A method for tracking the pose of a mobile robot equipped with a scanning laser range finder

Dubrawski, Artur; Siemiątkowska, B.

doi:10.1109/robot.1998.680720

Cited by 17 publications

(9 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While tactile information is particularly used for object recognition in manipulation [39]- [42], audio can be used for identifying directions and locations [43]- [45]. Depth data may be used by both robot manipulators or mobile robots [32], [46], [47].…”

Section: A Perceptionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning in Robotics: Survey on Model Structures and Training Strategies

Karoly

Galambos

Kuti

et al. 2021

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

The ever-increasing complexity of robot applications induces the need for methods to approach problems with no (viable) analytical solution. Deep learning (DL) provides a set of tools to address this kind of problems. This survey presents a categorization of the major challenges in robotics that leverage DL technologies and introduces representative examples of successful solutions for the described problems. We also consider the question when and whether to use modular, monolithic models or end-to-end DL, in order to provide a guideline for the selection of the correct model structure and training strategy. By doing so, the current role and adaptability of different techniques at different hierarchical levels of a robot-application can be highlighted, thus providing a well-structured basis to assist future approaches. Index Terms-Deep learning (DL), machine learning (ML), manipulators, mobile robots, neural networks, robot control, robot learning. I. INTRODUCTION C OMPUTERS can easily solve formal problems that are demanding for humans. However, the increasing need for adaptive systems requires the solution of tasks that are hard to formulate, but can be easily solved by humans, such as the recognition and manipulation of objects. In order to perform such tasks, a certain complex knowledge of the environment is inevitable. The automatic extraction of the required knowledge is called machine learning (ML). The way the data is presented to the ML system, heavily influences how well the extracted knowledge represents the given problem. The ML approaches that also perform feature extraction, using multiple hierarchical artificial neural network layers, are referred to as deep learning (DL) [1], [2]. The theoretical background of DL had been introduced for a long time, when it finally gained widespread popularity, i.a., thanks to the winner entry of the ImageNet Challenge Manuscript

show abstract

Section: A Perceptionmentioning

confidence: 99%

“…A common requirement for intelligent robot systems is to flexibly adapt to novel tasks and environments, while being reliable and computationally efficient. Conventional analytic solutions do not scale well for motion planning problems with high dimensionality, so for these tasks DL-based solutions are also sought [47], [53]- [58].…”

Section: B Motionmentioning

confidence: 99%

Deep Learning in Robotics: Survey on Model Structures and Training Strategies

Karoly

Galambos

Kuti

et al. 2021

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

show abstract

“…This improved approach has following advantages comparing to the original one [6]. First, considering the effect of sensor noise, we use a weighted criterion to judge whether the new point belongs to the line or not.…”

Section: Line Feature Extractionmentioning

confidence: 99%

Mobile robot indoor map building and pose tracking using laser scanning

Zhuang¹,

Shu-bo²,

Liu³

et al.

2004 International Conference on Intelligent Mechatronics and Automation, 2004. Proceedings.

View full text Add to dashboard Cite

Map building and pose tracking are central tasks ter an autttaewotls mobile robot's navigation. The intention of this paper is to introduce our research in mobile robot indoor map building and pose tracking using laser range finder. The line feature extraction methods, which include improved angle histograms algorithm and weighted least square fitting, are proposed firstly. We then discuss the criterion of lines merging in map building. The pose tracking approach based on Extended Kalman Filter is also presented in this paper. Conclusions and experimental results based on a real mobile platform are also given in the final part of this paper. Index Terms -Map building, pose tracking, laser scanner, extend Kalman fdter, uncertainty representation.

show abstract

“…They presented a fuzzy logic supervisor with three inputs, two outputs and 24 fuzzy rules. Other approaches of using fuzzy logic to adopt the Kalman filter for sensor fusion applications have been documented in [11][12][13][14][15]. On the other hand, the information form of the Kalman filter was briefly discussed in [9], and recently Mutambara [9] employed information estimation as a principal filtering technique.…”

Section: Introductionmentioning

confidence: 99%

“…At time k , obtain the bearing measurements Z ( k ) and compute the updating j , ( k l k ) and Y,(kI k ) using Eqs (15)(16)…”

mentioning

confidence: 99%

Laser pose tracking for a mobile robot using fuzzy adaptive extended information filtering

Chang

Tsai

Hsu

et al.

Proceedings of the 2003 American Control Conference, 2003.

View full text Add to dashboard Cite

This paper presents a laser pose tracking method for a mobile robot using fuzzy adaptive extended information filtering (FAEIF).The FAEIF, composed of a fuzzy tuner, is proposed to improve the performance of the EIF, and to avoid the EIF divergence problems caused by the noise variations or occurrence of modeling errors. By monitoring the innovation sequences, the fuzzy tuner adjusts on-line the key parameter of the EIF and thus improves accuracy and robustness of its estimates. Through simulation and experiment results, the proposed laser-scanner-based pose estimation method has been proven capable of giving satisfactory performance and overcoming the filter divergence problems under the noise variations and occurrence of modeling errors.

show abstract

A method for tracking the pose of a mobile robot equipped with a scanning laser range finder

Cited by 17 publications

References 3 publications

Deep Learning in Robotics: Survey on Model Structures and Training Strategies

Deep Learning in Robotics: Survey on Model Structures and Training Strategies

Mobile robot indoor map building and pose tracking using laser scanning

Laser pose tracking for a mobile robot using fuzzy adaptive extended information filtering

Contact Info

Product

Resources

About