Local map-based exploration for mobile robots

Authors:
Hyejeong Ryu;Wan Kyun Chung
Affiliations:
Robotics Laboratory, Department of Mechanical Engineering, Pohang University of Science and Technology (POSTECH), Pohang, Korea;Robotics Laboratory, Department of Mechanical Engineering, Pohang University of Science and Technology (POSTECH), Pohang, Korea
Venue:
Intelligent Service Robotics
Year:
2013

Citing 11
Cited 0

Generalized best-first search strategies and the optimality of A*

Journal of the ACM (JACM)
Integrating Exploration, Localization, Navigation and Planning with a Common Representation

Autonomous Robots
A frontier-based approach for autonomous exploration

CIRA '97 Proceedings of the 1997 IEEE International Symposium on Computational Intelligence in Robotics and Automation
A practical approach for EKF-SLAM in an indoor environment: fusing ultrasonic sensors and stereo camera

Autonomous Robots
Monte Carlo localization in outdoor terrains using multilevel surface maps

Journal of Field Robotics - Special Issue on Field and Service Robotics
Exploring unknown environments with mobile robots using coverage maps

IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
FastSLAM 2.0: an improved particle filtering algorithm for simultaneous localization and mapping that provably converges

IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Active-semantic localization with a single consumer-grade camera

SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
Topological map induction using neighbourhood information of places

Autonomous Robots
Hierarchical SLAM: Real-Time Accurate Mapping of Large Environments

IEEE Transactions on Robotics
Large-Scale SLAM Building Conditionally Independent Local Maps: Application to Monocular Vision

IEEE Transactions on Robotics

Quantified Score

Hi-index	0.00

Visualization

Abstract

For an accurate and efficient exploration, a local map-based exploration strategy is proposed. Segmented frontiers and relative transformations constitute a tree structure; using frontier segmentation and a local map management method, a robot can expand the mapped environment by moving along the tree structure. Although this local map-based exploration method uses only local maps and adjacent node information, mapping completion and efficiency can be greatly improved by merging and updating the frontier nodes. Simulation results demonstrate that the computational time does not increase during the exploration process, or when the resulting map becomes large. Additionally, the resulting path is effective in reducing the uncertainty in simultaneous localization and mapping or localization because of the loop-inducing characteristics from the child node to the parent node.