Hector Open Source Modules for Autonomous Mapping and Navigation with Rescue Robots

Kohlbrecher, Stefan; Meyer, Johannes; Graber, Thorsten; Petersen, Kai; Klingauf, Uwe; Stryk, Oskar von

doi:10.1007/978-3-662-44468-9_58

Cited by 117 publications

(75 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Future work will include the application of this algorithm to real-world speech source labeling, object labeling in camera networks as well as labeling of semantic information based on occupancy grid maps for autonomous mapping and navigation with multiple rescue robots [32]. …”

Section: Discussionmentioning

confidence: 99%

Robust and adaptive diffusion-based classification in distributed networks

Binder

Muma

Zoubir

2016

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Distributed adaptive signal processing and communication networking are rapidly advancing research areas which enable new and powerful signal processing tasks, e.g., distributed speech enhancement in adverse environments. An emerging new paradigm is that of multiple devices cooperating in multiple tasks (MDMT). This is different from the classical wireless sensor network (WSN) setup, in which multiple devices perform one single joint task. A crucial first step in order to achieve a benefit, e.g., a better node-specific audio signal enhancement, is the common unique labeling of all relevant sources that are observed by the network. This challenging research question can be addressed by designing adaptive data clustering and classification rules based on a set of noisy unlabeled sensor observations. In this paper, two robust and adaptive distributed hybrid classification algorithms are introduced. They consist of a local clustering phase that uses a small part of the data with a subsequent, fully distributed on-line classification phase. The classification is performed by means of distance-based similarity measures. In order to deal with the presence of outliers, the distances are estimated robustly. An extensive simulation-based performance analysis is provided for the proposed algorithms. The distributed hybrid classification approaches are compared to a benchmark algorithm where the error rates are evaluated in dependence of different WSN parameters. Communication cost and computation time are compared for all algorithms under test. Since both proposed approaches use robust estimators, they are, to a certain degree, insensitive to outliers. Furthermore, they are designed in a way that they are applicable to on-line classification problems.

show abstract

Section: Discussionmentioning

confidence: 99%

Robust and adaptive diffusion-based classification in distributed networks

Binder

Muma

Zoubir

2016

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

show abstract

“…We discussed in previous section how the LIDAR overcomes the limitations of both wheeled based and visual odometry in estimating the mobile robots' pose, which motivated our choice for this device. Similar to [12], we selected a single LIDAR using the Hector Simultaneous Localization and Mapping (SLAM) algorithm. The output of the algorithm is an accurate pose estimation of the mobile robot within its environment.…”

Section: Proposed Schemementioning

confidence: 99%

Combining Hector SLAM and Artificial Potential Field for Autonomous Navigation Inside a Greenhouse

Harik

Korsæth

2018

Robotics

View full text Add to dashboard Cite

Abstract:The key factor for autonomous navigation is efficient perception of the surroundings, while being able to move safely from an initial to a final point. We deal in this paper with a wheeled mobile robot working in a GPS-denied environment typical for a greenhouse. The Hector Simultaneous Localization and Mapping (SLAM) approach is used in order to estimate the robots' pose using a LIght Detection And Ranging (LIDAR) sensor. Waypoint following and obstacle avoidance are ensured by means of a new artificial potential field (APF) controller presented in this paper. The combination of the Hector SLAM and the APF controller allows the mobile robot to perform periodic tasks that require autonomous navigation between predefined waypoints. It also provides the mobile robot with a robustness to changing conditions that may occur inside the greenhouse, caused by the dynamic of plant development through the season. In this study, we show that the robot is safe to operate autonomously with a human presence, and that in contrast to classical odometry methods, no calibration is needed for repositioning the robot over repetitive runs. We include here both hardware and software descriptions, as well as simulation and experimental results.

show abstract

“…This approach utilises the high scan rates of modern LIDAR sensors, and provides a more accurate alternative to traditional odometry [18]. Scan alignment is performed based on optimising the alignment of the laser beam endpoints using Gauss-Newton optimisation approach to find the best alignment of the current laser scan data with the existing map through a rigid transform for some cost function [18].…”

Section: Hector Slammentioning

confidence: 99%

“…As discussed in section 3.2, Hector SLAM can be used in situations where the plane of the LIDAR changes, allowing 3D navigation. To achieve this an IMU is required and integrating this sensor information to track the transformation of the base to a stabilised base [18]. This consideration will be included in future work to give a more robust SLAM system.…”

Section: -Hector Slammentioning

confidence: 99%

An Improved Robot for Bridge Inspection

Peel¹,

Luo²,

Cohn³

et al. 2017

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

View full text Add to dashboard Cite

-This paper presents a significant improvement from the previous submission by the same authors at ISARC 2016. The robot is now equipped with low-cost cameras and a 2D laser scanner, which is used to monitor and survey a bridge bearing. The robot is capable of localising by combining data from a pre-surveyed 3D model of the space with real-time data collection in-situ. Autonomous navigation is also performed using the 2D laser scanner in a mapped environment. The Robot Operating System (ROS) framework is used to integrate data collection and communication for navigation.

show abstract

Hector Open Source Modules for Autonomous Mapping and Navigation with Rescue Robots

Cited by 117 publications

References 10 publications

Robust and adaptive diffusion-based classification in distributed networks

Robust and adaptive diffusion-based classification in distributed networks

Combining Hector SLAM and Artificial Potential Field for Autonomous Navigation Inside a Greenhouse

An Improved Robot for Bridge Inspection

Contact Info

Product

Resources

About