Filtern
Erscheinungsjahr
Dokumenttyp
Sprache
- Englisch (24)
- Mehrsprachig (1)
Schlagworte
Organisationseinheit der BAM
Gas source localization with a micro-drone using bio-inspired and particle filter-based algorithms
(2013)
Gas source localization (GSL) with mobile robots is a challenging task due to the unpredictable nature of gas dispersion, the limitations of the currents sensing technologies, and the mobility constraints of ground-based robots. This work proposes an integral solution for the GSL task, including source declaration. We present a novel pseudo-gradient-based plume tracking algorithm and a particle filter-based source declaration approach, and apply it on a gas-sensitive micro-drone. We compare the performance of the proposed system in simulations and real-world experiments against two commonly used tracking algorithms adapted for aerial exploration missions.
This paper presents a sampling strategy for mobile gas sensors. Sampling points are selected using a modified artificial potential field (APF) approach, which balances multiple criteria to direct sensor measurements towards locations of high mean concentration, high concentration variance and areas for which the uncertainty about the gas distribution model is still large. By selecting in each step the most often suggested close-by measurement location, the proposed approach introduces a locality constraint that allows planning suitable paths for mobile gas sensors. Initial results in simulation and in real-world experiments with a gas-sensitive micro-drone demonstrate the suitability of the proposed sampling strategy for gas distribution mapping and its use for gas source localization.
Roboticists often take inspiration from animals for designing sensors, actuators or algorithms that control the behaviour of robots. Bio-inspiration is motivated with the uncanny ability of animals to solve complex tasks like recognizing and manipulating objects, walking on uneven terrains, or navigating to the source of an odour plume. In particular the task of tracking an odour plume up to its source has nearly exclusively been addressed using biologically inspired algorithms and robots have been developed, for example, to mimic the behaviour of moths, dungbeetles, or lobsters. In this paper we argue that biomimetic approaches to gas source localization are of limited use, primarily because animals differ fundamentally in their sensing and actuation capabilities from state-of-the-art gas-sensitive mobile robots. To support our claim, we compare actuation and chemical sensing available to mobile robots to the corresponding capabilities of moths. We further characterize airflow and chemosensor measurements obtained with three different robot platforms (two wheeled robots and one flying micro drone) in four prototypical environments and show that the assumption of a constant and unidirectional airflow, which is at the basis of many gas source localization approaches, is usually far from being valid. This analysis should help to identify how underlying principles, which govern the gas source tracking behaviour of animals, can be usefully 'translated' into gas source localization approaches that fully take into account the capabilities of mobile robots. We also describe the requirements for a reference application, monitoring of gas emissions at landfill sites with mobile robots, and discuss an engineered gas source localization approach based on statistics as an alternative to biologically-inspired algorithms.
This article presents the development and validation of an autonomous, gas sensitive microdrone that is capable of estimating the wind vector in real time using only the onboard control unit of the microdrone and performing gas distribution mapping (DM). Two different sampling approaches are suggested to address this problem. On the one hand, a predefined trajectory is used to explore the target area with the microdrone in a real-world gas DM experiment. As an alternative sampling approach, we introduce an adaptive strategy that suggests next sampling points based on an artificial potential field (APF). Initial results in real-world experiments demonstrate the capability of the proposed adaptive sampling strategy for gas DM and its use for gas source localization.
Carbon capture & storage (CCS) is one of the most promising technologies for greenhouse gas (GHG) management. However, an unsolved issue of CCS is the development of appropriate long-term monitoring systems for leak detection of the stored CO2. To complement already existing monitoring infrastructure for CO2 storage areas, and to increase the granularity of gas concentration measurements, a quickly deployable, mobile measurement device is needed. In this paper, we present an autonomous gas-sensitive micro-drone, which can be used to monitor GHG emissions, more specifically, CO2. Two different measurement strategies are proposed to address this task. First, the use of predefined sensing trajectories is evaluated for the task of gas distribution mapping using the micro-drone. Alternatively, we present an adaptive strategy, which suggests sampling points based on an artificial potential field (APF). The results of real-world experiments demonstrate the feasibility of using gas-sensitive micro-drones for GHG monitoring missions. Thus, we suggest a multi-layered surveillance system for CO2 storage areas.
In this paper, we show that a micro unmanned aerial vehicle (UAV) equipped with commercially available gas sensors can address environmental monitoring and gas source localization (GSL) tasks. To account for the challenges of gas sensing under real-world conditions, we present a probabilistic approach for GSL that is based on a particle filter (PF). Simulation and real-world experiments demonstrate the suitability of this algorithm for micro UAV platforms.
Gas distribution mapping is important to have an accurate understanding of gas concentration levels in hazardous environments. A major problem is that in-situ gas sensors are only able to measure concentrations at their specific location. The gas distribution in-between the sampling locations must therefore be modeled. In this research, we interpret the task of spatial interpolation between sparsely distributed sensors as a task of enhancing an image's resolution, namely super-resolution. Because autoencoders are proven to perform well for this super-resolution task, we trained a convolutional encoder-decoder neural network to map the gas distribution over a spatially sparse sensor network. Due to the difficulty to collect real-world gas distribution data and missing ground truth, we used synthetic data generated with a gas distribution simulator for training and evaluation of the model. Our results show that the neural network was able to learn the behavior of gas plumes and outperforms simpler interpolation techniques.
To better understand the dynamics in hazardous environments, gas distribution mapping aims to map the gas concentration levels of a specified area precisely. Sampling is typically carried out in a spatially sparse manner, either with a mobile robot or a sensor network and concentration values between known data points have to be interpolated. In this paper, we investigate sequential deep learning models that are able to map the gas distribution based on a multiple time step input from a sensor network. We propose a novel hybrid convolutional LSTM - transpose convolutional structure that we train with synthetic gas distribution data. Our results show that learning the spatial and temporal correlation of gas plume patterns outperforms a non-sequential neural network model.
Wireless sensor networks provide occupational health experts with valuable information about the distribution of air pollutants in an environment. However, especially low-cost sensors may produce faulty measurements or fail completely. Consequently, not only spatial coverage but also redundancy should be a design criterion for the deployment of a sensor network. For a sensor network deployed in a steel factory, we analyze the correlations between sensors and build machine learning forecasting models, to investigate how well the sensor network can compensate for the outage of sensors. While our results show promising prediction quality of the models, they also indicate the presence of spatially very limited events. We, therefore, conclude that initial measurements with, e.g., mobile units, could help to identify important locations to design redundant sensor networks.
The Sharp GP2Y1010AU0F is a widely used low-cost dust sensor, but despite its popularity, the manufacturer provides little information on the sensor. We installed 16 sensing nodes with Sharp dust sensors in a hot rolling mill of a steel factory. Our analysis shows a clear correlation between sensor drift and accumulated production of the steel factory. An eye should be kept on the long-term drift of the sensors to prevent early saturation. Two of 16 sensors experienced full saturation, each after around eight and ten months of operation.