Ali Marjovi

Multi-robot exploration and fire searching

Exploration of an unknown environment is a fundamental concern in mobile robotics. This paper presents an approach for cooperative multi-robot exploration, fire searching and mapping in an unknown environment. The proposed approach aims to minimize the overall exploration time, making it possible to localize fire sources in an efficient way. In order to achieve this goal, the robots should cooperate in an effective way, so they can individually and simultaneously explore different areas of the environment while they identify fire sources. The proposed approach employs a decentralized frontier based exploration method which evaluates the cost-gain ratio to navigate to target way-points. The target way-points are obtained by an A* search variant algorithm. The potential field method is used to control the robots motion while avoiding obstacles. When a robot detects a fire, it estimates the flames position by triangulation. The communication between the robots is done in a decentralized control way where they share the necessary data to generate the map of the environment and to perform cooperative actions in a behavioral decision making way. This paper presents simulation and experimental results of the proposed exploration and fire search method and concludes with a discussion of the obtained results and future improvements.

Multi-robot olfactory search in structured environments

This paper presents a cooperative distributed approach for searching odor sources in unknown structured environments with multiple mobile robots. While searching and exploring the environment, the robots independently generate on-line local topological maps and by sharing them with each other they construct a global map. The proposed method is a decentralized frontier based algorithm enhanced by a cost/utility evaluation function that considers the odor concentration and airflow at each frontier. Therefore, frontiers with higher probability of containing an odor source will be searched and explored first. The method also improves path planning of the robots for the exploration process by presenting a priority policy. Since there is no global positioning system and each robot has its own coordinate reference system for its localization, this paper uses topological graph matching techniques for map merging. The proposed method was tested in both simulation and real world environments with different number of robots and different scenarios. The search time, exploration time, complexity of the environment and number of double-visited map nodes were investigated in the tests. The experimental results validate the functionality of the method in different configurations.

An olfactory-based robot swarm navigation method

This paper presents a novel robot swarming navigation algorithm in order to find the odor sources in an unknown environment, based on the ability of each swarm member to sense the odor. Each robot in the swarm has a cooperative localization system which uses wireless network as a mean of measuring the distance from the other robots. In this method, at least three robots act as stationary measurement beacons while the other robots of the swarm navigate in the environment towards the odor source. In the next step, the roles of the robots will be switched and some other robots will act as beacons. The experimental tests report a good result in finding the odor source and also the accuracy of localization system1.

3DCLIMBER: A climbing robot for inspection of 3D human made structures

3DCLIMBER is a running project in the University of Coimbra for developing a climbing robot with the capability of manipulating over 3D human-made structures. This paper mainly discuss the conceptual and detailed design and development of a Pole Climbing robot with minimum degrees of freedom which can climb over 3D structures with bends and branches followed by Preliminary test results of the robot performance. Electronics architecture and control algorithms are briefly described. The paper finishes with discussion of the current results and identifies some future works.

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

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.

Optimal spatial formation of swarm robotic gas sensors in odor plume finding

Finding the best spatial formation of stationary gas sensors in detection of odor clues is the first step of searching for olfactory targets in a given space using a swarm of robots. Considering no movement for a network of gas sensors, this paper formulates the problem of odor plume detection and analytically finds the optimal spatial configuration of the sensors for plume detection, given a set of assumptions. This solution was analyzed and verified by simulations and finally experimentally validated in a reduced scale realistic environment using a set of Roomba-based mobile robots.

Optimal Swarm Formation for Odor Plume Finding

This paper presents an analytical approach to the problem of odor plume finding by a network of swarm robotic gas sensors, and finds an optimal configuration for them, given a set of assumptions. Considering cross-wind movement for the swarm, we found that the best spatial formation of robots in finding odor plumes is diagonal line configuration with equal distance between each pair of neighboring robots. We show that the distance between neighboring pairs in the line topology depends mainly on the wind speed and the environmental conditions, whereas, the number of robots and the swarms crosswind movement distance do not show significant impact on optimal configurations. These solutions were analyzed and verified by simulations and experimentally validated in a reduced scale realistic environment using a set of mobile robots.

Distributed graph-based convoy control for networked intelligent vehicles

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 ensembles 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.

Multi-Robot Topological Exploration Using Olfactory Cues

This paper presents a distributed multi-robot system to search for odor sources inside unknown environments. The robots cooperatively explore the whole environment and generate its topological map. The exploration method is a decentralized frontier based algorithm that is enhanced by considering odor concentration at each frontier inside its cost/gain function. The robots independently generate local topological maps and by transferring them to each other, they are able to integrate these maps and generate a whole global map. The proposed method was tested and validated in real reduced scale scenarios.

Swarm robotic plume tracking for intermittent and time-variant odor dispersion

This paper presents a method for odor plume tracking by a swarm of robots in realistic conditions. In real world environments, the chemical concentration within an odor plume is patchy, intermittent and time-variant. This study shows that swarm robots can cooperatively track the odor plume towards its source by establishing a cohesive spatial sensor network to deal with the turbulences and patchy nature of odor plumes. The robots move together and maintain a distance margin between themselves in order to keep the cohesion of the constructed sensor network while the odor concentration and air-flow speed are considered in the equations of navigation of the robots in the network to more efficiently track the plume. The method is evaluated in simulation against various number of robots, the emission rate of the odor source, the number of obstacles in the environment and the size of the testing environment. The emergent behavior of the swarm proves the functionality, robustness and scalability of the system in different conditions.