AMAli Marjovi

Ali Marjovi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ali Marjovi has a total of 28 co-authors. Here are the top co-authors by number of shared publications:

  • Lino Marques

    University of Coimbra

    13 shared publications
  • Alcherio Martinoli

    Distributed Intelligent Systems and Algorithms Laboratory, School of Architecture, Civil and Environmental Engineering, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland

    6 shared publications
  • Anibal T. de Almeida

    Institute of Systems and Robotics, Department of Electrical and Computer Engineering, University of Coimbra, 3030-290 Coimbra, Portugal

    4 shared publications
  • Adrian Arfire

    Distributed Intelligent Systems and Algorithms Laboratory, School of Architecture, Civil and Environmental Engineering, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland

    3 shared publications
  • Danial Kamran

    Department of Computer Engineering, Sharif University of Technology, Tehran, Iran

    2 shared publications
  • Mahmoud Tavakoli

    Institute of Systems and Robotics, University of Coimbra, 3030-290 Coimbra, Portugal

    2 shared publications

Latest Publications

  • Open Access

    Particle Source Localization With a Low-Cost Robotic Sensor System: Algorithmic Design and Performance Evaluation

    by Xinxing Chen, Ali Marjovi, Jian Huang, Alcherio Martinoli

    In this paper we tackle the problem of finding the source of particulate matter with a mobile robot equipped with a low-cost multi-channel optical particle counting sensor. The proposed method is based on the Infotaxis odor source localization algorithm and makes multiple modifications to adapt it to particle plumes. In particular, we propose three simple but efficient ways to fuse multiple probability maps associated with various particle sizes and use the resulted integrated map to guide the robot’s movements. A refined measurement data collection is conducted in a wind tunnel to fit the particle plume model. The method with three proposed integration strategies is evaluated in simulation and in the wind tunnel emulating realistic environmental conditions in a repeatable fashion. In particular, we have investigated the impact of two environmental parameters - the wind speed and source release rate on the algorithm performance. The proposed algorithm with the weighted multi-modality map integration strategy outperforms the original Infotaxis and the other two variants. In high wind speed, the proposed algorithm is able on average to estimate the source location with less than 1 meter error in the 80 m2 wind tunnel arena.


  • Adaptive Lévy Taxis for odor source localization in realistic environmental conditions

    by Romain Emery, Faezeh Rahbar, Ali Marjovi, Alcherio Martinoli

    Odor source localization with mobile robots has recently been subject to many research works, but remains a challenging task mainly due to the large number of environmental parameters that make it hard to describe gas concentration fields. We designed a new algorithm called Adaptive Lévy Taxis (ALT) to achieve odor plume tracking through a correlated random walk. In order to compare its performances with well-established solutions, we have implemented three moth-inspired algorithms on the same robotic platform. To improve the performance of the latter algorithms, we developed a rigorous way to determine one of their key parameters, the odor concentration threshold at which the robot considers to be inside or outside the plume. The methods have been systematically evaluated in a large wind tunnel under various environmental conditions. Experiments revealed that the performance of ALT is consistently good in all environmental conditions (in particular when compared to the three reference algorithms) in terms of both distance traveled to find the source and success rate.


  • Towards 3-D distributed odor source localization: An extended graph-based formation control algorithm for plume tracking

    by Jorge M. Soares, Ali Marjovi, Jonathan Giezendanner, Anil Kodiyan, A. Pedro Aguiar, Antonio M. Pascoal, Alcherio Martinoli

    The large number of potential applications for robotic odor source localization has motivated the development of a variety of plume tracking algorithms, the majority of which work in restricted two-dimensional scenarios. In this paper, we introduce a distributed algorithm for 3-D plume tracking using a system of ground and aerial robots in formation. We propose an algorithm that takes advantage of spatially distributed measurements to track the plume in 3-D and lead the robots to the source by integrating three behaviors - upwind movement, plume centering, and Laplacian feedback formation control. We evaluate this strategy in simulation and with real robots in a wind tunnel. For a source close to the ground, results show that a team of robots running our algorithm reaches the source with low lateral error while also tracing the horizontal and vertical plume shape.


  • Enhancing measurement quality through active sampling in mobile air quality monitoring sensor networks

    by Adrian Arfire, Ali Marjovi, Alcherio Martinoli

    In recent years, a growing number of research groups have targeted the development and deployment of networks using low-cost chemical sensors for monitoring air quality. Due to economical reasoning, most of these systems make use of some sort of mobility to increase spatial coverage. The effect of mobility on measurement quality has, however, been largely neglected. The long response time of the chemical sensors typically used for this type of application, in conjunction with platform mobility, leads to significant signal distortion. While this problem can be addressed through signal deconvolution techniques, their effectiveness is limited by the typical poor Signal-to-Noise Ratio (SNR) of the measured signal. In this paper, we study the possibility of enhancing the measurement quality of chemical sensors through the use of active sampling (or sniffing). We propose different sniffer designs, employing both fans and pumps as actuators. Using a rigorous experimental framework, inside a wind tunnel, we study the ability of active samplers to increase measurement SNR, and thus indirectly to improve sensor dynamic response. We obtain a significant and consistent improvement in SNR for one of our pump-based sniffer designs. Finally, we validate the robustness of this signal enhancement in real-world conditions through an outdoor car-based experiment.


  • 3-Point RANSAC for fast vision based rotation estimation using GPU technology

    by Danial Kamran, Mohammad T. Manzuri, Ali Marjovi, Mahdi Karimian

    In many sensor fusion algorithms, the vision based RANdom Sample Consensus (RANSAC) method is used for estimating motion parameters for autonomous robots. Usually such algorithms estimate both translation and rotation parameters together which makes them inefficient solutions for merely rotation estimation purposes. This paper presents a novel 3-point RANSAC algorithm for estimating only the rotation parameters between two camera frames which can be utilized as a high rate source of information for a camera-IMU sensor fusion system. The main advantage of our proposed approach is that it performs less computations and requires fewer iterations for achieving the best result. Despite many previous works that validate each hypothesis for all of data points and count the number of inliers for it, we use a voting based scheme for selecting the best rotation among all primary answers. This methodology is much more faster than the traditional inlier based approach and is more efficient for parallel implementation of RANSAC iterations. We also investigate parallel implementation of the proposed 3-point RANSAC using CUDA technology which leads to a great improvement in the processing time of estimation algorithm. We have utilized real datasets for evaluation of our algorithm and also compared it with the well-known 8-point algorithm in terms of accuracy and speed. The results show that the proposed approach improves the speed of estimation algorithm up to 150 times faster than the 8-point algorithm with similar accuracy.


  • Model-based rendezvous calibration of mobile sensor networks for monitoring air quality

    by Adrian Arfire, Ali Marjovi, Alcherio Martinoli

    Mobile Wireless Sensor Networks (WSNs) hold the potential to constitute a real game changer for our understanding of urban air pollution, through a significant augmentation of spatial resolution in measurement. However, temporal drift, cross-sensitivity and effects caused by varying environmental conditions (e.g., temperature) in low-cost chemical sensors (typically used in mobile WSNs) pose a tough challenge for reliable calibration. Based on state-of-the-art rendezvous calibration methods, we propose a novel model-based method for automatically estimating the baseline and gain characteristics of low-cost chemical sensors taking temporal drift and temperature dependencies of the sensors into account. The performance of our algorithm is evaluated using data gathered by our long-term mobile sensor network deployment, developed within the Nano-Tera.ch OpenSense II project1 in Lausanne, Switzerland. We show that, in a realistic context of sparse and irregular rendezvous events, our method consistently improves rendezvous calibration performance for single-hop online calibration.


  • Distributed graph-based convoy control for networked intelligent vehicles

    by Ali Marjovi, Milos Vasic, Joseph Lemaitre, Alcherio Martinoli

    This paper presents an approach for formation control of multi-lane vehicular convoys in highways. We extend a Laplacian graph-based, distributed control law such that networked intelligent vehicles can join or leave the formation dynamically without jeopardizing the ensemble's stability. Additionally, we integrate two essential control behaviors for lane-keeping and obstacle avoidance into the controller. To increase the performance of the convoy controller in terms of formation maintenance and fuel economy, the parameters of the controller are optimized in realistic scenarios using Particle Swarm Optimization (PSO), a powerful metaheuristic optimization method well-suited for large parameter spaces. The performances of the optimized controllers are evaluated in high-fidelity multi-vehicle simulations outlining the efficiency and robustness of the proposed strategy.


  • High Resolution Air Pollution Maps in Urban Environments Using Mobile Sensor Networks

    by Ali Marjovi, Adrian Arfire, Alcherio Martinoli

    We propose three modeling methods using a mobile sensor network to generate high spatio-temporal resolution air pollution maps for urban environments. In our deployment in Lausanne (Switzerland), dedicated sensing nodes are anchored to the public buses and measure multiple air quality parameters including the Lung Deposited Surface Area (LDSA), a state of the art metric for quantifying human exposure to ultra fine particles. In this paper, our focus is on generating LDSA maps. In particular, since the sensor network coverage is spatially and temporally dynamic, we leverage models to estimate the values for the locations and times where the data are not available. We first discretize the area topologically based on the street segments in the city and we then propose the following three prediction models: i) a log-linear regression model based on nine meteorological (e.g., Temperature and precipitations) and gaseous (e.g., NO 2 and CO) explanatory variables measured at two static stations in the city, ii) a novel network-based log-linear regression model that takes into account the LDSA values of the most correlated streets and also the nine explanatory variables mentioned above, iii) a novel Probabilistic Graphical Model (PGM) in which each street segment is considered as one node of the graph, and inference on conditional joint probability distributions of the nodes results in estimating the values in the nodes of interest. More than 44 millions of geo- and time-stamped LDSA measurements (i.e., More than 14 months of real data) are used in this paper to evaluate the proposed modeling approaches in various time resolutions (hourly, daily, weekly and monthly). The results show that the three approaches bring significant improvements in R2, RMSE and FAC metrics compared to a baseline K-Nearest Neighbor method.


  • Multi-robot odor distribution mapping in realistic time-variant conditions

    by Ali Marjovi, Lino Marques

    This paper tackles the problem of multi-robot odor distribution mapping through time series analysis. Considering the conditions of real world environments where the chemical concentration distribution is patchy, intermittent and time-variant, we propose a method to incorporate the temporal and spatial aspect of sensory data into the problem of odor distribution mapping. Despite the previous works in this field, the method gives more importance to the recent acquired measurements and also to the measurements which have been spatially closer to the place of the sensors (at the time of their acquisition). Real experiments were done in a realistic small-scale controlled environment (designed for systematic olfactory tests), considering up to five real robots and two different navigation algorithms. Experiments show that the generated odor maps are remarkably more accurate than the results of the conventional spatial interpolation method. Studying various spatio-temporal neighborhoods in the time series analysis concluded that a proper definition of the neighborhood (in time and space) provides accurate results in gas distribution mapping.