Multi-robot Task Allocation Research Articles

A Multi-Robot Task Allocation Method Based on the Synergy of the K-Means++ Algorithm and the Particle Swarm Algorithm

Addressing challenges in the traditional K-means algorithm, such as the challenge of selecting initial clustering center points and the lack of a maximum limit on the number of clusters, and where the set of tasks in the clusters is not reasonably sorted after the task assignment, which makes the cooperative operation of multiple robots inefficient, this paper puts forward a multi-robot task assignment method based on the synergy of the K-means++ algorithm and the particle swarm optimization (PSO) algorithm. According to the processing capability of the robots, the K-means++ algorithm that limits the maximum number of clusters is used to cluster the target points of the task. The clustering results are assigned to the multi-robot system using the PSO algorithm based on the distances between the robots and the centers of the clusters, which divides the multi-robot task assignment problem into a multiple traveling salesmen problem. Then, the PSO algorithm is used to optimize the ordering of the task sets in each cluster for the multiple traveling salesmen problem. An experimental verification platform is established by building a simulation and physical experiment platform utilizing the Robot Operating System (ROS). The findings indicate that the proposed algorithm outperforms both the clustering-based market auction algorithm and the non-clustering particle swarm algorithm, enhancing the efficiency of collaborative operations among multiple robots.

A Systematic Literature Review on Multi-Robot Task Allocation

Muti-Robot system is gaining attention and is one of the critical areas of research when it comes to robotics. Coordination among multiple robots and how different tasks are allocated to different system agents are being studied. The objective of this Systematic Literature Review (SLR) is to provide insights on the recent advancement in Multi Robot Task Allocation(MRTA) problems emphasizing promising approaches for task allocation. In this study, we collected scientific papers from 5 different databases for MRTA. We outline the different approaches for task allocation algorithms, classifying them according to the methods, and emphasizing recent advances. In addition, we discuss the function of uncertainty in task allocation and typical coordination techniques utilized in task allocation to identify gaps in the literature and suggest the most promising ones.

A lexicographic optimization-based approach for efficient task allocation in industrial transportation multi-robot systems

In industrial transportation applications, multi-robot systems (MRS) are assigned to perform transportation tasks until their batteries are depleted, requiring them to move to battery charging stations. This temporary unavailability of the robots during charging decreases system productivity that measures the number of transportation tasks accomplished with the available robot energy. As a result, maximizing task completion becomes crucial, especially with prioritized tasks and increased workload. This can be achieved through an energy management strategy. In this context, the Lexicographic Optimization-based Multi-Robot Task Allocation (LO-MRTA) approach is proposed to maximize the reward in terms of system productivity with a limited energy consumption. The existing multi-robot energy management approaches consider the energy management during the tasks execution and neglect workload scaling issue with increasing tasks, whereas the LO-MRTA approach accounts for the energy consumption in the large-scale tasks allocation process. The main idea of the proposed approach is to consider the global state of the robots in the MRS system before carrying out the tasks execution, enhancing the task allocation decisions in terms of the energy management. The evaluation scenarios show the promising performance of the LO-MRTA approach in comparison with three existing baselines in terms of the system productivity, overall energy consumption and workload scaling effects.

Learning to Allocate Time-Bound and Dynamic Tasks to Multiple Robots Using Covariant Attention Neural Networks

Abstract In various applications of multi-robotics in disaster response, warehouse management, and manufacturing, tasks that are known a priori and tasks added during run time need to be assigned efficiently and without conflicts to robots in the team. This multi-robot task allocation (MRTA) process presents itself as a combinatorial optimization (CO) problem that is usually challenging to be solved in meaningful timescales using typical (mixed)integer (non)linear programming tools. Building on a growing body of work in using graph reinforcement learning to learn search heuristics for such complex CO problems, this paper presents a new graph neural network architecture called the covariant attention mechanism (CAM). CAM can not only generalize but also scale to larger problems than that encountered in training, and handle dynamic tasks. This architecture combines the concept of covariant compositional networks used here to embed the local structures in task graphs, with a context module that encodes the robots’ states. The encoded information is passed onto a decoder designed using multi-head attention mechanism. When applied to a class of MRTA problems with time deadlines, robot ferry range constraints, and multi-trip settings, CAM surpasses a state-of-the-art graph learning approach based on the attention mechanism, as well as a feasible random-walk baseline across various generalizability and scalability tests. Performance of CAM is also found to be at par with a high-performing non-learning baseline called BiG-MRTA, while noting up to a 70-fold improvement in decision-making efficiency over this baseline.

A decoupled solution to heterogeneous multi-formation planning and coordination for object transportation

Multi-robot formations have numerous applications, such as cooperative object transportation in intelligent warehouses. In this context, robots are tasked with delivering objects in formation while avoiding intra- and inter-formation collisions. This necessitates the development of solutions for multi-robot task allocation, formation generation, rigid formation route planning, and formation coordination. In this paper, we present a cooperative formation object transportation system for heterogeneous multi-robot systems which captures robot dynamics and avoids inter-formation collisions. Accounting for heterogeneous formations expands the applicability of the proposed robotic transport system. For formation generation, we propose an approach based on conflict-based search, which integrates high-level path planning with low-level trajectory optimisation. For heterogeneous formation planning, we present a two-stage iterative trajectory optimisation framework which adheres to the kinematic constraints of our heterogeneous multi-robot system while retaining formation rigidity. For multi-formation coordination, we use a loosely-coupled algorithm which can guarantee collision-free and deadlock-free formation navigation under minimal assumptions. We demonstrate the efficacy of our approach in simulation.

An adaptive genetic algorithm for the optimization of multi-mobile robot collaboration

The proposed approach utilizes the Robot Operating System (ROS) to simulate multi-robot collaboration across various scenarios, ensuring rigorous testing and validation of the algorithm. Our simulation environment encompasses complex tasks such as 3D digitalization, which demand precise coordination and efficient resource management among robots. The adaptive genetic algorithm (GA) continuously adjusts its parameters to improve performance, making it highly suitable for dynamic and unpredictable environments. Our results demonstrate that the adaptive GA significantly enhances the efficiency and effectiveness of Multi-Robot Task Allocation (MRTA) compared to traditional methods that lack optimization. By incorporating a cost function with various weighted factors, the task allocation process becomes both comprehensive and adaptable to specific mission requirements. This ensures that the robots can allocate tasks efficiently, even as conditions change. This study underscores the potential of adaptive genetic algorithms to advance the capabilities of mobile multi-robot systems, particularly in applications that require high levels of collaboration and precision. Our approach not only improves task allocation efficiency but also enhances the overall coordination and performance of the robotic system. The adaptability and robustness of the GA make it a promising solution for real-world applications, including search-and-rescue missions, environmental monitoring, and industrial automation. So, the potential of adaptive genetic algorithm presents a significant advancement in optimizing mobile multi-robot collaboration. Also, its ability to dynamically adjust to changing conditions and improve task allocation processes highlights its potential for a wide range of applications, marking a notable step forward in the field of collaborative robotics.

On a dynamic and decentralized energy-aware technique for multi-robot task allocation

In the real world, multi-robot systems need to deal with on-the-fly (runtime) arrivals of new sets of tasks. This entails repeated adjustments of their current task allocations to include the newer ones while also ensuring that the overall performance does not degrade. This paper proposes a decentralized and distributed dynamic task allocation algorithm to handle this issue in a multi-robot scenario. The proposed work provides a conflict-free allocation of a set of tasks constituting a job to robots and minimizes the total execution time. These jobs can comprise multiple independent and/or dependent tasks or a combination thereof, which are injected on-the-fly into a network of robots. The dependent tasks of a job are related by precedence constraints that specify the ordering or dependencies between pairs of tasks. The work also describes a decentralized adaptive energy threshold mechanism for determining whether or not a robot needs to visit a battery stockpile after the execution of a task. Conflicting task selections among the robots in this decentralized set-up are resolved using mobile agents during runtime. Apart from allocating tasks to the robots, these mobile agents exploit the benefits of centralized and decentralized systems and provide an advantage over auction-based task allocation algorithms. The proposed algorithm takes into consideration the energy requirements, both during the task allocation process and actual execution. The proposed algorithm also caters to strategies to deal with delays caused by obstacles and congestion during the actual execution of the tasks. Experiments conducted using Webots, an open-source robot simulator, and Tartarus, a multi-agent platform, authenticate the efficacy of the proposed algorithm compared to other prominent task allocation algorithms in terms of minimization of average waiting time, total task allocation time, total job allocation time, and total execution time of an experiment.

Online task allocation and scheduling in multi-manipulator system considering collision constraints and unknown tasks

Compared to a single robot, multi-robot systems (MRS) offer several advantages in complex multi-task scenarios. The overall efficiency of MRS relies heavily on an efficient task allocation and scheduling process. Multi-robot task allocation (MRTA) is often formulated as a multiple traveling salesman problem, which is NP-hard and typically addressed offline. This paper specifically addresses the online allocation problem in multi-manipulator systems within multi-task scenarios. The tasks are initially pre-allocated to alleviate the computational burden of online allocation. Subsequently, considering collision constraints, we search for the current feasible set of manipulators and employ greedy algorithms to achieve local optima as the online allocation result within this set. Our method can handle the online addition of new, unknown tasks to the task list. Moreover, we demonstrate the feasibility of our approach through simulations and on a realistic platform, where multiple manipulators are tasked with polishing the white body of automobile parts. The results demonstrate that our method is effective and efficient for online allocation and scheduling scenarios.

Swiss Round Selection Algorithm for Multi-Robot Task Scheduling

Efficient and stable control and task assignment optimization in electronic commerce logistics and warehousing systems involving multiple robots executing multiple tasks is highly challenging. Hence, this paper proposes a Swiss round selection algorithm for multi-robot task allocation to address the challenges mentioned. Firstly, based on the shipping process of electronic commerce logistics and warehousing systems, the tasks are divided into packaging and sorting stages, and a grid model for the electronic commerce warehousing system is established. Secondly, by increasing the probabilities of crossover and mutation in the population and adopting a full crossover and full mutation approach, the search scope of the population is expanded. Then, a Swiss round selection mechanism with burst probability is proposed, which ensures the smooth inheritance of high-quality individuals while improving the diversity of the population. Finally, 12 comparative experiments are designed with different numbers of robots and tasks. The experimental results demonstrate that the Swiss round selection algorithm outperforms the genetic algorithm in terms of maximum task completion time and convergence time to reach the optimal value. Thus, the effectiveness of the Swiss round selection algorithm in solving the multi-robot task allocation problem is verified.

Distributed and autonomous multi-robot for task allocation and collaboration using a greedy algorithm and robot operating system platform

Research investigations in the realm of micro-robotics often center around strategies addressing the multi-robot task allocation (MRTA) problem. Our contribution delves into the collaborative dynamics of micro-robots deployed in targeted hostile environments. Employing advanced algorithms, these robots play a crucial role in enhancing and streamlining operations within sensitive areas. We adopt a tailored GREEDY approach, strategically adjusting weight parameters in a multi-objective function that serves as a cost metric. The objective function, designed for optimization purposes, aggregates the cost functions of all agents involved. Our evaluation meticulously examines the MRTA efficiency for each micro-robot, considering dependencies on factors such as radio connectivity, available energy, and the absolute and relative availability of agents. The central focus is on validating the positive trend associated with an increasing number of agents constituting the cluster. Our methodology introduces a trio of micro-robots, unveiling a flexible strategy aimed at detecting individuals at risk in demanding environments. Each micro-robot within the cluster is equipped with logic that ensures compatibility and cooperation, enabling them to effectively execute assigned missions. The implementation of MRTA-based collaboration algorithms serves as an adaptive strategy, optimizing agents' mobility based on specific criteria related to the characteristics of the target site.<p class="JAMRISAbstract"> </p>

An indicator-based evolutionary algorithm with adaptive archive update cycle for multi-objective multi-robot task allocation

The multi-robot task allocation problem has garnered significant attention in research and development. This paper addresses the multi-robot task allocation problem by introducing a unified model that seamlessly transforms into four popular mathematical models through simple parameter adjustments. We propose an efficient indicator-based multi-objective evolutionary algorithm with a hybrid encoding scheme for task execution order and robot starting point information. The algorithm employs the hypervolume indicator for environmental selection to enhance convergence and the modified crowding distance for archive updates to promote diversity. Additionally, an adaptive archive update mechanism is designed for time efficiency. In experiments comparing our proposed algorithm with 8 state-of-the-art algorithms on 18 randomly generated instances of various sizes, along with 4 real-world problems from the TSPLIB benchmark, our algorithm consistently outperformed the comparison algorithms in five key indicators. These results underscore the effectiveness of our approach in addressing real-world multi-robot task allocation problems.

Scalable Multi-Robot Task Allocation Using Graph Deep Reinforcement Learning with Graph Normalization

Task allocation plays an important role in multi-robot systems regarding team efficiency. Conventional heuristic or meta-heuristic methods face difficulties in generating satisfactory solutions in a reasonable computational time, particularly for large-scale multi-robot task allocation problems. This paper proposes a novel graph deep-reinforcement-learning-based approach, which solves the problem through learning. The framework leverages the graph sample and aggregate concept as the encoder to extract the node features in the context of the graph, followed by a cross-attention decoder to output the probability that each task is allocated to each robot. A graph normalization technique is also proposed prior to the input, enabling an easy adaption to real-world applications, and a deterministic solution can be guaranteed. The most important advantage of this architecture is the scalability and quick feed-forward character; regardless of whether cases have a varying number of robots or tasks, single depots, multiple depots, or even mixed single and multiple depots, solutions can be output with little computational effort. The high efficiency and robustness of the proposed method are confirmed by extensive experiments in this paper, and various multi-robot task allocation scenarios demonstrate its advantage.

Heuristic reoptimization of time‐extended multi‐robot task allocation problems

AbstractProviding high quality solutions is crucial when solving NP‐hard time‐extended multi‐robot task allocation (MRTA) problems. Reoptimization, that is, the concept of making use of a known solution to an optimization problem instance when the solution to a similar problem instance is sought, is a promising and rather new research field in this application domain. However, so far no approximative time‐extended MRTA solution approaches exist for which guarantees on the resulting solution's quality can be given. We investigate the reoptimization problems of inserting as well as deleting a task to/from a time‐extended MRTA problem instance. For both problems, we can give performance guarantees in the form of an upper bound of 2 on the resulting approximation ratio for all heuristics fulfilling a mild assumption. We furthermore introduce specific solution heuristics and prove that smaller and tight upper bounds on the approximation ratio can be given for these heuristics if only temporal unconstrained tasks and homogeneous groups of robots are considered. A conclusory evaluation of the reoptimization heuristic demonstrates a near‐to‐optimal performance in application.

An effective collaboration evolutionary algorithm for multi-robot task allocation and scheduling in a smart farm

The rapid development of intelligent and unmanned technologies has created new opportunities and challenges for smart farms. Agricultural production is increasingly incorporating intelligent robots for various farming activities. This paper investigates the task allocation and scheduling for multiple agricultural robots operating in a smart farm. For addressing this problem, a collaborative discrete bee colony algorithm (CDABC) is introduced to provide a viable solution, aiming to optimize the system efficiency in smart farms. To enhance the global search ability, several solution neighborhoods are designed based on a single robot and multi robots, and a problem-oriented dynamic neighborhood strategy list is given for the collaborative employment bees stage. Additionally, the neighborhoods based on the critical robot are constructed to enhance the local exploitation capability. A novel collaborative following bee strategy is also integrated to help individuals trapped in the local optimum move to more ideal areas in the scout bee stage. Finally, comprehensive design experiments are carried out to determine optimal parameter configurations and demonstrate that CDABC has the better performance than the state-of-the-art algorithms.

Multi-Robot Task Allocation Using Multimodal Multi-Objective Evolutionary Algorithm Based on Deep Reinforcement Learning

Multi-Robot Task Allocation Using Multimodal Multi-Objective Evolutionary Algorithm Based on Deep Reinforcement Learning

Efficient and Robust Multirobot Navigation and Task Allocation Using Soft Actor Critic

In this research, we present a novel solution to the problem of multi-robot task allocation (MRTA) by utilizing a variant of the state-of-art Deep Reinforcement Learning algorithm, Soft Actor-Critic (SAC) within Multirobot Navigation Systems(MRS). Our approach addresses the existing research gaps in MRTA for MRS, which have received limited attention and have proven challenging to solve using conventional methods. Through extensive simulation evaluations, we demonstrate that our system outperforms current state-of-the-art methods in terms of performance metrics. These findings highlight the effectiveness and superiority of our proposed approach in overcoming the inherent challenges of large-scale MRS. Additionally, we contribute to the field by proposing improvements to the Task Allocation Index (TAI) metric, enabling a more comprehensive evaluation of MRTA performance.

CoLoSSI: Multi-Robot Task Allocation in Spatially-Distributed and Communication Restricted Environments

CoLoSSI: Multi-Robot Task Allocation in Spatially-Distributed and Communication Restricted Environments

Energy Efficient Multi-Robot Task Allocation Constrained by Time Window and Precedence

Energy Efficient Multi-Robot Task Allocation Constrained by Time Window and Precedence

A Cooperative Ant Colony System for Multiobjective Multirobot Task Allocation With Precedence Constraints

A Cooperative Ant Colony System for Multiobjective Multirobot Task Allocation With Precedence Constraints

An efficient two-stage evolutionary algorithm for multi-robot task allocation in nuclear accident rescue scenario

With the growing maturity of multi-robot system technology, its applications have expanded across various domains. This paper addresses the critical issue of task allocation in nuclear accident rescue scenario, which plays a pivotal role in the success of such operations. The problem is formulated as a multi-objective optimization problem, taking into account three key indicators: execution time, radiation accumulation, and waiting cost. To effectively tackle this problem, an two-stage evolutionary algorithm is proposed. Firstly, a solution encoding method and a crossover mutation method is devised tailored to the problem’s characteristics. Secondly, a two-stage search strategy is designed. In the first stage, a fixed population size and shift-based density estimation method are used to quickly converge the solution set to the Pareto front. The latter stage uses an infinite size population to find as many Pareto solutions as possible. Finally, a local search strategy is introduced to improve the quality of solution set. In the experimental section, our proposed method is compared with five state-of-the-art algorithms on nine instances of varying scales. Across five evaluation metrics, the proposed algorithm demonstrates competitive performance on all instances. These results underscore the efficacy and competitiveness of our approach in tackling the task allocation problem in multi-robot systems within nuclear accident rescue.