Evaluating the Performances of the Agoraphilic Navigation Algorithm under Dead-Lock Situations

Hewawasam, H.S.; Ibrahim, M. Yousef; Kahandawa, Gayan; Choudhury, T. A.

doi:10.1109/isie45063.2020.9152280

Cited by 2 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The APF method is popular among researchers due to its many advantages, such as simplicity and adaptability. However, there are well-documented inherited problems in APF-based methods [7,12,13]. These inherited drawbacks, such as (i) trap situations or dead locks (local minima), (ii) no passage between closely spaced obstacles, (iii) oscillations in narrow corridors and (iv) the goal non-reachable-with-obstacles-nearby problem (GN-RON), have motivated researchers to improve the APF-based methods and overcome these problems [14][15][16][17].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning-Based Agoraphilic Navigation Algorithm for Use in Dynamic Environments with a Moving Goal

2023

Self Cite

View full text Add to dashboard Cite

This paper presents a novel development of a new machine learning-based control system for the Agoraphilic (free-space attraction) concept of navigating robots in unknown dynamic environments with a moving goal. Furthermore, this paper presents a new methodology to generate training and testing datasets to develop a machine learning-based module to improve the performances of Agoraphilic algorithms. The new algorithm presented in this paper utilises the free-space attraction (Agoraphilic) concept to safely navigate a mobile robot in a dynamically cluttered environment with a moving goal. The algorithm uses tracking and prediction strategies to estimate the position and velocity vectors of detected moving obstacles and the goal. This predictive methodology enables the algorithm to identify and incorporate potential future growing free-space passages towards the moving goal. This is supported by the new machine learning-based controller designed specifically to efficiently account for the high uncertainties inherent in the robot’s operational environment with a moving goal at a reduced computational cost. This paper also includes comparative and experimental results to demonstrate the improvements of the algorithm after introducing the machine learning technique. The presented experiments demonstrated the success of the algorithm in navigating robots in dynamic environments with the challenge of a moving goal.

show abstract

Section: Introductionmentioning

confidence: 99%

“…The database for v k,n also consists of seven fuzzy membership functions as shown in Equation (13). The variable v k,n is positive if the moving obstacle is approaching the robot.…”

mentioning

confidence: 99%