Search results

Heterogeneous teams consisting of unmanned ground vehicles and unmanned aerial vehicles are being used for different types of missions such as surveillance, tracking and exploration. Exploration missions with heterogeneous robot teams (HeRTs) should acquire a common map for understanding the surroundings better. The purpose of this paper is to provide a unique approach with cooperative use of agents that provides a well-detailed observation over the environment where challenging details and complex structures are involved. Also, this method is suitable for real-time applications and autonomous path planning for exploration.

Lidar odometry and mapping and various similarity metrics such as Shannon entropy, Kullback–Leibler divergence, Jeffrey divergence, K divergence, Topsoe divergence, Jensen–Shannon divergence and Jensen divergence are used to construct a common height map of the environment. Furthermore, the authors presented the layering method that provides more accuracy and a better understanding of the common map.

In summary, with the experiments, the authors observed features located beneath the trees or the roofed top areas and above them without any need for global positioning system signal. Additionally, a more effective common map that enables planning trajectories for both vehicles is obtained with the determined similarity metric and the layering method.

In this study, the authors present a unique solution that implements various entropy-based similarity metrics with the aim of constructing common maps of the environment with HeRTs. To create common maps, Shannon entropy–based similarity metrics can be used, as it is the only one that holds the chain rule of conditional probability precisely. Seven distinct similarity metrics are compared, and the most effective one is chosen for getting a more comprehensive and valid common map. Moreover, different from all the studies in literature, the layering method is used to compute the similarities of each local map obtained by a HeRT. This method also provides the accuracy of the merged common map, as robots’ sight of view prevents the same observations of the environment in features such as a roofed area or trees. This novel approach can also be used in global positioning system-denied and closed environments. The results are verified with experiments.

The purpose of this paper is to present a novel approach to coordination of multi‐agent teams, and in particular multi‐robot teams. The new approach is based on models of organisational sociology, namely the concept of social networks. The social relationships used in the model that is presented in this paper are trust and kinship relationships, but modified for use in heterogeneous multi‐robot teams.

The coordination of a robot team is achieved through task allocation. The proposed task allocation mechanism was tested in the multi‐robot team task allocation simulation.

The social networks‐based task allocation algorithm has performed according to expectations and the obtained results are very promising. Some intriguing similarities with higher mammalian societies were observed and they are discussed in this paper. The social networks‐based approach also exhibited the ability to learn and store information using social networks.

The research focused on simulated environments and further research is envisaged in the physical environments to confirm the applicability of the presented approach.

In this paper, the proposed coordination was applied to simulated multi‐robot teams. It is important to note that the proposed coordination model is not robot specific, but can also be applied to almost any multi‐agent system without major modifications.

The paper emphasizes applicability of considering multi‐robot teams as socially embodied agents. It also presents a novel and efficient approach to task allocation.

The historical data usually consist of overlapping reports, and these reports may contain inconsistent data, which may return incorrect results of a query search. Moreover, users who issue the query may not learn of this inconsistency even after a data cleaning process (e.g. schema matching or data screening). The inconsistency can exist in different types of data, such as temporal or spatial data. Therefore, this paper aims to introduce an information fusion method that can detect data inconsistency in the early stages of data fusion.

This paper introduces an information fusion method for multi-robot operations, for which fusion is conducted continuously. When the environment is explored by multiple robots, the robot logs can provide more information about the number and coordination of targets or victims. The information fusion method proposed in this paper generates an underdetermined linear system of overlapping spatial reports and estimates the case values. Then, the least squares method is used for the underdetermined linear system. By using these two methods, the conflicts between reports can be detected and the values of the intervals at specific times or locations can be estimated.

The proposed information fusion method was tested for inconsistency detection and target projection of spatial fusion in sensor networks. The proposed approach examined the values of sensor data from simulation that robots perform search tasks. This system can be expanded to data warehouses with heterogeneous data sources to achieve completeness, robustness and conciseness.

Little research has been devoted to the linear systems for information fusion of tasks of mobile robots. The proposed information fusion method minimizes the cost of time and comparison for data fusion and also minimizes the probability of errors from incorrect results.

This paper aims to present a concise review on the variant state-of-the-art dynamic task allocation strategies. It presents a thorough discussion about the existing dynamic task allocation strategies mainly with respect to the problem application, constraints, objective functions and uncertainty handling methods.

This paper briefs the introduction of multi-robot dynamic task allocation problem and discloses the challenges that exist in real-world dynamic task allocation problems. Numerous task allocation strategies are discussed in this paper, and it establishes the characteristics features between them in a qualitative manner. This paper also exhibits the existing research gaps and conducive future research directions in dynamic task allocation for multiple mobile robot systems.

This paper concerns the objective functions, robustness, task allocation time, completion time, and task reallocation feature for performance analysis of different task allocation strategies. It prescribes suitable real-world applications for variant task allocation strategies and identifies the challenges to be resolved in multi-robot task allocation strategies.

This paper provides a comprehensive review of dynamic task allocation strategies and incites the salient research directions to the researchers in multi-robot dynamic task allocation problems. This paper aims to summarize the latest approaches in the application of exploration problems.

Multi-robot coalition formation (MRCF) refers to the formation of robot coalitions against complex tasks requiring multiple robots for execution. Situations, where the robots have to participate in multiple coalitions over time due to a large number of tasks, are called Time-extended MRCF. While being NP-hard, time-extended MRCF also holds the possibility of resource deadlocks due to any cyclic hold-and-wait conditions among the coalitions. Existing schemes compromise on solution quality to form workable, deadlock-free coalitions through instantaneous or incremental allocations.

This paper presents an evolutionary algorithm (EA)-based task allocation framework for improved, deadlock-free solutions against time-extended MRCF. The framework simultaneously allocates multiple tasks, allowing the robots to participate in multiple coalitions within their schedule. A directed acyclic graph–based representation of robot plans is used for deadlock detection and avoidance.

Allowing the robots to participate in multiple coalitions within their schedule, significantly improves the allocation quality. The improved allocation quality of the EA is validated against two auction schemes inspired by the literature.

To the best of the author's knowledge, this is the first framework which simultaneously considers multiple MR tasks for deadlock-free allocation while allowing the robots to participate in multiple coalitions within their plans.

This paper aims to propose a parallel automated assembly line system to produce multiple products in a semi-continuous system.

The control system developed in this research consists of a manufacturing system for two-level hierarchical dynamic decisions of autonomous/automated/automatic-guided vehicles (AGVs) dispatching/next station selection and machining schedules and a station control scheme for operational control of machines and components. In this proposed problem, the assignment of multiple AGVs to different assembly lines and the semi-continuous stations is a critical objective. AGVs and station scheduling decisions are made at the assembly line level. On the other hand, component and machining resource scheduling are made at the station level.

The proposed scheduler first decomposes the dynamic scheduling problems into a static AGV and machine assignment during each short-term rolling window. It optimizes weighted completion time of tasks for each short-term window by formulating the task and resource assignment problem as a minimum cost flow problem during each short-term scheduling window. A comprehensive decision making process and heuristics are developed for efficient implementation. A simulation study is worked out for validation.

Several assembly lines are configured to produce multiple products in which the technologies of machines are shared among the assembly lines when required. The sequence of stations is pre-specified in each assembly line and the components of a product are kept in machine magazine. The transportation between the stations in an assembly line (intra assembly line) and among stations in different assembly lines (inter assembly line) are performed using AGVs.

Target tracking systems are generally computationally intensive and require expensive and power‐hungry visual sensors. On the other hand, the existing target tracking control approaches fail to track the target swiftly and accurately when the mobile robot moves in the diversified manoeuvre modes. The purpose of this paper is to propose a novel target tracking control method with a low cost embedded vision system to achieve high accuracy and speediness of target tracking control, regardless of the type of manoeuvre modes.

The pan/tilt angle differences are transformed from the tracking error between the image centre and the coordinates of the target centroid returned by the CMUcam3; the corresponding pan/tilt angle variation rates are calculated based on the manoeuvre control. All of them are fed to the controller. Then the controller generates appropriate control signals to fit the changing speed of target centroid and compensate for the tracking error. The experiments are designed in a way that the CMUcam3 keeps the target centre coincident with the image centre when the mobile robot moves in the diversified manoeuvre modes.

In spite of the type of manoeuvre modes, the controller responds to the tracking error instantly and actuates the pan/tilt with suitable position and speed commands, and the target centroid remains in the bounding box during the entire movement.

The proposed target tracking control takes the correlation between the robot manoeuvre modes and the target tracking control into account, and particularly suits for the target tracking tasks in planetary exploration, surveillance and military applications.

The purpose of this paper is to propose a local orientation and navigation framework based on visual features that provide location recognition, context augmentation, and viewer localization information to a blind or low‐vision user.

The authors consider three types of “visual noun” features: signage, visual‐text, and visual‐icons that are proposed as a low‐cost method for augmenting environments. These are used in combination with an RGB‐D sensor and a simplified SLAM algorithm to develop a framework for navigation assistance suitable for the blind and low‐vision users.

It was found that signage detection cannot only help a blind user to find a location, but can also be used to give accurate orientation and location information to guide the user navigating a complex environment. The combination of visual nouns for orientation and RGB‐D sensing for traversable path finding can be one of the cost‐effective solutions for navigation assistance for blind and low‐vision users.

This is the first step for a new approach in self‐localization and local navigation of a blind user using both signs and 3D data. The approach is meant to be cost‐effective but it only works in man‐made scenes where a lot of signs exist or can be placed and are relatively permanent in their appearances and locations.

Based on 2012 World Health Organization, 285 million people are visually impaired, of which 39 million are blind. This project will have a direct impact on this community.

Signage detection has been widely studied for assisting visually impaired people in finding locations, but this paper provides the first attempt to use visual nouns as visual features to accurately locate and orient a blind user. The combination of visual nouns with 3D data from an RGB‐D sensor is also new.

Different machines are already present in the human environment, easing human beings' daily life. In the future, this tendency will be accentuated by integration of numerous robots (e.g. wheeled robots, legged robots, humanoid robots, network sensors, etc.) in the human environment. A wide range of applications, such as those dealing with warehouse management, industrial assembling, military applications, daily‐life tasks, can benefit from multi‐robot systems. The purpose of this paper is to propose an intelligent system for industrial robotics in the logistic field, based on collaboration between heterogeneous robots.

The proposed infrastructure for this multi‐robot system is composed of a robots' network including one humanoid robot, wheeled robots, cameras, and remote computer. All devices can communicate between them by using wireless network. The goal of the humanoid robot is to lead the wheeled robots according to the environment and wheeled robots are used to carry a load. The camera allows providing complementary information about the environment; and thanks to machine learning, this control strategy allows complex tasks to be perormed for these logistic applications.

This concept is implemented on real robots within the frame of a demonstrator including the above‐mentioned kind of robots. The preliminary results, obtained during experimentations, prove the feasibility of the presented strategy for real applications.

The main originalities of this work are, on the one hand, the use of an heterogeneous multi‐robots system for logistic tasks, and on the other hand, the proposed machine learning allows a collaboration task between heterogeneous robots in an autonomous manner.