Fusing sonars and LRF data to perform SLAM in reduced visibility scenarios

Machado Santos, Joao, Couceiro, Micael S., Portugal, David and Rocha, Rui P. (2014) Fusing sonars and LRF data to perform SLAM in reduced visibility scenarios. In: IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), 2014, 14-15 May 2014, Espinho, Portugal.

06849772.pdf - Whole Document
Available under License Creative Commons Attribution.

Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive


Simultaneous Localization and Mapping (SLAM) approaches have evolved considerably in recent years. However, there are many situations which are not easily handled, such as the case of smoky, dusty, or foggy environments where commonly used range sensors for SLAM are highly disturbed by noise induced in the measurement process by particles of smoke, dust or steam. This work presents a sensor fusion method for range sensing in Simultaneous Localization and Mapping (SLAM) under reduced visibility conditions. The proposed method uses the complementary characteristics between a Laser Range Finder (LRF) and an array of sonars in order to ultimately map smoky environments. The method was validated through experiments in a smoky indoor scenario, and results showed that it is able to adequately cope with induced disturbances, thus decreasing the impact of smoke particles in the mapping task.

Keywords:SLAM, LRF, Sonar, Multisensor Fusion, Reduced Visibility
Subjects:H Engineering > H671 Robotics
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:14671
Deposited On:11 Aug 2014 09:21

Repository Staff Only: item control page