Bio-insect and artificial robot interaction using cooperative reinforcement learning

In this paper, we propose fuzzy logic-based cooperative reinforcement learning for sharing knowledge among autonomous robots. The ultimate goal of this paper is to entice bio-insects towards desired goal areas using artificial robots without any human aid. To achieve this goal, we found an interaction mechanism using a specific odor source and performed simulations and experiments [1]. For efficient learning without human aid, we employ cooperative reinforcement learning in multi-agent domain. Additionally, we design a fuzzy logic-based expertise measurement system to enhance the learning ability. This structure enables the artificial robots to share knowledge while evaluating and measuring the performance of each robot. Through numerous experiments, the performance of the proposed learning algorithms is evaluated.     

The barriers to widespread use of intelligent robots and manufacturing machines

The theme of this presentation is that technical barriers exist that have prevented widespread industrial use of intelligent robots and manufacturing machines. These barriers must be successfully addressed for major progress to occur in these fields. Each barrier is identified and discussed, current research projects addressing each barrier in that area are presented, and opinions expressed as to how that barrier will be removed. This paper presents some current industry/university cooperative research results that reinforce the author's view; nine selected projects will be highlighted. Areas of special interest are presented including intelligent robots, intelligent machines, adaptive control structures, the potential of neural nets, the influence of cognitive processes, and the potential for autonomous machine operation in the factory of the future. Some comments on the mechanisms needed for successful industry/university cooperative research are offered.     

CDCSMA-CD communication method for cooperative robot systems

Robot cooperation means 'work-accomplishment action with collaboration of multiple robots by applying shared information, transmitted from a robot to others in a system'. The definition implies that efficiency of a cooperative robot system depends directly upon two main factors, one is communication among the robots and the other is movement of the robots. Robots with appropriate cooperation are expected to work efficiently. The authors propose here an efficient communication method for a cooperative robots system, Code Division Carrier Sensing Multiple Accesses with Collision Detection (CDCSMA-CD). CDCSMA-CD, differing from communication methods in the past, is specifically designed for a cooperative robot system so it can be applied appropriately for both point-to-point and broadcast communication. Within this paper, the principle and hardware structure of the proposed CDCSMA-CD are described. The efficiency of CDCSMA-CD, compared with other communication methods, is then evaluated and discussed.     

多移动机器人协同搬运技术综述

多移动机器人协同搬运系统是多移动机器人系统的典型应用，在一些特殊场合中具有较强的应用潜力。对此，本文综述了多移动机器人协同搬运的相关技术，总结了国内外的发展状况。针对不同的搬运对象，分析比较了抓取、推拉、锁定3种搬运方案，重点分析了不同搬运方案下的多移动机器人协同搬运策略算法原理以及各自的优缺点；概述了多移动机器人搬运系统中涉及的周边技术，主要包括多移动机器人任务分配、环境感知定位、轨迹规划3个方面；最后对多移动机器人协同搬运技术的研究方向进行了展望。     

Cooperative manipulation of a floating object by some space robots with joint velocity controllers: application of a tracking control method using the transpose of the generalized Jacobian matrix

We have studied the cooperative manipulation of floating object by several space robots. For these cooperative motions, we have reported that a tracking control method using the transpose of the generalized Jacobian matrix (GJM) can be utilized for robots with joint torque controllers. For cooperative motions by some robots with joint velocity controllers, we proposed a tracking control method using the transpose of the GJM. Simulation results show the effectiveness of the proposed control method.     

Human,machines, and the interpretation of formal systems

There are plenty of intelligent machines in our world today: digital computers and autonomous robots. At the heart of each of these machines there are automatic formal systems (programs running on a digital computer). Now, if the interpretation of a formal system does not belong to the formal system itself, if the interpretation has to be added, it is worth asking: in the case of these intelligent machines that are massively interspersed in our social interactions, where does the interpretation come from? In this paper, we analyse what we call the invisibility of interpretation. Dealing with various types of formal systems (computers, robots, formalist approaches to Economics), the human source of the interpretation of these systems is sometimes concealed by a formalist restriction. To show how the formalist restriction produces the invisibility of interpretation allows us to underline our responsibility, as human agents, for all this interpretative work—and its importance for us as human beings.     

Bilateral teleoperation of a group of mobile robots for cooperative tasks

A visual and force feedback-based teleoperation scheme is proposed for cooperative tasks. The bilateral teleoperation system includes a haptic device, an overhead camera and a group of wheeled robots. The commands of formation and average velocities of the multiple robots are generated by the operator through the haptic device. The state of the multiple robots and the working environment is sent to the human operator. The received information contains the feedback force through the haptic device and visual information returned by a depth camera. The feedback force based on the difference between the desired and actual average velocities is presented. The wave variable method is employed in the bilateral teleoperation of multiple mobile robots with time delays. The effectiveness of the bilateral teleoperation system is demonstrated by experiments. The robots in the slave side are able to follow the commands from the master side to interact with the environments, including moving in different formations and pushing a box. The results show that the scheme enables the operator to manipulate a group of robots to complete cooperative tasks freely.     

一类非完整轮式机器人的编队一致性

讨论了一类具有非完整约束和有向通信拓扑的轮式机器人的编队一致性问题.基于Zipf分布设计了带有耦合权重的编队一致性协议,减少了机器人间的信息交换,降低机器人编队在复杂的通讯环境中对所有机器人状态信息的依赖程度.将多机器人系统的编队一致性问题转化为误差系统的稳定性分析问题,给出了机器人形成编队的一致性条件,并利用图论和李亚诺夫稳定性理论证明在该条件下可实现系统编队收敛到期望的队形和虚拟领导者的运动规律上的目标.仿真实验和实物实验验证了所设计编队一致性协议的有效性.     

Behaviors for physical cooperation between robots for mobility improvement

A team of small, low-cost robots instead of a single large, complex robot is useful in operations such as search and rescue, urban exploration etc. However, performance of such a team is limited due to restricted mobility of the team members. We propose solutions based on physical cooperation among mobile robots to improve the overall mobility. Our focus is on the development of the low level system components. Recognizing that small robots need to overcome discrete obstacles, we develop specific analytical maneuvers to negotiate each obstacle where a maneuver is built from a sequence of fundamental cooperative behaviors. In this paper we present cooperative behaviors that are achieved by interactions among robots via un-actuated links thus avoiding the need for additional actuation. We analyze the cooperative lift behavior and demonstrate that useful maneuvers such a gap crossing can be built using this behavior. We prove that the requirements on ground friction and wheel torques set fundamental limits for physical cooperation. Using the design guidelines based on static analysis we have developed simple and low cost hardware to illustrate cooperative gap crossing with two robots. We have developed a complete dynamic model of two-robot cooperation which leads to control design. A novel connecting link design is proposed that can change the system configuration with no additional actuators. A decentralized control architecture is designed for the two-robot system, where each robot controls its own state with no information about the state of the other robot thus avoiding the need of continuous communication between the two robots. Simulation and hardware results demonstrate a successful implementation with the gap crossing example. We have analytically proved that robot dynamics can be used to reduce the friction requirements and have demonstrated, with simulations, the implementation of this idea for the cooperative lifting behavior.

A dynamic safety system based on sensor fusion

Machines in industry, including industrial robots, have in many cases dramatically reduced the man-made work and improved the work environment. New machines introduce, however, new risk factors. Traditionally machines are safeguarded by means that more or less rigidly separates the machines from the personnel. This works well in many traditional areas, i.e., where industrial robots are involved. There is however a risk that the safety system limits the valuable flexibility of the robot, which can be considered as a quality that tends to become even more valuable in the progress of programming possibilities and sensor technology. This article shows an example how a safety system can be designed to achieve increased flexibility in co-operation between human and production safety strategy. The proposed safety system is totally based on sensor information that monitors the working area, calculate the safety level and improve the system dynamically, e.g., reduce the robot capability in conjunction to the system safety level. The safety system gain information from the sensors and calculates a risk level which controls the robot speed, i.e., the speed is reduced to achieve a sufficiently low risk level. The sensor data is combined with fuzzy-based sensor fusion and fuzzy rules. The safety system is based on sensor information, hence it automatically adjusts to changes in the guarded area as long as the functionality of the sensors is maintained. Finally, we present a system implementation in an industrial robot application.     

Multi-degree cyclic scheduling of two robots in a no-wait flowshop

This paper addresses multi-degree cyclic scheduling of two robots in a no-wait flowshop, where exactly r(r > 1) identical parts with constant processing times enter and leave the production line during each cycle, and transportation of the parts between machines is performed by two robots on parallel tracks. The objective is to minimize the cycle time. The problem is transformed into enumeration of pairs of overlapping moves that cannot be performed by the same robot. This enumeration is accomplished by enumerating intervals for some linear functions of decision variables. The algorithm developed is polynomial in the number of machines for a fixed r, but exponential if r is arbitrary. Computational results with benchmark instances are reported. Note to Practitioners-This paper was motivated by the problem of cyclic scheduling of a no-wait production line, where a part must be processed without any interruption either on or between machines due to characteristics of the processing technology itself or the absences of storage capacity between operations of a part. Multi-degree schedules, in which multiple parts enter and leave the line during a cycle, usually have larger throughput rate than simple ones. This paper proposes an algorithm for multi-degree cyclic scheduling of a no-wait flowshop with two robots. Computational results show that the throughput rate can be really improved by using multi-degree schedules with two robots. However, we have not addressed the decision of the optimal value of the degree of the cycle. Furthermore, since we consider that the two robots travel along parallel tracks, the collision-avoidance constraints have been relaxed in the algorithm. In future research, we will address the two problems and generalize the algorithm to multi-robot cases.     

A methodology for design and analysis of cooperative behaviors with mobile robots

New methodologies are needed for modeling of physically cooperating mobile robots to be able to systematically design and analyze such systems. In this context, we present a method called the ‘P-robot Method’ under which we introduce entities called the p-robots at the environmental contact points and treat the linked mobile robots as a multiple degree-of-freedom object, comprising an articulated open kinematic chain, which is manipulated by the p-robots. The method is suitable to address three critical aspects of physical cooperation: a) analysis of environmental contacts, b) utilization of redundancy, and c) exploitation of system dynamics. Dynamics of the open chain are computed independent of the constraints, thus allowing the same set of equations to be used as the constraint conditions change, and simplifying the addition of multiple robots to the chain. The decoupling achieved through constraining the p-robots facilitates the analysis of kinematic as well as force constraints. We introduce the idea of a ‘tipping cone’, similar to a standard friction cone, to test whether forces on the robots cause undesired tipping. We have employed the P-robot Method for the static as well as dynamic analysis for a cooperative behavior involving two robots. The method is generalizable to analyze cooperative behaviors with any number of robots. We demonstrate that redundant actuation achieved by an adding a third robot to cooperation can help in satisfying the contact constraints. The P-robot Method can be useful to analyze other interesting multi-body robotic systems as well.     

VARIABLE PATROL PLANNING OF MULTI-ROBOT SYSTEMS BY A COOPERATIVE AUCTION SYSTEM

A cooperative auction system (CAS) is proposed to solve the large-scale multi-robot patrol planning problem. Each robot picks its own patrol points via the cooperative auction system and the system continuously re-auctions, based on the team work performance. The proposed method not only works in static environments but also considers variable path planning when the number of mobile robots increases or decreases during patrol. From the results of the simulation, the proposed approach demonstrates decreased time complexity, a lower routing path cost, improved balance of workload among robots, and the potential to scale to a large number of robots and is adaptive to environmental perturbations when the number of robots changes during patrol.     

Bearing-only Cooperative Localization

In cooperative localization a group of robots exchange relative position measurements from their exteroceptive sensors and their motion information from interoceptive sensors to collectively estimate their position and heading. For the localization errors to be bounded, it is required that the system be observable, independent of the estimation technique being used. In this paper, we develop a test-bed of three ground robots, which are equipped with wheel encoders and omnidirectional cameras, to implement the bearing-only cooperative localization. The simulation and experimental results validate the observability conditions, derived in Sharma et al. (IEEE Trans Robot 28:2, 2011), for the complete observability of the bearing-only cooperative localization problem.     

从集群智能角度分析协同驾驶:综述和展望

协同驾驶是集群智能技术的典型应用之一.和集群机器人相比,协同驾驶既有集群智能技术的共性问题,也有特性问题.对协同驾驶与集群机器人对比研究,有助于更好理解协同驾驶问题的内在难点,也有助于推动集群智能技术的发展,完善复杂系统科学.本文从集群智能研究的角度出发,对协同驾驶进行反思综述.本文首先介绍协同驾驶的研究背景和意义,然后从集群智能的角度进一步分析协同驾驶和集群机器人的区别,接着介绍协同驾驶的关键技术,并着重强调协同规划在协同驾驶中的特殊性与重要性,最后分析了世界各国协同驾驶发展现状,并针对现阶段我国协同驾驶发展的难点提出一些建议,同时对协同驾驶的未来进行展望.     

Motion Planning for Two Robots of an Object Handling System Considering Fast Transition Between Stable States

Fast transition from a stable initial state to a stable handling state is important when multiple mobile robots grasp and transport a bulky and heavy object. In this paper, we present motion planning for two robots of an irregularly shaped object handling system considering fast transition between stable states. A cooperative object handling system consisting of a gripper robot equipped with a gripper and a lifter robot equipped with a lifter was first designed. Then, a strategy to realize fast transition between stable states by using the object handling system designed was proposed. While grasping and lifting an object off the ground, a gripper robot grasps and lifts up the object from one side to provide enough space for a lifter robot to lift the object off the ground cooperatively. Fast transition between stable states is formulated as a constraint optimization problem. The goal is to realize transition from a stable initial state to a stable handling state in a minimal amount of time. Experiments involving two robots and everyday objects were conducted. The two robots cooperatively obtained fast transition between stable states. The results illustrate the validity of the proposed method.     

Deadlock Resolution in Automated Manufacturing Systems With Robots

An automated manufacturing system (AMS) contains a number of versatile machines (or workstations), buffers, and an automated material handling system (MHS). The MHS can be an automated guide vehicle (AGV) system, and/or a system that consists of multiple robots. Deadlock resolution in AMS is an important issue. For the AMS with an AGV system as MHS, the problems of deadlock resolution for part processing process and AGV system as an integrated system has been studied. It is shown that AGVs can serve as both material handling devices and central buffers at the same time to help resolve deadlocks. For AMS with robots as MHS, the existing work treated the robots just as material handling devices and showed that the robots had contribution to deadlock. In this paper, such AMS is modeled by resource-oriented Petri nets. Contrary to the existing work, it is shown that the robots have no contribution to deadlock by adopting such nets to control AMS. More interestingly, they can be used to resolve deadlock by serving as temporary part storage devices. A new deadlock control policy is proposed by treating robots as both material handling devices and buffers. The new policy outperforms the existing ones.     

Reactive navigation of multiple moving agents by collaborative resolution of conflicts

In navigation that involves several moving agents or robots that are not in possession of each other's plans, a scheme for resolution of collision conflicts between them becomes mandatory. A resolution scheme is proposed in this paper specifically for the case where it is not feasible to have a priori the plans and locations of all other robots, robots can broadcast information between one another only within a specified communication distance, and a robot is restricted in its ability to react to collision conflicts that occur outside of a specified time interval called the reaction time interval. Collision conflicts are resolved through velocity control by a search operation in the robot's velocity space. The existence of a cooperative phase in conflict resolution is indicated by a failure of the search operation to find velocities in the individual velocity space of the respective robots involved in the conflict. A scheme for cooperative resolution of conflicts is modeled as a search in the joint velocity space of the robots involved in conflict when the search in the individual space yields a failure. The scheme for cooperative resolution may further involve modifying the states of robots not involved in any conflict. This phenomenon is characterized as the propagation phase where cooperation spreads to robots not directly involved in the conflict. Apart from presenting the methodology for the resolution of conflicts at various levels (individual, cooperative, and propagation), the paper also formally establishes the existence of the cooperative phase during real‐time navigation of multiple mobile robots. The effect of varying robot parameters on the cooperative phase is presented and the increase in requirement for cooperation with the scaling up of the number of robots in a system is also illustrated. Simulation results involving several mobile robots are presented to indicate the efficacy of the proposed strategy. © 2005 Wiley Periodicals, Inc.     

Grounded Symbolic Communication between Heterogeneous Cooperating Robots

In this paper, we describe the implementation of a heterogeneous cooperative multi-robot system that was designed with a goal of engineering a grounded symbolic representation in a bottom-up fashion. The system comprises two autonomous mobile robots that perform cooperative cleaning. Experiments demonstrate successful purposive navigation, map building and the symbolic communication of locations in a behavior-based system. We also examine the perceived shortcomings of the system in detail and attempt to understand them in terms of contemporary knowledge of human representation and symbolic communication. From this understanding, we propose the Adaptive Symbol Grounding Hypothesis as a conception for how symbolic systems can be envisioned.     

Some aspects of dynamic 3D representation and control of industrial processes via the Internet

In our research we examine and use 3D representation of industrial processes, for example the novel methods of Incremental Sheet Forming. We also test 3D imaging methods on our industrial robot solving the Rubik's Cube. We have created 3D models of our robots and their environment in our laboratory to examine the behavior of different industrial processes both in the real, and in the 3D virtual environment. We have connected the 3D model with the real system with which we could extend the features of our robots with some services that exits in the virtual space. We have also established synchronized connections of the real and virtual systems, which enables us to control the real robots and machines from its 3D model via the Internet.