A volumetric representation for obstacle detection in vegetated terrain

Lourenço, André; Marques, Francisco; Santana, Pedro; Barata, José

doi:10.1109/robio.2014.7090344

Cited by 4 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Localisation is estimated with an Extended Kalman Filter, fed by a PhidgetSpatial Inertial Measurement Unit (IMU), from Phidgets, and a GPS-RTK Proflex 800, from Ashtec SAS. Motion planning is carried out using conventional motion and path planning techniques [14] operating on a cost map [15].…”

Section: The Unmanned Ground Vehicle (Ugv)mentioning

confidence: 99%

An Aerial-Ground Robotic Team for Systematic Soil and Biota Sampling in Estuarine Mudflats

Deusdado¹,

Pinto

Guedes³

et al. 2015

Advances in Intelligent Systems and Computing

Self Cite

View full text Add to dashboard Cite

This paper presents an aerial-ground field robotic team, designed to collect and transport soil and biota samples in estuarine mudflats. The robotic system has been devised so that its sampling and storage capabilities are suited for radionuclides and heavy metals environmental monitoring. Automating these time-consuming and physically demanding tasks is expected to positively impact both their scope and frequency. The success of an environmental monitoring study heavily depends on the statistical significance and accuracy of the sampling procedures, which most often require frequent human intervention. The bird's-eye view provided by the aerial vehicle aims at supporting remote mission specification and execution monitoring. This paper also proposes a preliminary experimental protocol tailored to exploit the capabilities o↵ered by the robotic system. Preliminary field trials in real estuarine mudflats show the ability of the robotic system to successfully extract and transport soil samples for o✏ine analysis.

show abstract

Section: The Unmanned Ground Vehicle (Ugv)mentioning

confidence: 99%

An Aerial-Ground Robotic Team for Systematic Soil and Biota Sampling in Estuarine Mudflats

Deusdado¹,

Pinto

Guedes³

et al. 2015

Advances in Intelligent Systems and Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…The possibility of having distributed modules extends techniques such as the one presented in [12]. Allowing not only the choice of the most efficient navigation mode for the environment but also the ability to turn on and off software modules and hardware components.…”

Section: Software Architecturementioning

confidence: 99%

A Health and Usage Monitoring System for ROS-based service robots

Pinto

Deusdado²,

Marques

et al. 2015

2015 10th International Symposium on Mechatronics and Its Applications (ISMA)

Self Cite

View full text Add to dashboard Cite

This paper presents a multi-core processing solution for ROS-based service robots. The power management together with the control and availability of the processing resources are supervised by a custom-made Power Management Board (PMB) based on a Digital Signal Processor (DSP) micro controller, implementing a Health and Usage Monitoring System (HUMS). The proposed architecture also allows for the PMB to control the most critical robot functions in case of low battery conditions or impossibility of performing energy harvesting, thus extending the lifespan of the robot. All PMB data is recorded on a SD card so as to allow offline analyses of the robotic mission and, thus, support subsequent maintenance activities. Two different implementations of the proposed system have been fielded in two Multi-Robot Systems (MRS) for environmental monitoring, covering aerial, water surface, and wheeled ground vehicles. An additional implementation of the architecture is currently being deployed on an industrial autonomous logistics robot. These three implementations are presented and discussed.

show abstract

“…Related work: Volumetric representation [9,10] is the direct way to apply deep learning to transform data into volumetric representation, such as, voxel grids [11]. In this way, the 3D filter without the neural network can be used to train a CNN.…”

mentioning

confidence: 99%

Point‐selection and multi‐level‐point‐feature fusion‐based 3D point cloud classification

et al. 2020

View full text Add to dashboard Cite

Recent years, the research on object classification based on threedimensional (3D) point cloud pays more attention to extract the features from point sets directly. PointNet++ is the latest network structure for 3D classification which has achieved acceptable results. Although it has achieved acceptable results, there are still two problems: (i) The farthest point sampling (FPS) algorithm in PointNet++ ignores the fact that the feature of each point contributes differently to the classification and segmentation tasks. Therefore, FPS cannot guarantee that the selected point sets can correctly represent the main features of the object. (ii) The multi-scale grouping and multi-resolution grouping in PointNet++ do not consider the features between different levels of the same point. In order to solve these problems, the authors propose the point-selection structure which can calculate the importance of each point's feature. In addition, multi-level-point-feature fusion module is proposed to extract the features of the point at all levels and fuse them as a new feature of that point. In this Letter, they make some experiments on ModelNet40 and ScanNet datasets, which achieves better results compared to the state-of-the-art methods.

show abstract

A volumetric representation for obstacle detection in vegetated terrain

Cited by 4 publications

References 21 publications

An Aerial-Ground Robotic Team for Systematic Soil and Biota Sampling in Estuarine Mudflats

An Aerial-Ground Robotic Team for Systematic Soil and Biota Sampling in Estuarine Mudflats

A Health and Usage Monitoring System for ROS-based service robots

Point‐selection and multi‐level‐point‐feature fusion‐based 3D point cloud classification

Contact Info

Product

Resources

About