Automatic Tuning of RatSLAM’s Parameters by Irace and Iterative Closest Point

Menezes, Matheus Chaves; Munoz, Mauro E. S.; Freitas, Edison P.; Cheng, Sen; Walther, Thomas; Neto, Areolino A.; Ribeiro, Paulo F.; Oliveira, Alexandre César Muniz de

doi:10.1109/iecon43393.2020.9254718

Cited by 5 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the accuracy and performance contexts (item (i)), xRatSLAM has already been used by researchers in experiments that require shorter execution times to perform time-consuming tasks, such as parameter tuning in long-term mapping [ 30 , 31 ]. However, opportunities for enhancements are highlighted below to show how the framework can be improved: Other RatSLAM module implementations; A built-in assessment module for mapping accuracy evaluation; Dynamic libraries (plug-ins) in the module inclusion mechanism; Support for 3D SLAM, as required for unmanned aerial vehicles (UAV: drones) or uncrewed underwater vehicles (UUV); A ROS wrapper for xRatSLAM; An interface for other programming languages such as Python; A module repository for sharing implementations between different users; Usability improvements to suit neuroscience theorists and practitioners.…”

Section: Conclusion and Future Workmentioning

confidence: 99%

xRatSLAM: An Extensible RatSLAM Computational Framework

Muñoz

Menezes

Freitas

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Simultaneous localization and mapping (SLAM) refers to techniques for autonomously constructing a map of an unknown environment while, at the same time, locating the robot in this map. RatSLAM, a prevalent method, is based on the navigation system found in rodent brains. It has served as a base algorithm for other bioinspired approaches, and its implementation has been extended to incorporate new features. This work proposes xRatSLAM: an extensible, parallel, open-source framework applicable for developing and testing new RatSLAM variations. Tests were carried out to evaluate and validate the proposed framework, allowing the comparison of xRatSLAM with OpenRatSLAM and assessing the impact of replacing framework components. The results provide evidence that the maps produced by xRatSLAM are similar to those produced by OpenRatSLAM when they are fed with the same input parameters, which is a positive result, and that implemented modules can be easily changed without impacting other parts of the framework.

show abstract

Section: Conclusion and Future Workmentioning

confidence: 99%

xRatSLAM: An Extensible RatSLAM Computational Framework

Muñoz

Menezes

Freitas

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…On the other hand, the global optimization approach, which is based on saving some keyframes in the environment and uses bundle adjustment to estimate the motion [ 4 ], is currently a popular approach for vision-based SLAM such as ORB-SLAM [ 5 , 6 , 7 ] and also Google’s cartographer [ 8 , 9 ]. In addition to solving SLAM problems, the convolutional neural network SLAM which is currently available as RatSLAM is proven to have a superior performance in some situations [ 10 , 11 ].…”

Section: Introductionmentioning

confidence: 99%

Path Planning and Motion Control of Indoor Mobile Robot under Exploration-Based SLAM (e-SLAM)

Roy

Sheu

et al. 2023

Sensors

View full text Add to dashboard Cite

Indoor mobile robot (IMR) motion control for e-SLAM techniques with limited sensors, i.e., only LiDAR, is proposed in this research. The path was initially generated from simple floor plans constructed by the IMR exploration. The path planning starts from the vertices which can be traveled through, proceeds to the velocity planning on both cornering and linear motion, and reaches the interpolated discrete points joining the vertices. The IMR recognizes its location and environment gradually from the LiDAR data. The study imposes the upper rings of the LiDAR image to perform localization while the lower rings are for obstacle detection. The IMR must travel through a series of featured vertices and perform the path planning further generating an integrated LiDAR image. A considerable challenge is that the LiDAR data are the only source to be compared with the path planned according to the floor map. Certain changes still need to be adapted into, for example, the distance precision with relevance to the floor map and the IMR deviation in order to avoid obstacles on the path. The LiDAR setting and IMR speed regulation account for a critical issue. The study contributed to integrating a step-by-step procedure of implementing path planning and motion control using solely the LiDAR data along with the integration of various pieces of software. The control strategy is thus improved while experimenting with various proportional control gains for position, orientation, and velocity of the LiDAR in the IMR.

show abstract