An Improved Reactive Navigation Method for Mobile Robots using Potential Fields

2021 ◽  
Vol 2021 (0) ◽  
pp. 1P2-G13
Author(s):  
Ankit A. Ravankar ◽  
Abhijeet Ravankar ◽  
Takanori Emaru ◽  
Yukinori Kobayashi
Keyword(s):  
Mobile Robots ◽  
Potential Fields ◽  
Reactive Navigation ◽  
Navigation Method

scholarly journals Interval Type-2 Neural Fuzzy Controller-Based Navigation of Cooperative Load-Carrying Mobile Robots in Unknown Environments

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4181 ◽  
Author(s):  
Chun-Hui Lin ◽  
Shyh-Hau Wang ◽  
Cheng-Jian Lin
Keyword(s):  
Mobile Robots ◽  
Control Method ◽  
Fuzzy Controller ◽  
Bee Colony ◽  
Load Carrying ◽  
Navigation Control ◽  
Interval Type ◽  
Navigation Method ◽  
Neural Fuzzy

In this paper, a navigation method is proposed for cooperative load-carrying mobile robots. The behavior mode manager is used efficaciously in the navigation control method to switch between two behavior modes, wall-following mode (WFM) and goal-oriented mode (GOM), according to various environmental conditions. Additionally, an interval type-2 neural fuzzy controller based on dynamic group artificial bee colony (DGABC) is proposed in this paper. Reinforcement learning was used to develop the WFM adaptively. First, a single robot is trained to learn the WFM. Then, this control method is implemented for cooperative load-carrying mobile robots. In WFM learning, the proposed DGABC performs better than the original artificial bee colony algorithm and other improved algorithms. Furthermore, the results of cooperative load-carrying navigation control tests demonstrate that the proposed cooperative load-carrying method and the navigation method can enable the robots to carry the task item to the goal and complete the navigation mission efficiently.

scholarly journals A hand-drawn map-based navigation method for mobile robots using objectness measure

2019 ◽  
Vol 16 (3) ◽  
pp. 172988141984633 ◽  
Author(s):  
Jie Niu ◽  
Kun Qian
Keyword(s):  
Mobile Robots ◽  
Autonomous Navigation ◽  
Saliency Map ◽  
Experimental Results ◽  
Environment Map ◽  
Environmental Cognition ◽  
Candidate Regions ◽  
Cognitive Environment ◽  
Candidate Object ◽  
Navigation Method

Correct cognition of the environment is the premise of mobile robots to realize autonomous navigation control tasks. The inconsistency caused by time-varying environmental information is a bottleneck for the development and application of cognitive environment technologies. In this article, we propose an environmental cognition method that uses a hand-drawn map. Firstly, we use the single skeleton refinement and fuzzy c-means algorithms to segment the image. Then, we select candidate regions combining the saliency map. At the same time, we use the superpixels straddling method to filter the windows. The final candidate object regions are obtained based on a fusion of saliency segmentation and superpixels clustering. Based on the above objectness estimation results, we use a human–computer interaction method to construct an inaccurate hand-drawn environment map for navigation. The experimental results from PASCAL VOC2007 validate the efficacy of the proposed objectness measure method, where our result of 41.2% on mean average precision is the best of the tested methods. Furthermore, the experimental results of robot navigation in the actual scene also verified the effectiveness of the proposed approach.

Issues of Motion Control of Mobile Robots Based on the Potential Guidance Method

2019 ◽  
Vol 20 (11) ◽  
pp. 677-685
Author(s):  
A. B. Filimonov ◽  
N. B. Filimonov
Keyword(s):  
Mobile Robots ◽  
Motion Control ◽  
A Priori ◽  
Target Position ◽  
Potential Fields ◽  
Modified Method ◽  
Working Space ◽  
Local Navigation ◽  
Virtual Forces ◽  
Priori Information

One of the topical areas of research in modern robotics is the problem of local navigation of mobile robots (MR), which ensures the movement of the robot to the target with the bypass of obstacles in the process of movement. The navigation process includes the following steps: mapping the environment, localization of the robot and planning the route leading to the goal. Among the popular methods of local navigation of robots is the method of artificial potential fields (PF). The essence of the PF method is to implement the movement of the MR in the field of "information forces" using the forces of "attraction" to the target position and the forces of "repulsion" from obstacles.This article addresses the issues of local navigation and motion control of the MR based on the method of PF.When using traditional attracting potential forces, the structure of virtual forces near the obstacle depends on the distance of the MR from the target, and the robot movement will slow down at the end of the route, which will inevitably lead to an unjustified tightening of the total time of moving the robot to the target position. To eliminate this undesirable effect, the authors propose to use attracting potential fields of special type.The authors propose new methods of PF allowing to solve the key problems for the control of MR — "traps" (potential pits) and bypass obstacles: the method of two maps of potential fields and the method of "fairway" on the map of potential fields. The methods of "beetle" for solving the problem of bypass obstacles in the condition of the absence of a priori information about the working space of MR are discussed. A modified method of "beetle" having a number of advantages in comparison with classical methods is proposed. 

Real-time nonparametric reactive navigation of mobile robots in dynamic environments

2017 ◽  
Vol 91 ◽  
pp. 11-24 ◽  
Author(s):  
Sungjoon Choi ◽  
Eunwoo Kim ◽  
Kyungjae Lee ◽  
Songhwai Oh
Keyword(s):  
Mobile Robots ◽  
Real Time ◽  
Dynamic Environments ◽  
Reactive Navigation
Sign in / Sign up

Export Citation Format

Share Document