tinySLAM: A SLAM algorithm in less than 200 lines C-language program

Steux, Bruno; Hamzaoui, Oussama El

doi:10.1109/icarcv.2010.5707402

Cited by 74 publications

(50 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Theoretically, the first method extracts features from range scans, such as lines, corners, and semicircles of tree trunks, and then matches the extracted known features with a generated feature map to recognize the position. In relative positioning, on the contrary, scan matching utilizes two or more consecutive frames of scan points to directly obtain the movement mobile platform with various algorithms, e.g., classical Iterative Closest Point (ICP) [23], Iterative Closest Line (ICL) [24], Monte Carlo [25], and Maximum Likelihood Estimation (MLE) [26,27]. SLAM is mainly utilized in robotics for various indoor applications.…”

Section: Slam Developed For Forestrymentioning

confidence: 99%

SLAM-Aided Stem Mapping for Forest Inventory with Small-Footprint Mobile LiDAR

Tang

Chen

Kukko

et al. 2015

Forests

View full text Add to dashboard Cite

Accurately retrieving tree stem location distributions is a basic requirement for biomass estimation of forest inventory. Combining Inertial Measurement Units (IMU) with Global Navigation Satellite Systems (GNSS) is a commonly used positioning strategy in most Mobile Laser Scanning (MLS) systems for accurate forest mapping. Coupled with a tactical or consumer grade IMU, GNSS offers a satisfactory solution in open forest environments, for which positioning accuracy better than one decimeter can be achieved. However, for such MLS systems, positioning in a mature and dense forest is still a challenging task because of the loss of GNSS signals attenuated by thick canopy. Most often laser scanning sensors in MLS systems are used for mapping and modelling rather than positioning. In this paper, we investigate a Simultaneous Localization and Mapping (SLAM)-aided positioning solution with point clouds collected by a small-footprint LiDAR. Based on the field test data, we evaluate the potential of SLAM positioning and mapping in forest inventories. The results show that the positioning accuracy in the selected test field is improved by 38% compared to that of a traditional tactical grade IMU + GNSS positioning system in a mature forest environment and, as a result, we are able to produce a unambiguous tree distribution map.

show abstract

Section: Slam Developed For Forestrymentioning

confidence: 99%

SLAM-Aided Stem Mapping for Forest Inventory with Small-Footprint Mobile LiDAR

Tang

Chen

Kukko

et al. 2015

Forests

View full text Add to dashboard Cite

show abstract

“…2) Maximum Likelihood SLAM: We use the tinySLAM algorithm [19], which is based on the Incremental Maximum Likelihood principle and which solely estimates the most probable robot position on a 2D map. In lieu of "laser" range and bearing measurements, we simply extract the horizon line from the depth images from the Kinect sensor, and convert it to a (range, bearing) representation, spanning about 60 degrees with 0.25deg steps.…”

Section: B Fast Visual Estimation Of Bearing Anglesmentioning

confidence: 99%

Depth camera SLAM on a low-cost WiFi mapping robot

Mirowski¹,

Palaniappan²,

Ho³

2012

2012 IEEE International Conference on Technologies for Practical Robot Applications (TePRA)

View full text Add to dashboard Cite

Abstract-Radio-Frequency fingerprinting is an interesting solution for indoor localization. It exploits existing telecommunication infrastructure, such as WiFi routers, along with a database of signal strengths at different locations, but requires manually collecting signal measurements along with precise position information. To automatically build signal maps, we use an autonomous, self-localizing, low-cost mobile robotic platform.Our robot relies on the Kinect depth camera that is limited by a narrow field of view and short range. Our two-stage localization architecture first performs real-time obstacle-avoidance-based navigation and visual-based odometry correction for bearing angles. It then uses RGB-D images for Simultaneous Localization and Mapping. We compare the applicability of 6-degrees-offreedom RGB-D SLAM, and of particle filtering 2D SLAM algorithms and present novel ideas for loop closures. Finally, we demonstrate the use of the robot for WiFi localization in an office space.

show abstract

“…A comparison with SLAM approaches (Carmen) is also given, and the results for three datasets show that the scan matching with quadtrees gives promising results (small offset). The SLAM algorithm presented in [8] retained our attention because it was designed to be run in real time and the source code is publicly available. It is designed to use the measurements from a laser range scanner.…”

Section: Iirelated Workmentioning

confidence: 99%

High level assisted control mode based on SLAM for a remotely controlled robot

Devaux

Nadrag

Colle

et al. 2011

2011 15th International Conference on Advanced Robotics (ICAR)

View full text Add to dashboard Cite

level assisted control mode based on SLAM for a remotely controlled robot.15th International Conference on Advanced Robotics (ICAR 2011), Jun 2011, Tallinn, Estonia. pp.186-191, 2011, <10.1109/ICAR.2011. Abstract-Our aim in ambient assistive technologies is to reduce long term hospitalization for elderly people, especially with pathologies such as Mild Cognitive Impairment (MCI). The smart environment assists these people and their families for safety and cognitive stimulation so they stay as long as possible at home. The originality comes from using the robot in the elderly person's home. This robot is remote controlled by a distant user, a therapist or a relation, for determining alarming situations or for participating in stimulation exercises. Several modes are possible for controlling the robot. This paper deals with an assisted control mode in which the remote user gives to the robot one goal then the robot reaches the goal by itself. During the robot movement, the user can dynamically change the current goal. An important hypothesis is that the robot has no a priori knowledge on its environment at the beginning. The knowledge will increase with time and the planned trajectory will be refreshed at two levels: a local one -faster but not always sufficient-and a global one -slower but which always finds a path if one exists-. The idea is to work only with local information, using the robot sensors, the operator keeping the high level control. To assure that control, the remote operator uses a video feedback and information from a laser range.

show abstract

tinySLAM: A SLAM algorithm in less than 200 lines C-language program

Cited by 74 publications

References 4 publications

SLAM-Aided Stem Mapping for Forest Inventory with Small-Footprint Mobile LiDAR

SLAM-Aided Stem Mapping for Forest Inventory with Small-Footprint Mobile LiDAR

Depth camera SLAM on a low-cost WiFi mapping robot

High level assisted control mode based on SLAM for a remotely controlled robot

Contact Info

Product

Resources

About