Team Of Autonomous Robots Research Articles

Alignment in vision-based syntactic language games for teams of robots using stochastic regular grammars and reinforcement learning: The fully autonomous case and the human supervised case

This paper approaches the syntactic alignment of a robot team by means of dialogic language games and by applying online probabilistic reinforcement learning algorithms. The syntactic alignment is studied under two different configurations of the robot team: (a) when the team is formed exclusively by robots and (b) when a human is included in the team, in which case the human is endowed with a natural language to communicate with the other members of the team. For the two above mentioned cases, we are interested in the analysis of the convergence of the team to an optimal common language. The main contribution of the paper is the application of stochastic regular grammars, with learning capability, to generate the robots team’s language. Apart from the analysis of the convergence to a common language in the case of a fully autonomous robot team without human intervention we are also particularly interested in analyzing how the syntactic alignment of the robot team can be influenced or mediated by humans. The paper is organized as follows: first, we describe the syntactic language games, in particular the type of grammar and syntactic rules of the robots team’s language and the dynamic process of the language games which are based on dialogic communicative acts and a reinforcement learning policy that allows the robot team to converge to a common language. Afterwards, the experimental results are presented and discussed. The experimental work has been organized around the linguistic description of visual scenes of the blocks world type. The general conclusion of our experiments can be briefly stated in this way: “for the fully autonomous case (only robots) the final emergent grammar is arbitrary, while in the second case of including a human in the team the final emergent grammar is the one used by the human”.

Coordination strategies for multi-robot exploration and mapping

Situational awareness in rescue operations can be provided by teams of autonomous mobile robots. Human operators are required to teleoperate the current generation of mobile robots for such applications; however, teleoperation is increasingly difficult as the number of robots is expanded. As the number of robots is increased, each robot may also interfere with one another and eventually decrease mapping performance. As presented here, through careful consideration of robot team coordination and exploration strategy, large numbers of mobile robots can be allocated to accomplish the mapping task more quickly and accurately. We present both the coordination and exploration strategies and present results from experiments in simulation as well as with up to nine mobile platforms.

Coordination of control in robot teams using game-theoretic learning

This paper presents a distributed decision making approach to the problem of control effort allocation to robotic team members. The objective is for a team of autonomous robots to coordinate their actions in order to efficiently complete a task. A novel controller design methodology is proposed which allows the robot team to work together based on a gametheoretic learning algorithms using fictitious play and extended Kalman filters. In particular each robot of the team predicts the other robots' planned actions while making decision to maximise its own expected reward that is dependent on the reward for joint successful completion of the task. After theoretical analysis the performance of the proposed algorithm is tested on a scenario of collaboration between material handling and patrolling robots in a warehouse.

Distributed multi-robot patrol: A scalable and fault-tolerant framework

This paper addresses the Multi-Robot Patrolling Problem, where agents must coordinate their actions while continuously deciding which place to move next after clearing their locations. This problem is commonly addressed using centralized planners with global knowledge and/or calculating a priori routes for all robots before the beginning of the mission. In this work, two distributed techniques to solve the problem are proposed. These are motivated by the need to adapt to the changes in the system at any time and the possibility to add or remove patrolling agents (e.g., due to faults).The first technique presented is greedy and aims to maximize robot’s local gain. The second one is an extension of the former, which takes into account the distribution of agents in the space to reduce interference and foster scalability.The validation of the proposed solution is preliminarily conducted through realistic simulations as well as experiments with robot platforms in a small lab scenario. Subsequently, the work is verified in a large indoor real-world environment with a team of autonomous mobile robots with scalability and fault-tolerance assessment.

A PSO-Inspired Multi-Robot Map Exploration Algorithm Using Frontier-Based Strategy

Map exploration is a fundamental problem in mobile robots. This paper presents a distributed algorithm that coordinates a team of autonomous mobile robots to explore an unknown environment. The proposed strategy is based on frontiers which are the regions on the boundary between open and unexplored space. With this strategy, robots are guided to move constantly to the nearest frontier to reduce the size of unknown region. Based on the Particle Swarm Optimization (PSO) model incorporated in the algorithm, robots are navigated towards remote frontier after exploring the local area. The exploration completes when there is no frontier cell in the environment. The experiments implemented on both simulated and real robot scenarios show that the proposed algorithm is capable of completing the exploration task. Compared to the conventional method of randomly selecting frontier, the proposed algorithm proves its efficiency by the decreased 60% exploration time at least. Additional experimental results show the decreased coverage time when the number of robots increases, which further suggests the validity, efficiency and scalability.

Exploration and mapping with autonomous robot teams

The MAGIC 2010 robot competition showed how well multi-robot teams can work with human teams in urban search.

Robust Control of Mobility and Communications in Autonomous Robot Teams

A team of robots are deployed to accomplish a task while maintaining a viable ad-hoc network capable of supporting data transmissions necessary for task fulfillment. Solving this problem necessitates: 1) estimation of the wireless propagation environment to identify viable point-to-point communication links; 2) determination of end-to-end routes to support data traffic; and 3) motion control algorithms to navigate through spatial configurations that guarantee required minimum levels of service. Therefore, we present methods for: 1) estimation of point-to-point channels using pathloss and spatial Gaussian process models; 2) data routing so as to determine suitable end-to-end communication routes given estimates of point-to-point channel rates; and 3) motion planning to determine robot trajectories restricted to configurations that ensure survival of the communication network. Because of the inherent uncertainty of wireless channels, the model of links and routes is stochastic. The criteria for route selection is to maximize the probability of network survival-defined as the ability to support target communication rates-given achievable rates on local point-to-point links. Maximum survival probability routes for present and future positions are input into a mobility control module that determines robot trajectories restricted to configurations that ensure the probability of network survival stays above a minimum reliability level. Local trajectory planning is proposed for simple environments and global planning is proposed for complex surroundings. The three proposed components are integrated and tested in experiments run in two different environments. Experimental results show successful navigation with continuous end-to-end connectivity.

Asynchronous Control with ATR for Large Robot Teams

In this paper, we discuss and investigate the advantages of an asynchronous display, called “image queue”, tested for an urban search and rescue foraging task. The image queue approach mines video data to present the operator with a relevant and comprehensive view of the environment by selecting a small number of images that together cover large portions of the area searched. This asynchronous approach allows operators to search through a large amount of data gathered by autonomous robot teams, and allows comprehensive and scalable displays to obtain a network-centric perspective for unmanned ground vehicles (UGVs). In the reported experiment automatic target recognition (ATR) was used to augment utilities based on visual coverage in selecting imagery for presentation to the operator. In the cued condition a box was drawn in the region in which a possible target was detected. In the no-cue condition no box was drawn although the target detection probability continued to play a role in the selection of imagery. We found that operators using the image queue displays missed fewer victims and relied on teleoperation less often than those using streaming video. Image queue users in the no-cue condition did better in avoiding false alarms and reported lower workload than those in the cued condition.

A multi-robot exploration algorithm based on a static Bluetooth communication chain

In the first part of the present paper, a novel communication scheme of an autonomous robot team via Bluetooth radio is investigated. In the presented solution, an autonomous unit is equipped with two independent Bluetooth radios and so a relatively fast communication is possible in the team in a static (i.e. no ad hoc) networking topology. The performance of such a network was tested by implementing a linear graph topology by NXT robots. It was found that the reliability and the speed of such a communication scheme are satisfactory and give rise to applications in a robot team control task. In the second part of the paper, an area exploration method is presented based on the static linear communication network above. The method was tested by computer simulations for various obstacle configurations and densities. It was found that the proposed method performs better than the chosen reference methods in the case of zero or low obstacle density and when high (75% or 100%) exploration ratio is required. With a simple proof, we have shown that the proposed (fixed chain-like team) exploration method is optimal in the obstacle-free case under the constraint of the connectivity with the base station.

Fishing for Robots

This chapter reviews various research efforts to study animal group behaviors to boost bioengineering. The chapter also shows that understanding how a school of fish moves as one provides insights into controlling teams of autonomous robots. Unpowered robotic gliders can use simple rules to maintain their formation, even in choppy waters. Researchers have tried to use dynamical systems analysis to understand how the group makes the right decisions, how it uses feedback to correct poor decisions, and whether such rules would work with robots. Using analytic methods, teams looked at how the two informed groups of fish battled it out to lead the naive fish, which made up the vast majority of the school. Research has shown how sensitive group patterns can be to who is sensing whom. As soon as everyone starts sensing everyone else, the only stable solution is the whole group moving in a straight-line direction.

The Robockey Cup

Each fall, a group of intrepid students converge in a classroom on the third floor of the University of Pennsylvania's Towne Engineering Building for what they know will be one of the most challenging courses in their academic career. That first class begins with a discussion of where it will end. In particular, we talk about what they will accomplish in the final project, where they will design, fabricate, assemble, program, and debug small teams of autonomous hockey-playing robots, complete with wireless communications, infrared puck sensing, and enough onboard computational power to handle just about any task that can dream up. Most of the students look incredulous; after all, many of them have never built a circuit or written C code before.

Attractor dynamics approach to formation control: theory and application

In this paper we show how non-linear attractor dynamics can be used as a framework to control teams of autonomous mobile robots that should navigate according to a predefined geometric formation. The environment does not need to be known a priori and may change over time. Implicit to the control architecture are some important features such as establishing and moving the formation, split and join of formations (when necessary to avoid obstacles). Formations are defined by a formation matrix. By manipulating this formation matrix it is also possible to switch formations at run time. Examples of simulation results and implementations with real robots (teams of Khepera robots and medium size mobile robots), demonstrate formation switch, static and dynamic obstacle avoidance and split and join formations without the need for any explicit coordination scheme. Robustness against environmental perturbations is intrinsically achieved because the behaviour of each robot is generated as a time series of asymptotically stable states, which contribute to the asymptotic stability of the overall control system.

Towards cooperation of heterogeneous, autonomous robots: A case study of humanoid and wheeled robots

In this paper a case study of the cooperation of a strongly heterogeneous autonomous robot team, composed of a highly articulated humanoid robot and a wheeled robot with largely complementing and some redundant abilities is presented. By combining strongly heterogeneous robots the diversity of achievable tasks increases as the variety of sensing and motion abilities of the robot system is extended, compared to a usually considered team of homogeneous robots. A number of methodologies and technologies required in order to achieve the long-term goal of cooperation of heterogeneous autonomous robots are discussed, including modeling tasks and robot abilities, task assignment and redistribution, robot behavior modeling and programming, robot middleware and robot simulation. Example solutions and their application to the cooperation of autonomous wheeled and humanoid robots are presented in this case study. The scenario describes a tightly coupled cooperative task, where the humanoid robot and the wheeled robot track a moving ball, which is to be approached and kicked by the humanoid robot into a goal. The task can be fulfilled successfully by combining the abilities of both robots.

Coordinated Control of Space Robot Teams for the On-Orbit Construction of Large Flexible Space Structures

The construction of future space structures in Earth orbit such as solar power stations and space telescopes will require coordinated teams of autonomous space robots. These robot teams can excite undesirable vibrations in the structures while manipulating or assembling them. Controlling robot teams physically interacting with structural elements in space is challenging. The combined system dynamics are described by sets of nonlinear partial differential equations. Here, these dynamic equations are transformed into a set of linear time-varying ordinary differential equations. The control of the high-frequency robots is then decoupled from the control of the much lower frequency structures. This allows linear optimal control theory to be used to control the robots and minimize structural vibrations. Simulation and experimental studies shown here demonstrate the validity of the approach.

On the design of neuro-controllers for individual and social learning behaviour in autonomous robots: an evolutionary approach

In biology/psychology, the capability of natural organisms to learn from the observation/interaction with conspecifics is referred to as social learning. Roboticists have recently developed an interest in social learning, since it might represent an effective strategy to enhance the adaptivity of a team of autonomous robots. In this study, we show that a methodological approach based on artifcial neural networks shaped by evolutionary computation techniques can be successfully employed to synthesise the individual and social learning mechanisms for robots required to learn a desired action (i.e. phototaxis or antiphototaxis).

Performance Evaluation of a Multi-Robot Search & Retrieval System: Experiences with MinDART

Swarm techniques, where many simple robots are used instead of complex ones for performing a task, promise to reduce the cost of developing robot teams for many application domains. The challenge lies in selecting an appropriate control strategy for the individual units. This work explores the effect of control strategies of varying complexity and environmental factors on the performance of a team of robots at a foraging task when using physical robots (the Minnesota Distributed Autonomous Robotic Team). Specifically we study the effect of localization and of simple indirect communication techniques on task completion time using two sets of foraging experiments. We also present results for task performance with varying team sizes and target distributions. As indicated by the results, control strategies with increasing complexity reduce the variance in the performance, but do not always reduce the time to complete the task.

A Flexible Delegation-Type Interface Enhances System Performance in Human Supervision of Multiple Robots: Empirical Studies With RoboFlag

Three experiments and a computational analysis were conducted to investigate the effects of a delegation-type interface on human supervision of simulated multiple unmanned vehicles. Participants supervised up to eight robots using automated behaviors ("plays"), manual (waypoint) control, or both to capture the flag of an opponent with an equal number of robots, using a simple form of a delegation-type interface, Playbook. Experiment 1 showed that the delegation interface increased mission success rate and reduced mission completion time when the opponent "posture" was unpredictably offensive or defensive. Experiment 2 showed that performance was superior when operators could flexibly use both automated behaviors and manual control, although there was a small increase in subjective workload. Experiment 3 investigated additional dimensions of flexibility by comparing delegation interfaces to restricted interfaces. Eight interfaces were tested, varying in the level of abstraction at which robot behavior could be tasked and the level of aggregation (single or multiple robots) to which plays could be assigned. Performance was superior with flexible interfaces for four robots, but this benefit was eliminated when eight robots had to be supervised. Finally, a computational analysis using task-network modeling and Monte Carlo simulation gave results that closely paralleled the empirical data on changes in workload across interface type. The results provide initial empirical evidence for the efficacy of delegation-type interfaces in human supervision of a team of multiple autonomous robots.

STP: Skills, tactics, and plays for multi-robot control in adversarial environments

In an adversarial multi-robot task, such as playing robot soccer, decisions for team and single-robot behaviour must be made quickly to take advantage of short-term fortuitous events. When no such opportunities exist, the team must execute sequences of coordinated team action that increases the likelihood of future opportunities. A hierarchical architecture, called STP, has been developed to control an autonomous team of robots operating in an adversarial environment. STP consists of skills for executing the low-level actions that make up robot behaviour, tactics for determining what skills to execute, and plays for coordinating synchronized activity among team members. The STP architecture combines each of these components to achieve autonomous team control. Moreover, the STP hierarchy allows for fast team response in adversarial environments while carrying out actions with longer goals. This article presents the STP architecture for controlling an autonomous robot team in a dynamic adversarial task that allows for coordinated team activity towards long-term goals, with the ability to respond rapidly to dynamic events. Secondly, the subcomponent of skills and tactics is presented as a generalized single-robot control hierarchy for hierarchical problem decomposition with flexible control policy implementation and reuse. Thirdly, the play techniques contribute as a generalized method for encoding and synchronizing team behaviour, providing multiple competing team responses, and for supporting effective strategy adaptation against opponent teams. STP has been fully implemented on a robot platform and thoroughly tested against a variety of unknown opponent teams in a number of RoboCup robot soccer competitions. These competition results are presented as a mechanism to analyse the performance of STP in a real setting.

A multiagent cooperative mobile robotics approach for search and rescue missions

This paper presents a reusable framework for coordinating a team of mobile robots that can accomplish high level or tightly coupled missions, which could not be easily achieved using single robot solutions. To complete this task, we consider the behavior-based architecture model for the basic control layer. For coordinating the team of autonomous mobile robots, we use the agent-oriented software engineering paradigm. We apply the combination of a single and of multiagent techniques for evaluating a search-and-rescue mission. The experiments are using the Pioneer 2 DX robot and the Saphira simulator.

Exploiting Agent Oriented Software Engineering in Cooperative Robotics Search and Rescue

This paper reports our progress in applying multiagent systems analysis and design in the area of cooperative robotics. In this paper, we apply the Multiagent Systems Engineering (MaSE) methodology to design a team of autonomous, heterogeneous search and rescue robots. MaSE provides a top-down approach to building cooperative robotic systems instead of the bottom-up approach employed in most robotic implementations. We follow the MaSE steps and discuss various approaches and their impact on the final system design.