scholarly journals Multi-Robot Planning Under Uncertain Travel Times and Safety Constraints

2019 ◽  
Author(s):  
Masoumeh Mansouri ◽  
Bruno Lacerda ◽  
Nick Hawes ◽  
Federico Pecora
Keyword(s):  
Team Performance ◽  
Current Practice ◽  
Stochastic Petri Nets ◽  
Travel Times ◽  
Planning Approach ◽  
Robot Systems ◽  
Markov Decision ◽  
Safety Constraints ◽  
Multi Agent ◽  
Multi Robot

We present a novel modelling and planning approach for multi-robot systems under uncertain travel times. The approach uses generalised stochastic Petri nets (GSPNs) to model desired team behaviour, and allows to specify safety constraints and rewards. The GSPN is interpreted as a Markov decision process (MDP) for which we can generate policies that optimise the requirements. This representation is more compact than the equivalent multi-agent MDP, allowing us to scale better. Furthermore, it naturally allows for asynchronous execution of the generated policies across the robots, yielding smoother team behaviour. We also describe how the integration of the GSPN with a lower-level team controller allows for accurate expectations on team performance. We evaluate our approach on an industrial scenario, showing that it outperforms hand-crafted policies used in current practice.

scholarly journals Modelling and verification of reconfigurable multi-agent systems

2021 ◽  
Vol 35 (2) ◽  
Author(s):  
Yehia Abd Alrahman ◽  
Nir Piterman
Keyword(s):  
Model Checking ◽  
Communication Protocols ◽  
Local State ◽  
Multi Agent Systems ◽  
Agent Systems ◽  
Robot Systems ◽  
Message Exchange ◽  
Multi Agent ◽  
Exchange Data ◽  
Multi Robot

AbstractWe propose a formalism to model and reason about reconfigurable multi-agent systems. In our formalism, agents interact and communicate in different modes so that they can pursue joint tasks; agents may dynamically synchronize, exchange data, adapt their behaviour, and reconfigure their communication interfaces. Inspired by existing multi-robot systems, we represent a system as a set of agents (each with local state), executing independently and only influence each other by means of message exchange. Agents are able to sense their local states and partially their surroundings. We extend ltl to be able to reason explicitly about the intentions of agents in the interaction and their communication protocols. We also study the complexity of satisfiability and model-checking of this extension.

A Hybrid Decentralized Coordinated Approach for Multi-Robot Exploration Task

2018 ◽  
Vol 62 (9) ◽  
pp. 1284-1300 ◽  
Author(s):  
Khalil Mohamed ◽  
Ayman El Shenawy ◽  
Hany Harb
Keyword(s):  
Task Assignment ◽  
Target Cells ◽  
Local Data ◽  
Networked Robots ◽  
Exploration Process ◽  
Robot Systems ◽  
Markov Decision ◽  
Partially Observable ◽  
Assignment Approach ◽  
Multi Robot

Abstract Exploring the environment using multi-robot systems is a fundamental process that most automated applications depend on. This paper presents a hybrid decentralized task assignment approach based on Partially Observable Semi-Markov Decision Processes called HDec-POSMDPs, which are general models for multi-robot coordination and exploration problems in which robots can make their own decisions according to its local data with limited communication between the robot team. In this paper, a variety of multi-robot exploration algorithms and their comparison have been tackled. These algorithms, which have been taken into consideration, are dependent on different parameters. Collectively, there are five metrics maximize the total exploration percentage, minimize overall mission time, reduce the number of hops in the networked robots, reduce the energy consumed by each robot and minimize the number of turns in the path from the start pose cells to the target cells. Therefore, a team of identical mobile robots is used to perform coordination and exploration process in an unknown cell-based environment. The performance of the task depends on the strategy of coordination among the robots involved in the team. Therefore, the proposed approach is implemented, tested and evaluated in MRESim computer simulator, and its performance is compared with different coordinated exploration strategies for different environments and different team sizes. The experimental results demonstrate a good performance of the proposed approach compared to the four existing approaches.

scholarly journals Automated Verification of Social Laws for Continuous Time Multi-Robot Systems

2019 ◽  
Vol 33 ◽  
pp. 7683-7690 ◽  
Author(s):  
Ronen Nir ◽  
Erez Karpas
Keyword(s):  
Continuous Time ◽  
Automated Verification ◽  
Shared Environment ◽  
Multi Agent Systems ◽  
Agent Systems ◽  
Temporal Planning ◽  
Social Law ◽  
Robot Systems ◽  
Multi Agent ◽  
Multi Robot

Designing multi-agent systems, where several agents work in a shared environment, requires coordinating between the agents so they do not interfere with each other. One of the canonical approaches to coordinating agents is enacting a social law, which applies restrictions on agents’ available actions. A good social law prevents the agents from interfering with each other, while still allowing all of them to achieve their goals. Recent work took the first step towards reasoning about social laws using automated planning and showed how to verify if a given social law is robust, that is, allows all agents to achieve their goals regardless of what the other agents do. This work relied on a classical planning formalism, which assumed actions are instantaneous and some external scheduler chooses which agent acts next. However, this work is not directly applicable to multi-robot systems, because in the real world actions take time and the agents can act concurrently. In this paper, we show how the robustness of a social law in a continuous time setting can be verified through compilation to temporal planning. We demonstrate our work both theoretically and on real robots.

Optimal distributed interconnectivity of multi-robot systems by spatially-constrained clustering

2017 ◽  
Vol 25 (2) ◽  
pp. 96-113 ◽  
Author(s):  
Matin Macktoobian ◽  
Mahdi Aliyari Sh
Keyword(s):  
Clustering Algorithm ◽  
Task Assignment ◽  
Constrained Clustering ◽  
Loosely Coupled ◽  
Robot Systems ◽  
Multi Agent ◽  
Probabilistic Proof ◽  
Data Passing ◽  
Spatially Constrained Clustering ◽  
Multi Robot

A spatially-constrained clustering algorithm is presented in this paper. This algorithm is a distributed clustering approach to fine-tune the optimal distances between agents of the system to strengthen the data passing among them using a set of spatial constraints. In fact, this method will increase interconnectivity among agents and clusters, leading to improvement of the overall communicative functionality of the multi-robot system. This strategy will lead to the establishment of loosely-coupled connections among the clusters. These implicit interconnections will mobilize the clusters to receive and transmit information within the multi-agent system. In other words, this algorithm classifies each agent into the clusters with the lowest cost of local communication with its peers. This research demonstrates that the presented decentralized method will actually boost the communicative agility of the swarm by probabilistic proof of the acquired optimality. Hence, the common assumption regarding the full-knowledge of the agents’ primary locations has been fully relaxed compared to former methods. Consequently, the algorithm’s reliability and efficiency is confirmed. Furthermore, the method’s efficacy in passing information will improve the functionality of higher-level swarm operations, such as task assignment and swarm flocking. Analytical investigations and simulated accomplishments, corresponding to highly-populated swarms, prove the claimed efficiency and coherence.

scholarly journals A Constraint-based Mission Planning Approach for Reconfigurable Multi-Robot Systems

2018 ◽  
Vol 21 (62) ◽  
pp. 25
Author(s):  
Thomas M Roehr
Keyword(s):  
Degrees Of Freedom ◽  
Resource Constraints ◽  
Mission Planning ◽  
General Nature ◽  
Planning Problem ◽  
Modular Systems ◽  
Planning Approach ◽  
Robot Systems ◽  
Revised Definitions ◽  
Multi Robot

The application of reconfigurable multi-robot systems introduces additional degrees of freedom to design robotic missions compared to classical multi-robot systems. To allow for autonomous operation of such systems, planning approaches have to be investigated that cannot only cope with the combinatorial challenge arising from the increased flexibility of modular systems, but also exploit this flexibility to improve for example the safety of operation. While the problem originates from the domain of robotics it is of general nature and significantly intersects with operations research. This paper suggests a constraint-based mission planning approach, and presents a set of revised definitions for reconfigurable multi-robot systems including the representation of the planning problem using spatially and temporally qualified resource constraints. Planning is performed using a multi-stage approach and a combined use of knowledge-based reasoning, constraint-based programming and integer linear programming. The paper concludes with the illustration of the solution of a planned example mission.

scholarly journals Applications of DEC-MDPs in Multi-Robot Systems

Robotics ◽  
2013 ◽  
pp. 143-165
Author(s):  
Aurélie Beynier ◽  
Abdel-Illah Mouaddib
Keyword(s):  
Decentralized Control ◽  
Decision Processes ◽  
Decision Problems ◽  
Large Set ◽  
Complex Environments ◽  
Uncertain Environments ◽  
Robot Systems ◽  
Markov Decision ◽  
Partially Observable ◽  
Multi Robot

Optimizing the operation of cooperative multi-robot systems that can cooperatively act in large and complex environments has become an important focal area of research. This issue is motivated by many applications involving a set of cooperative robots that have to decide in a decentralized way how to execute a large set of tasks in partially observable and uncertain environments. Such decision problems are encountered while developing exploration rovers, teams of patrolling robots, rescue-robot colonies, mine-clearance robots, et cetera. In this chapter, we introduce problematics related to the decentralized control of multi-robot systems. We first describe some applicative domains and review the main characteristics of the decision problems the robots must deal with. Then, we review some existing approaches to solve problems of multiagent decentralized control in stochastic environments. We present the Decentralized Markov Decision Processes and discuss their applicability to real-world multi-robot applications. Then, we introduce OC-DEC-MDPs and 2V-DEC-MDPs which have been developed to increase the applicability of DEC-MDPs.

scholarly journals Engineering Challenges Ahead for Robot Teamwork in Dynamic Environments

2020 ◽  
Vol 10 (4) ◽  
pp. 1368
Author(s):  
Kurt Geihs
Keyword(s):  
Autonomous Robots ◽  
Conceptual Modeling ◽  
Dynamic Environments ◽  
Systems Perspective ◽  
Robot Systems ◽  
Multi Agent ◽  
Review State ◽  
Future Work ◽  
Theoretical Foundations ◽  
Multi Robot

The increasing number of robots around us creates a demand for connecting these robots in order to achieve goal-driven teamwork in heterogeneous multi-robot systems. In this paper, we focus on robot teamwork specifically in dynamic environments. While the conceptual modeling of multi-agent teamwork was studied extensively during the last two decades and commercial multi-agent applications were built based on the theoretical foundations, the steadily increasing use of autonomous robots in many application domains gave the topic new significance and shifted the focus more toward engineering concerns for multi-robot systems. From a distributed systems perspective, we discuss general engineering challenges that apply to robot teamwork in dynamic application domains and review state-of-the-art solution approaches for these challenges. This leads us to open research questions that need to be tackled in future work.

scholarly journals Fuzzy Reinforcement Learning and Curriculum Transfer Learning for Micromanagement in Multi-Robot Confrontation

Information ◽  
2019 ◽  
Vol 10 (11) ◽  
pp. 341 ◽  
Author(s):  
Hu ◽  
Xu
Keyword(s):  
Decision Making ◽  
Reinforcement Learning ◽  
Transfer Learning ◽  
Action Function ◽  
State Action ◽  
Markov Decision ◽  
Decision Making System ◽  
Multi Agent ◽  
Function Approximator ◽  
Multi Robot

Multi-Robot Confrontation on physics-based simulators is a complex and time-consuming task, but simulators are required to evaluate the performance of the advanced algorithms. Recently, a few advanced algorithms have been able to produce considerably complex levels in the context of the robot confrontation system when the agents are facing multiple opponents. Meanwhile, the current confrontation decision-making system suffers from difficulties in optimization and generalization. In this paper, a fuzzy reinforcement learning (RL) and the curriculum transfer learning are applied to the micromanagement for robot confrontation system. Firstly, an improved Qlearning in the semi-Markov decision-making process is designed to train the agent and an efficient RL model is defined to avoid the curse of dimensionality. Secondly, a multi-agent RL algorithm with parameter sharing is proposed to train the agents. We use a neural network with adaptive momentum acceleration as a function approximator to estimate the state-action function. Then, a method of fuzzy logic is used to regulate the learning rate of RL. Thirdly, a curriculum transfer learning method is used to extend the RL model to more difficult scenarios, which ensures the generalization of the decision-making system. The experimental results show that the proposed method is effective.

scholarly journals Decision-Making Under Uncertainty in Multi-Agent and Multi-Robot Systems: Planning and Learning

2018 ◽  
Author(s):  
Christopher Amato
Keyword(s):  
Decision Making Under Uncertainty ◽  
High Quality ◽  
Learning Methods ◽  
Robust Solutions ◽  
Systems Planning ◽  
Robot Systems ◽  
Multi Agent ◽  
Robot Tasks ◽  
Multi Agent Planning ◽  
Multi Robot

Multi-agent planning and learning methods are becoming increasingly important in today's interconnected world. Methods for real-world domains, such as robotics, must consider uncertainty and limited communication in order to generate high-quality, robust solutions. This paper discusses our work on developing principled models to represent these problems and planning and learning methods that can scale to realistic multi-agent and multi-robot tasks.

Sign in / Sign up

Export Citation Format

Share Document