Suranga Hettiarachchi and William M. Spears
The purpose of this paper is to demonstrate a novel use of a generalized Lennard‐Jones (LJ) force law in Physicomimetics, combined with offline evolutionary learning, for the…
Abstract
Purpose
The purpose of this paper is to demonstrate a novel use of a generalized Lennard‐Jones (LJ) force law in Physicomimetics, combined with offline evolutionary learning, for the control of swarms of robots moving through obstacle fields towards a goal. The paper then extends the paradigm to demonstrate the utility of a real‐time online adaptive approach named distributed agent evolution with dynamic adaptation to local unexpected scenarios (DAEDALUS).
Design/methodology/approach
To achieve the best performance, the parameters of the force law used in the Physicomimetics approach are optimized, using an evolutionary algorithm (EA) (offline learning). A weighted fitness function is utilized consisting of three components: a penalty for collisions, lack of swarm cohesion, and robots not reaching the goal. Each robot of the swarm is then given a slightly mutated copy of the optimized force law rule set found with offline learning and the robots are introduced to a more difficult environment. The online learning framework (DAEDALUS) is used for swarm adaptation in this more difficult environment.
Findings
The novel use of the generalized LJ force law combined with an EA surpasses the prior state‐of‐the‐art in the control of swarms of robots moving through obstacle fields. In addition, the DAEDALUS framework allows the swarms of robots to not only learn and share behavioral rules in changing environments (in real time), but also to learn the proper amount of behavioral exploration that is appropriate.
Research limitations/implications
There are significant issues that arise with respect to “wall following methods” and “local minimum trap” problems. “Local minimum trap” problems have been observed in this paper, but this issue is not addressed in detail. The intention is to explore other approaches to develop more robust adaptive algorithms for online learning. It is believed that the learning of the proper amount of behavioral exploration can be accelerated.
Practical implications
In order to provide meaningful comparisons, this paper provides a more complete set of metrics than prior papers in this area. The paper examines the number of collisions between robots and obstacles, the distribution in time of the number of robots that reach the goal, and the connectivity of the formation as it moves.
Originality/value
This paper addresses the difficult task of moving a large number of robots in formation through a large number of obstacles. The important real‐world constraint of “obstructed perception” is modeled. The obstacle density is approximately three times the norm in the literature. The paper shows how concepts from population genetics can be used with swarms of agents to provide fast online adaptive learning in these challenging environments. In addition, this paper also presents a more complete set of metrics of performance.
Details
Keywords
Diana F. Spears, David R. Thayer and Dimitri V. Zarzhitsky
In light of the current international concerns with security and terrorism, interest is increasing on the topic of using robot swarms to locate the source of chemical hazards. The…
Abstract
Purpose
In light of the current international concerns with security and terrorism, interest is increasing on the topic of using robot swarms to locate the source of chemical hazards. The purpose of this paper is to place this task, called chemical plume tracing (CPT), in the context of fluid dynamics.
Design/methodology/approach
This paper provides a foundation for CPT based on the physics of fluid dynamics. The theoretical approach is founded upon source localization using the divergence theorem of vector calculus, and the fundamental underlying notion of the divergence of the chemical mass flux. A CPT algorithm called fluxotaxis is presented that follows the gradient of this mass flux to locate a chemical source emitter.
Findings
Theoretical results are presented confirming that fluxotaxis will guide a robot swarm toward chemical sources, and away from misleading chemical sinks. Complementary empirical results demonstrate that in simulation, a swarm of fluxotaxis‐guided mobile robots rapidly converges on a source emitter despite obstacles, realistic vehicle constraints, and flow regimes ranging from laminar to turbulent. Fluxotaxis outperforms the two leading competitors, and the theoretical results are confirmed experimentally. Furthermore, initial experiments on real robots show promise for CPT in relatively uncontrolled indoor environments.
Practical implications
A physics‐based approach is shown to be a viable alternative to existing mainly biomimetic approaches to CPT. It has the advantage of being analyzable using standard physics analysis methods.
Originality/value
The fluxotaxis algorithm for CPT is shown to be “correct” in the sense that it is guaranteed to point toward a true source emitter and not be fooled by fluid sinks. It is experimentally (in simulation), and in one case also theoretically, shown to be superior to its leading competitors at finding a source emitter in a wide variety of challenging realistic environments.
Details
Keywords
Lukas König, Sanaz Mostaghim and Hartmut Schmeck
In evolutionary robotics (ER), robotic control systems are subject to a developmental process inspired by natural evolution. The purpose of this paper is to utilize a control…
Abstract
Purpose
In evolutionary robotics (ER), robotic control systems are subject to a developmental process inspired by natural evolution. The purpose of this paper is to utilize a control system representation based on finite state machines (FSMs) to build a decentralized online‐evolutionary framework for swarms of mobile robots.
Design/methodology/approach
A new recombination operator for multi‐parental generation of offspring is presented and a known mutation operator is extended to harden parts of genotypes involved in good behavior, thus narrowing down the dimensions of the search space. A storage called memory genome for archiving the best genomes of every robot introduces a decentralized elitist strategy. These operators are studied in a factorial set of experiments by evolving two different benchmark behaviors such as collision avoidance and gate passing on a simulated swarm of robots. A comparison with a related approach is provided.
Findings
The framework is capable of robustly evolving the benchmark behaviors. The memory genome and the number of parents for reproduction highly influence the quality of the results; the recombination operator leads to an improvement in certain parameter combinations only.
Research limitations/implications
Future studies should focus on further improving mutation and recombination. Generality statements should be made by studying more behaviors and there is a need for experimental studies with real robots.
Practical implications
The design of decentralized ER frameworks is improved.
Originality/value
The framework is robust and has the advantage that the resulting controllers are easier to analyze than in approaches based on artificial neural networks. The findings suggest improvements in the general design of decentralized ER frameworks.
Details
Keywords
The purpose of this paper is to examine and illustrate the development of a methodology for generating swarms using lossless flocking.
Abstract
Purpose
The purpose of this paper is to examine and illustrate the development of a methodology for generating swarms using lossless flocking.
Design/methodology/approach
A general methodology for swarm design is described. Examples of this approach in the literature are examined. A general requirement for lossless flocking is developed. The requirement is used in developing two swarm behaviors.
Findings
It is possible to apply the approach to the lossless flocking and to use the swarm condition to develop two swarm behaviors which satisfy this condition in many situations.
Research limitations/implications
This paper illustrates the general swarm engineering method and demonstrates how it can be properly applied.
Originality/value
The swarm engineering method is used to develop the “quark” model, a new physicomimetic model.
Details
Keywords
Hui Wang, Michael Jenkin and Patrick Dymond
A simultaneous solution to the localization and mapping problem of a graph‐like environment by a swarm of robots requires solutions to task coordination and map merging. The…
Abstract
Purpose
A simultaneous solution to the localization and mapping problem of a graph‐like environment by a swarm of robots requires solutions to task coordination and map merging. The purpose of this paper is to examine the performance of two different map‐merging strategies.
Design/methodology/approach
Building a representation of the environment is a key problem in robotics where the problem is known as simultaneous localization and mapping (SLAM). When large groups of robots operate within the environment, the SLAM problem becomes complicated by issues related to coordination of the elements of the swarm and integration of the environmental representations obtained by individual swarm elements. This paper considers these issues within the formalism of a group of simulated robots operating within a graph‐like environment. Starting at a common node, the swarm partitions the unknown edges of the known graph and explores the graph for a pre‐arranged period. The swarm elements then meet at a particular time and location to integrate their partial world models. This process is repeated until the entire world has been mapped. A correctness proof of the algorithm is presented, and different coordination strategies are compared via simulation.
Findings
The paper demonstrates that a swarm of identical robots, each equipped with its own marker, and capable of simple sensing and action abilities, can explore and map an unknown graph‐like environment. Moreover, experimental results show that exploration with multiple robots can provide an improvement in exploration effort over a single robot and that this improvement does not scale linearly with the size of the swarm.
Research limitations/implications
The paper represents efforts toward exploration and mapping in a graph‐like world with robot swarms. The paper suggests several extensions and variations including the development of adaptive partitioning and rendezvous schedule strategies to further improve both overall swarm efficiency and individual robot utilization during exploration.
Originality/value
The novelty associated with this paper is the formal extension of the single robot graph‐like exploration of Dudek et al. to robot swarms. The paper here examines fundamental limits to multiple robot SLAM and does this within a topological framework. Results obtained within this topological formalism can be readily transferred to the more traditional metric representation.
Details
Keywords
Takashi Kuremoto, Masanao Obayashi and Kunikazu Kobayashi
The purpose of this paper is to present a neuro‐fuzzy system with a reinforcement learning algorithm (RL) for adaptive swarm behaviors acquisition. The basic idea is that each…
Abstract
Purpose
The purpose of this paper is to present a neuro‐fuzzy system with a reinforcement learning algorithm (RL) for adaptive swarm behaviors acquisition. The basic idea is that each individual (agent) has the same internal model and the same learning procedure, and the adaptive behaviors are acquired only by the reward or punishment from the environment. The formation of the swarm is also designed by RL, e.g. temporal difference (TD)‐error learning algorithm, and it may bring out a faster exploration procedure comparing with the case of individual learning.
Design/methodology/approach
The internal model of each individual composes a part of input states classification by a fuzzy net, and a part of optimal behavior learning network which adopting a kind of RL methodology named actor‐critic method. The membership functions and fuzzy rules in the fuzzy net are adaptively formed online by the change of environment states observed in the trials of agent's behaviors. The weights of connections between the fuzzy net and the action‐value functions of actor which provides a stochastic policy of action selection, and critic which provides an evaluation to state transmission, are modified by TD‐error.
Findings
Simulation experiments of the proposed system with several goal‐directed navigation problems are accomplished and the results show that swarms are successfully formed and optimized routes are found by swarm learning faster than the case of individual learning.
Originality/value
Two techniques, i.e. fuzzy identification system and RL algorithm, are fused into an internal model of the individuals for swarm formation and adaptive behavior acquisition. The proposed model may be applied to multi‐agent systems, swarm robotics, metaheuristic optimization, and so on.
Details
Keywords
Blesson Varghese and Gerard McKee
The purpose of this paper is to address a classic problem – pattern formation identified by researchers in the area of swarm robotic systems – and is also motivated by the need…
Abstract
Purpose
The purpose of this paper is to address a classic problem – pattern formation identified by researchers in the area of swarm robotic systems – and is also motivated by the need for mathematical foundations in swarm systems.
Design/methodology/approach
The work is separated out as inspirations, applications, definitions, challenges and classifications of pattern formation in swarm systems based on recent literature. Further, the work proposes a mathematical model for swarm pattern formation and transformation.
Findings
A swarm pattern formation model based on mathematical foundations and macroscopic primitives is proposed. A formal definition for swarm pattern transformation and four special cases of transformation are introduced. Two general methods for transforming patterns are investigated and a comparison of the two methods is presented. The validity of the proposed models, and the feasibility of the methods investigated are confirmed on the Traer Physics and Processing environment.
Originality/value
This paper helps in understanding the limitations of existing research in pattern formation and the lack of mathematical foundations for swarm systems. The mathematical model and transformation methods introduce two key concepts, namely macroscopic primitives and a mathematical model. The exercise of implementing the proposed models on physics simulator is novel.
Details
Keywords
Giulio Zecca, Paul Couderc, Michel Banâtre and Roberto Beraldi
The purpose of this paper is to show how a swarm of robots can cooperate to achieve a common task, in a totally distributed and autonomous way, by exploiting powerful clues…
Abstract
Purpose
The purpose of this paper is to show how a swarm of robots can cooperate to achieve a common task, in a totally distributed and autonomous way, by exploiting powerful clues contained in some devices that are distributed in the environment. This system exploits a coordination mechanism that is twofold, using radio frequency identification (RFID) tags for spatial coordination, and wireless robot‐to‐robot communication for the temporal and semantic synchronization.
Design/methodology/approach
Progress in the pervasive computing field has led to the distribution of knowledge and computational power in the environment, rather than condensing it in a single, powerful entity. This vision of ambient intelligence is supported by the interchange of information between physically sparse agents cooperating to achieve a common goal. An emerging method for this kind of collaboration considers the agents as insects in a swarm, having the possibility of communicating directly or indirectly with each other. The goal is to fulfill a common task, showing that a collaborative behavior can be useful in the real world. The paper focuses on a technique for the coordination of swarm‐robots with low capabilities, driven by instructions learned from RFID tags used as distributed pervasive memories. These robots exploit ubiquitous computing to regroup in a synchronization area, make a formation in space, coordinate with team‐mates in the same zone, and finally complete a cooperative task. The algorithm is validated through a simulation environment, showing its applicability and performance, before the real implementation on Roomba‐like robots.
Findings
The goal of the research is to prove the feasibility of such a novel approach. It is observed that a swarm of robots can achieve a good degree of autonomous cooperation without a central infrastructure or global network, carrying out a goal in a fair time.
Originality/value
The value is given by the benefits of splitting the synchronization semantics into two levels: space, by exploiting RFID landmarks; and time, by exploiting wireless short‐range communication. RFID tags are used to distribute computational power and actively interact with the surrounding areas, allowing to learn and modify the state of the environment. Robot‐to‐robot communication, instead, is used for providing timing and semantic information. In the proposal, this augmented environment is used to allow a good level of coordination among robots, both in time and space, with the aim of building a cooperative system.