the water. The plughole represents the goal position and the floating piece represents robot. In this model, when the plug is removed, water starts to drain out via the plughole and the robot can always reach the goal by the water flow. The water sink model simulator is implemented and a comparison of experimental results is done between the water sink model and potential field.

show abstract

“…Sutantyo combined LF and an artificial potential field to improve the SE, with the potential field generating a repulsive force between pairs of robots, thereby dispersing neighboring robots [26]. Palmieri proposed using a weighted RW to find multiple paths among dynamical obstacles to improve the performance of robot navigation [27]. To explore the correlation between RW methods and the environment, Dimidov et al used a swarm of Kilobots to search for a static target in different environments; the experimental results revealed which type of RW was best suited to each experimental scenario [28].…”

Section: Introductionmentioning

confidence: 99%

A Swarm Robotic Exploration Strategy Based on an Improved Random Walk Method

Pang

Song

Zhang

et al. 2019

Journal of Robotics

View full text Add to dashboard Cite

An environment can be searched far more efficiently if the appropriate search strategy is used. Because of the limited individual abilities of swarm robots, namely, local sensing and low processing power, random searching is the main search strategy used in swarm robotics. The random walk methods that are used most commonly are Brownian motion and Lévy flight, both of which mimic the self-organized behavior of social insects. However, both methods are somewhat limited when applied to swarm robotics, where having the robots search repeatedly can result in highly inefficient searching. Therefore, by analyzing the characteristics of swarm robotic exploration, this paper proposes an improved random walk method in which each robot adjusts its step size adaptively to reduce the number of repeated searches by estimating the density of robots in the environment. Simulation experiments and experiments with actual robots are conducted to study the effectiveness of the proposed method and evaluate its performance in an exploration mission. The experimental results presented in this paper show that an area is covered more efficiently using the proposed method than it is using either Brownian motion or Lévy flight.

show abstract

A Fast Random Walk Approach to Find Diverse Paths for Robot Navigation

Cited by 14 publications

References 14 publications

The Effect of Obstacle Design Architectures on Randomly Ranging AGVs in a Shared Workspace

The Effect of Obstacle Design Architectures on Randomly Ranging AGVs in a Shared Workspace

Water Sink Model for Robot Motion Planning

A Swarm Robotic Exploration Strategy Based on an Improved Random Walk Method

Contact Info

Product

Resources

About