Abstract Scan registration is an essential subtask when building maps based on range finder data from mobile robots. The problem to deduce how the robot has moved between consecutive scans, shape of overlapping portions scans. This paper presents a new algorithm for 3D data. generalization and improvement normal distributions transform (NDT) 2D developed by Biber Strasser, which allows accurate using memory‐efficient representation scan surface. A detailed quantitative qualitative comparison...

Registration of range sensor measurements is an important task in mobile robotics and has received a lot attention. Several iterative optimization schemes have been proposed order to align three-dimensional (3D) point scans. With the more widespread use high-frame-rate 3D sensors increasingly challenging application scenarios for robots, there need fast accurate registration methods that current state-of-the-art algorithms cannot always meet. This work proposes novel algorithm achieves cloud...

Gas source localization (GSL) with mobile robots is a challenging task due to the unpredictable nature of gas dispersion, limitations currents sensing technologies, and mobility constraints ground-based robots. This work proposes an integral solution for GSL task, including declaration. We present novel pseudo-gradient-based plume tracking algorithm particle filter-based declaration approach, apply it on gas-sensitive micro-drone. compare performance proposed system in simulations real-world...

To advance robotic science it is important to perform experiments that can be replicated by other researchers compare different methods. However, these comparisons tend biased, since re-implementations of reference methods often lack thoroughness and do not include the hands-on experience obtained during original development process. This paper presents a thorough comparison 3D scan registration algorithms based on mapping field experiment, carried out two research groups are leading in...

This article presents the development and validation of an autonomous, gas sensitive microdrone that is capable estimating wind vector in real time using only onboard control unit performing distribution mapping (DM). Two different sampling approaches are suggested to address this problem. On one hand, a predefined trajectory used explore target area with real-world DM experiment. As alternative approach, we introduce adaptive strategy suggests next points based on artificial potential field...

Gas distribution modelling constitutes an ideal application area for mobile robots, which - as intelligent gas sensors offer several advantages compared to stationary sensor networks. In this paper we propose the Kernel DM+V algorithm learn a statistical 2-d model from sequence of localized measurements. The does not make strong assumptions about sensing locations and can thus be applied on robot that is primarily used monitoring, also in case treats density estimation problem. contrast most...

This paper describes the development and validation of currently smallest aerial platform with olfaction capabilities. The developed Smelling Nano Aerial Vehicle (SNAV) is based on a lightweight commercial nano-quadcopter (27 g) equipped custom gas sensing board that can host up to two in situ metal oxide semiconductor (MOX) sensors. Due its small form-factor, SNAV not hazard for humans, enabling use public areas or inside buildings. It autonomously carry out missions hazardous environments...

The upcoming new generation of autonomous vehicles for transporting materials in industrial environments will be more versatile, flexible and efficient than traditional AGVs, which simply follow pre-defined paths. However, freely navigating can appear unpredictable to human workers thus cause stress render joint use the available space inefficient. Here we address this issue propose on-board intention projection on shared floor communication from robot human. We present a research prototype...

Eye tracking is getting increasingly popular in mathematics education research. Studies predominantly rely on the so-called eye-mind hypothesis (EMH), which posits that what persons fixate closely relates to they process. Given EMH was developed reading research, we see risk implicit assumptions are tacitly adopted even though may not apply this domain. This article investigates extent applies mathematics—geometry particular—and aims lift discussion of inferences can be validly made from...

This work presents a simulation framework developed under the widely used Robot Operating System (ROS) to enable validation of robotics systems and gas sensing algorithms realistic environments. The is rooted in principles computational fluid dynamics filament dispersion theory, modeling wind flow 3D real-world scenarios (i.e., accounting for walls, furniture, etc.). Moreover, it integrates different environmental sensors, such as metal oxide photo ionization detectors, or anemometers. We...

Object detection is crucial in diverse autonomous systems like surveillance, driving, and driver assistance, ensuring safety by recognizing pedestrians, vehicles, traffic lights, signs. However, adverse weather conditions such as snow, fog, rain pose a challenge, affecting accuracy risking accidents damage. This clearly demonstrates the need for robust object solutions that work all conditions. We employed three strategies to enhance deep learning-based weather: training on real-world...

Airborne chemical sensing with mobile robots has been an active research areasince the beginning of 1990s. This article presents a review work in this field,including gas distribution mapping, trail guidance, and different subtasks sourcelocalisation. Due to difficulty modelling real world environmentwith currently available simulation techniques, we focus largely on experimental donot consider publications that are purely based simulations.

We propose a new approach to appearance based loop detection from metric 3D maps, exploiting the NDT surface representation. Locations are described with feature histograms on orientation and smoothness, closure can be detected by matching histograms. also present quantitative performance evaluation using two real-world data sets, showing that proposed method works well in different environments.

Roboticists often take inspiration from animals for designing sensors, actuators, or algorithms that control the behavior of robots. Bio-inspiration is motivated with uncanny ability to solve complex tasks like recognizing and manipulating objects, walking on uneven terrains, navigating source an odor plume. In particular task tracking plume up its has nearly exclusively been addressed using biologically inspired robots have developed, example, mimic moths, dung beetles, lobsters. this paper...

In order to enable long-term operation of autonomous vehicles in industrial environments numerous challenges need be addressed. A basic requirement for many applications is the creation and maintenance consistent 3D world models. This article proposes a novel spatial representation online real-world mapping, building upon two known representations: normal distributions transform (NDT) maps occupancy grid maps. The proposed map (NDT-OM) combines advantages both representations; compactness...

Industrial applications often impose hard requirements on the precision of autonomous vehicle systems. As a consequence industrial Automatically Guided Vehicle (AGV) systems still use high-cost infrastructure based positioning solutions. In this paper we propose map localization method that fulfills and repeatability, typical for application scenarios. The proposed - Normal Distributions Transform Monte Carlo Localization (NDT-MCL) is well established probabilistic framework. novel...

In this paper we propose a new grid based approach to model dynamic environment. Each cell is assumed be an independent Markov chain (iMac) with two states. The state transition parameters are learned online and modeled as Poisson processes. As result, our representation not only encodes the expected occupancy of cell, but also models dynamics within cell. presents strategy on recency weighting learn from observations that able deal non-stationary dynamics. Moreover, interpretation...

So far, autonomous order picking (commissioning) systems have not been able to meet the stringent demands regarding speed, safety, and accuracy of real-world warehouse automation, resulting in reliance on human workers. In this letter, we target next step robot commissioning: automatizing currently manual procedure. To end, investigate use case palletizing with a dedicated research platform discuss lessons learned during testing simplified settings. The main theoretical contribution is novel...

In this article, we address the problem of realizing a complete efficient system for automated management fleets autonomous ground vehicles in industrial sites. We elicit from current practice and scientific state art key challenges related to transport environments relate them enabling techniques perception, task allocation, motion planning, coordination, collision prediction, control. propose modular approach based on least commitment, which integrates all modules through uniform...