In this paper, we present an algorithm for fully autonomous exploration and mapping of an unknown indoor robot environment. This algorithm is based on the active SLAM (simultaneous localization and mapping) approach. The mobile robot equipped with laser sensor builds a map of an environment, while keeping track of its current location. Autonomy is introduced to this system by automatically setting goal points so that either previously unknown space is mapped, or known landmarks are revisited in order to increase map accuracy. Final aim is to maximize both map coverage and accuracy. The proposed procedure is experimentally verified on Pioneer 3-DX mobile robot in real environment, using ROS framework for implementation.
This paper proposes a new reactive planning obstacles, mazes, and the like objects. To get out of the loop algorithm for mobile robot navigation in unknown environments. the robot must comprehend its repeated traversal through the The overall navigation system consists of three navigation same environment, which involves memorizing the subsystems. The lower level subsystem deals with the control of . a the linear and angular volocities using a multivariable PI envirnmentreadtsen [5].controller described with a full matrix. The position control of The main contribution of this paper is design of a robust the mobile robot is in the medium level, and it is a nonlinear. The autonomous mobile robot control system suitable for on-line nonlinear control design is implemented by a backstepping applications by using soft computing methodologies. This algorithm whose parameters are adjusted by a genetic algorithm. system provides the mobile robot that may navigate in an a The high level subsystem uses the Fuzzy logic and Dempster-priori unknown indoor environment using sonar sensors Shafer evidence theory to design the fusion of sensor data, map information. To achieve these requirements the proposed building and path planning tasks. The path planning algorithm is . :based on a modified potential field method. In this algorithm, the systemnishiearcicaly rganiz ito thee ct separated fuzzy rules for selecting the relevant obstacles for robot motion subsystems with arbitrary responsibility. At each level of this are introduced. Also, suitable steps are taken to pull the robot out system one or more soft computing methodologies are adopted of the local minima. A particular attention is paid to detection of to solve its specific problems. the robot's trapped state and its avoidance. One of the main issues A low level velocity controller is developed using the in this paper is to reduce the complexity of planning algorithms, standard PI multivariable control law. The medium level Simulation results show a good quality of position tracking .on control capabilities and obstacle avoidance behavior of the mobile robot. pstity w e hatsito nonleargnoe tozenr the stability of the error, that is its convergence to zero [6], [7]. Some of control parameters are continuous time functions, and I. INTRODUCTION usually the backstepping method [6], [8] was used for theirThe basic feature of an autonomous mobile robot is its adjustment. In order to achieve the optimal parameters values capability to operate independently in unknown or partially we used a genetic algorithm. known environments. The autonomy implies that the robot is A high level subsystem contains map building and path capable to react to static obstacles and unpredictable dynamic planning algorithms. In this paper the occupancy based map [9] events that may impede the successful execution of a task [1]. using Dempster-Shafer evidence theory based on sonar To achieve this level of robustness, methods need to be measurements is demonstrated. Also, we propose a new path developed...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.