Learning from History for Behavior-Based Mobile Robots in Non-Stationary Conditions

Learning in the mobile robot domain is a very challenging task, especially in non-stationary conditions. The behavior-based approach has proven to be useful in making mobile robots work in real-world situations. Since the behaviors are responsible for managing the interactions between the robots and its environment, observing their use can be exploited to model these interactions. In our approach, the robot is initially given a set of behavior-producing modules to choose from, and the algorithm provides a memory-based approach to dynamically adapt the selection of these behaviors according to the history of their use. The approach is validated using a vision- and sonar-based Pioneer I robot in non-stationary conditions, in the context of a multi-robot foraging task. Results show the effectiveness of the approach in taking advantage of any regularities experienced in the world, leading to fas t and adaptable specialization for the learning robot.     

A robust extended H∞ filtering approach to multi-robot cooperative localization in dynamic indoor environments

Multi-robot cooperative localization serves as an essential task for a team of mobile robots to work within an unknown environment. Based on the real-time laser scanning data interaction, a robust approach is proposed to obtain optimal multi-robot relative observations using the Metric-based Iterative Closest Point (MbICP) algorithm, which makes it possible to utilize the surrounding environment information directly instead of placing a localization-mark on the robots. To meet the demand of dealing with the inherent non-linearities existing in the multi-robot kinematic models and the relative observations, a robust extended $H_{\infty }$ filtering (REHF) approach is developed for the multi-robot cooperative localization system, which could handle non-Gaussian process and measurement noises with respect to robot navigation in unknown dynamic scenes. Compared with the conventional multi-robot localization system using extended Kalman filtering (EKF) approach, the proposed filtering algorithm is capable of providing superior performance in a dynamic indoor environment with outlier disturbances. Both numerical experiments and experiments conducted for the Pioneer3-DX robots show that the proposed localization scheme is effective in improving both the accuracy and reliability of the performance within a complex environment.     

基于信息素的多机器人协作任务分配

针对多机器人系统未知环境下自主任务分配问题,提出了将虚拟吸引信息素和虚拟排斥信息素相结合的多机器人任务分配方法。在动态未知环境下,进行了多机器人协作搜集实验,实验结果表明所提方法既可以避免多个机器人集中在一个空间内造成冲突加剧的现象,又可以实现多机器人自主地进行任务分配目的。     

Reinforcement Learning in the Multi-Robot Domain

This paper describes a formulation of reinforcement learning that enables learning in noisy, dynamic environments such as in the complex concurrent multi-robot learning domain. The methodology involves minimizing the learning space through the use of behaviors and conditions, and dealing with the credit assignment problem through shaped reinforcement in the form of heterogeneous reinforcement functions and progress estimators. We experimentally validate the approach on a group of four mobile robots learning a foraging task.     

Robot Awareness in Cooperative Mobile Robot Learning

Most of the straight-forward learning approaches in cooperative robotics imply for each learning robot a state space growth exponential in the number of team members. To remedy the exponentially large state space, we propose to investigate a less demanding cooperation mechanism—i.e., various levels of awareness—instead of communication. We define awareness as the perception of other robots locations and actions. We recognize four different levels (or degrees) of awareness which imply different amounts of additional information and therefore have different impacts on the search space size ((0), (1), (N), o(N),¹ where N is the number of robots in the team). There are trivial arguments in favor of avoiding binding the increase of the search space size to the number of team members. We advocate that, by studying the maximum number of neighbor robots in the application context, it is possible to tune the parameters associated with a (1) increase of the search space size and allow good learning performance. We use the cooperative multi-robot observation of multiple moving targets (CMOMMT) application to illustrate our method. We verify that awareness allows cooperation, that cooperation shows better performance than a purely collective behavior and that learned cooperation shows better results than learned collective behavior.     

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.     

基于交换树的多机器人任务协调与负荷平衡方法

针对多机器人任务分工与协调过程中,未能有效解决的带任务偏序关系的负荷平衡问题,提出一种基于交换树的多机器人任务协调与负荷平衡方法。首先,通过有向赋权图（约束图）对带偏序关系约束的多机器人任务分工问题进行描述;其次,根据有向赋权图提出了初始任务分工策略,通过改进Dijkstra算法解决多机器人之间任务协调问题;最后,提出负荷平衡策略,通过交换树竞拍的方法解决机器人之间任务负荷不平衡问题。仿真结果表明,与一般Dijkstra方法相比,执行完任务负荷平衡策略之后,工作效率明显提高了12%,机器人之间的任务负荷差也减少了30%,验证了该方法的有效性。     

Learning social behavior

This paper discusses the challenges of learning to behave socially in the dynamic, noisy, situated and embodied mobile multi-robot domain. Using the methodology for synthesizing basis behaviors as a substrate for generating a large repertoire of higher-level group interactions, in this paper we describe how, given the substrate, greedy agents can learn social rules that benefit the group as a whole. We describe three sources of reinforcement and show their effectiveness in learning non-greedy social rules. We then demonstrate the learning approach on a group of four mobile robots learning to yield and share information in a foraging task.     

Distributed boundary coverage with a team of networked miniature robots using a robust market-based algorithm

We study distributed boundary coverage of known environments using a team of miniature robots. Distributed boundary coverage is an instance of the multi-robot task-allocation problem and has applications in inspection, cleaning, and painting among others. The proposed algorithm is robust to sensor and actuator noise, failure of individual robots, and communication loss. We use a market-based algorithm with known lower bounds on the performance to allocate the environmental objects of interest among the team of robots. The coverage time for systems subject to sensor and actuator noise is significantly shortended by on-line task re-allocation. The complexity and convergence properties of the algorithm are formally analyzed. The system performance is systematically analyzed at two different microscopic modeling levels, using agent-based, discrete-event and module-based, realistic simulators. Finally, results obtained in simulation are validated using a team of Alice miniature robots involved in a distributed inspection case study.     

Recognition of Affective Communicative Intent in Robot-Directed Speech

Human speech provides a natural and intuitive interface for both communicating with humanoid robots as well as for teaching them. In general, the acoustic pattern of speech contains three kinds of information: who the speaker is, what the speaker said, and how the speaker said it. This paper focuses on the question of recognizing affective communicative intent in robot-directed speech without looking into the linguistic content. We present an approach for recognizing four distinct prosodic patterns that communicate praise, prohibition, attention, and comfort to preverbal infants. These communicative intents are well matched to teaching a robot since praise, prohibition, and directing the robot's attention to relevant aspects of a task, could be used by a human instructor to intuitively facilitate the robot's learning process. We integrate this perceptual ability into our robot's emotion system, thereby allowing a human to directly manipulate the robot's affective state. This has a powerful organizing influence on the robot's behavior, and will ultimately be used to socially communicate affective reinforcement. Communicative efficacy has been tested with people very familiar with the robot as well as with naïve subjects.     

Multi-Robot Task Allocation in Uncertain Environments

Multiple cooperating robots hold the promise of improved performance and increased fault tolerance for large-scale problems such as planetary survey and habitat construction. Multi-robot coordination, however, is a complex problem. We cast this problem in the framework of multi-robot dynamic task allocation under uncertainty. We then describe an empirical study that sought general guidelines for task allocation strategies in multi-robot systems. We identify four distinct task allocation strategies, and demonstrate them in two versions of the multi-robot emergency handling task. We describe an experimental setup to compare results obtained from a simulated grid world to those obtained from physical mobile robot experiments. Data resulting from eight hours of experiments with multiple mobile robots are compared to the trend identified in simulation. The data from the simulations show that there is no single strategy that produces best performance in all cases, and that the best task allocation strategy changes as a function of the noise in the system. This result is significant, and shows the need for further investigation of task allocation strategies and their application to planetary exploration.     

Stable social foraging swarms in a noisy environment

Bacteria, bees, and birds often work together in groups to find food. A group of robots can be designed to coordinate their activities to search for and collect objects. Networked cooperative uninhabited autonomous vehicles are being developed for commercial and military applications. Suppose that we refer to all such groups of entities as "social foraging swarms". In order for such multiagent systems to succeed it is often critical that they can both maintain cohesive behaviors and appropriately respond to environmental stimuli (e.g., by optimizing the acquisition of nutrients in foraging for food). In this paper, we characterize swarm cohesiveness as a stability property and use a Lyapunov approach to develop conditions under which local agent actions will lead to cohesive foraging even in the presence of "noise" characterized by uncertainty on sensing other agent's position and velocity, and in sensing nutrients that each agent is foraging for. The results quantify earlier claims that social foraging is in a certain sense superior to individual foraging when noise is present, and provide clear connections between local agent-agent interactions and emergent group behavior. Moreover, the simulations show that very complicated but orderly group behaviors, reminiscent of those seen in biology, emerge in the presence of noise.     

Destination Driven Motion Planning via Obstacle Motion Prediction and Multi-State Path Repair

This paper presents a real-time navigating system named Destination Driven Navigator for a mobile robot operating in unstructured static and dynamic environments. We have designed a new obstacle representation method named Cross-Line Obstacle Representation and a new concept work space to reduce the robot's search space and the environment storage cost, an Adapted Regression Model to predict dynamic obstacles' motion, Multi-State Path Repair rules to quickly translate an infeasible path into feasible one, and the path-planning algorithm to generate a path. A high-level Destination Driven Navigator uses these methods, models and algorithms to guide a mobile robot traveling in various environments while avoiding static and dynamic obstacles. A group of experiments has been conducted. The results exhibit that the Destination Driven Navigator is a powerful and effective paradigm for robot motion planning and obstacle avoidance.     

大规模多移动机器人合作任务的分布自主协作系统

以大规模多移动机器人觅食任务为背景,探讨了在分布式协作体系结构下系统任务级的协作与行为级的协调问题．提出了一种动态任务分配机制,在缩短任务完成时间的基础上减少了系统通信量并解决了任务死锁问题．同时,设计了一种基于预测的冲突消解方法,使机器人能够对动态障碍物进行精确避障．最后,通过仿真实验验证了上述方法的有效性．     

Design of a simulation environment for laboratory management by robot organizations

This paper describes the basic concepts needed for a simulation environment capable of supporting the design of robot organizations for managing chemical, or similar, laboratories on the planned U.S. Space Station. The environment should facilitate a thorough study of the problems to be encountered in assigning the responsibility of managing a nonlife-critical, but mission valuable, process to an organized group of robots. In the first phase of the work, we seek to employ the simulation environment to develop robot cognitive systems and strategies for effective multi-robot management of chemical experiments. Later phases will explore human-robot interaction and development of robot autonomy.Supported by NASA-Ames Cooperative Agreement No. NCC 2-525, A Simulation Environment for Laboratory Management by Robot Organizations.     

Swarm-like Methodologies for Executing Tasks with Deadlines

Very few studies have been carried out to test multi-robot task allocation swarm algorithms in real time systems, where each task must be executed before a deadline. This paper presents a comparative study of several swarm-like algorithms and auction based methods for this kind of scenarios. Moreover, a new paradigm called pseudo-probabilistic swarm-like, is proposed, which merges characteristics of deterministic and probabilistic classical swarm approaches. Despite that this new paradigm can not be classified as swarming, it is closely related with swarm methods. Pseudo-probabilistic swarm-like algorithms can reduce the interference between robots and are particularly suitable for real time environments. This work presents two pseudo-probabilistic swarm-like algorithms: distance pseudo-probabilistic and robot pseudo-probabilistic. The experimental results show that the pseudo-probabilistic swarm-like methods significantly improve the number of finished tasks before a deadline, compared to classical swarm algorithms. Furthermore, a very simple but effective learning algorithm has been implemented to fit the parameters of these new methods. To verify the results a foraging task has been used under different configurations.     

Divided attention during adaptation to visual-motor rotation in an endoscopic surgery simulator

We investigated how cognitive demand affects the acquisition of adaptive hand–eye coordination in a low-fidelity endoscopic simulator. Participants performed a peg transfer task. In the pre-exposure and post-exposure phases participants moved objects between pegs with forceps while directly viewing the pegboard. In the exposure phase participants completed that task while indirectly viewing the pegboard through a camera and monitor with a 90° clockwise visual rotation. A control group completed the experiment as described whereas an experimental group concurrently performed a short-term memory task (digit rehearsal) during the exposure phase. Performance was significantly disrupted during early exposure-phase performance for both groups. The cognitive task caused an additional initial performance decrement for the experimental group, but their performance quickly converged on control-group performance. Both groups performance improved over trials. Competition for attentional resources imposed by memory demands can impair simulator performance, but performers can quickly learn to compensate for the increased attentional demand.     

Development of a reduced human user input task allocation method for multiple robots

Task allocation mechanisms are employed by multi-robot systems to efficiently distribute tasks between different robots. Currently, many task allocation methods rely on detailed expert knowledge to coordinate robots. However, it may not be feasible to dedicate an expert human user to a multi-robot system. Hence, a non-expert user may have to specify tasks to a team of robots in some situations. This paper presents a novel reduced human user input multi-robot task allocation technique that utilises Fuzzy Inference Systems (FISs). A two-stage primary and secondary task allocation process is employed to select a team of robots comprising manager and worker robots. A multi-robot mapping and exploration task is utilised as a model task to evaluate the task allocation process. Experiments show that primary task allocation is able to successfully identify and select manager robots. Similarly, secondary task allocation successfully identifies and selects worker robots. Both task allocation processes are also robust to parameter variation permitting intuitive selection of parameter values.     

A Direct Interpretation of Dynamic Images with Camera and Object Motions for Vision Guided Robot Control

A general scheme to represent the relation between dynamic images and camera and/or object motions is proposed for applications to visual control of robots. We consider the case where a moving camera observes moving objects in a static scene. The camera obtains images of the objects moving within the scene. Then, the possible combinations of the camera and the objects' poses and the obtained images are not arbitrary but constrained to each other. Here we represent this constraint as a lower dimensional hypersurface in the product space of the whole combination of their motion control parameters and image data. The visual control is interpreted as to find a path on this surface leading to their poses where a given goal image will be obtained. In this paper, we propose a visual control method to utilize tangential properties of this surface. First, we represent images with a composition of a small number of eigen images by using K-L (Karhunen-Loève) expansion. Then, we consider to reconstruct the eigen space (the eigen image space) to achieve efficient and straightforward controls. Such reconstruction of the space results in the constraint surface being mostly flat within the eigen space. By this method, visual control of robots in a complex configuration is achieved without image processing to extract and correspond image features in dynamic images. The method also does not need camera or hand-eye calibrations. Experimental results of visual servoing with the proposed method show the feasibility and applicability of our newly proposed approach to a simultaneous control of camera self-motion and object motions.     

FA–QABC–MRTA: a solution for solving the multi-robot task allocation problem

Intelligent Service Robotics - The problem of task allocation in a multi-robot system is the situation where we have a set of tasks and a number of robots; then each task is assigned to the...