基于心智系数的多Agent合同网协作模型研究

在多Agent系统中,常用的协商模型为合同网协议。在分析了经典合同协议优缺点后,提出基于熟人模型和心智系数合同协议的多Agent协作模型。在系统构建过程中引入心智状态中的信任度、熟悉度、他信度、繁忙度等概念,提出心智系数的更新规则并设计实现基于心智的合同网模型的构建。最后以机器人足球比赛为背景,对协商过程进行模拟测试与结果分析,证实了该模型能在保证协商质量的基础上有效地降低协商的时间和通信量,实现多Agent系统的高效协作。     

基于π演算的足球机器人协作Q学习方法

针对多机器人协作学习时出现的学习速度慢、学习效率低等问题,提出了一种基于π演算心智模型的足球机器人协作Q学习方法,描述了机器人的运动模型,定义了球场现状、目标、意图、行为、协作、请求、扩展知识、能力判断和联合意图等机器人心智状态,构造了联合奖励函数。最后通过实验验证了方法的有效性。     

基于评价选择策略的Internet多机器人协作控制研究

针对Internet多机器人系统中存在的操作指令延迟、工作效率低、协作能力差等问题,提出了多机器人神经元群网络控制模型。在学习过程中,来自不同功能区域的多类型神经元连接形成动态神经元群集,来描述各机器人的运动行为与外部条件、内部状态之间复杂的映射关系,通过对内部权值连接的评价选择,以实现最佳的多机器人运动行为协调。以互联网足球机器人系统为实验平台,给出了学习算法描述。仿真结果表明,己方机器人成功实现了配合射门的任务要求,所提模型和方法提高了多机器人的协作能力,并满足系统稳定性和实时性要求。     

基于强化学习的未知环境多机器人协作搜集

针对多机器人协作复杂搜集任务中学习空间大,学习速度慢的问题,提出了带共享区的双层强化学习算法。该强化学习算法不仅能够实现低层状态-动作对的学习,而且能够实现高层条件-行为对的学习。高层条件-行为对的学习避免了学习空间的组合爆炸,共享区的应用强化了机器人间协作学习的能力。仿真实验结果说明所提方法加快了学习速度,满足了未知环境下多机器人复杂搜集任务的要求。     

一种基于操作条件反射原理的学习模型

针对认知机器人的自主学习问题,提出一种基于操作条件反射原理的学习模型(OCLM).该模型采用状态空间、操作行为空间、概率分布函数、仿生学习机制、系统熵等进行描述,给出状态的"负理想度"的概念,定义了取向函数的计算方法.运用模型对机器人避障导航问题进行仿真实验,并对参数设置进行了讨论.实验结果表明,基于OCLM模型的机器人能通过与环境的交互获得认知,成功避障到达目的地,具有一定的自学习能力,从而表明了模型的有效性.     

自适应模糊RBF神经网络的多智能体机器人强化学习

多机器人环境中的学习,由于机器人所处的环境是连续状态,连续动作,而且包含多个机器人,因此学习空间巨大,直接应用Q学习算法难以获得满意的结果。文章研究中针对多智能体机器人系统的学习问题,提出自适应模糊RBF神经网络强化学习算法,网络本身具有模糊推理能力、较强的函数逼近能力以及泛化能力,因此,实现了人类专家知识与机器学习方法的结合,减少学习问题的复杂度;实现连续状态空间与动作空间的策略学习。     

AUV心智逻辑*

为了表示和处理AUV（Autonomous Underwater Vehicle,自治水下机器人）的心智状态及心智活动,对Rao和Georgeff的BDI逻辑进行了拓展,定义了一种含模态词（信念、目标、能力、意图、上一次、下一次、曾经、将会、总有、总会）的一阶模态时态混合逻辑系统——AML（AUV心智逻辑）;基于Kripke可能世界语义模型给出了AML语义,构造了AML公理系统及演绎规则,并证明了AML的可靠性与完备性。AML为建造AUV心智模型提供了有力的表示和处理工具,弥补了Agent理论在机器人应用     

Goal在Agent中的使用研究综述

Agent系统是综合哲学和计算机科学等多门学科的交叉研究领域。心智模型是Agent研究中的核心问题,在各种心智模型中,最成功的是BDI模型,而Goal的引入为BDI心智模型的研究提供了新的思路。根据Goal在Agent中的特点,阐述了Goal在Agent模型中的引入、分类、语义、协商等主题,旨在总结和分析现有的Agent中Goal的使用和机制,为BDI Agent心智模型的研究和对Goal研究的发展趋势和方向提供参考。     

基于多约束条件的机器人抓取策略学习方法

针对机器人在多类别物体不同任务下的抓取决策问题,提出基于多约束条件的抓取策略学习方法.该方法以抓取对象特征和抓取任务属性为机器人抓取策略约束,通过映射人类抓取习惯规划抓取模式,并采用物体方向包围盒(OBB)建立机器人抓取规则,建立多约束条件的抓取模型.利用深度径向基(DRBF)网络模型结合减聚类算法(SCM)实现抓取策略的学习,两种算法的结合旨在提高学习鲁棒性与精确性.搭建以Refiex 1型灵巧手和AUBO六自由度机械臂组成的实验平台,对多类别物体进行抓取实验.实验结果表明,所提出方法使机器人有效学习到对多物体不同任务的最优抓取策略,具有良好的抓取决策能力.     

基于多演示动作基元参数化学习的机器人任务泛化

针对机器人示范学习过程中任务泛化与动作轨迹泛化问题,提出了一种将多演示动作轨迹的任务参数化学习与动作序列推理相结合的方法.针对通用动作基元的多演示轨迹样本,利用动态运动基元进行轨迹编码并建立任务参数化模型,利用高斯过程回归学习外部参数与模型参数之间的映射.针对新的任务实例,利用规划域定义语言推理缺失动作序列,任务参数化模型根据新的外部参数泛化出动作的目标轨迹,并修正轨迹误差.在UR5机器人上的实验表明,面对不同任务实例和环境变化,该方法可灵活生成动作序列并调整泛化目标,基于多演示的任务参数化模型能够对给定外部参数泛化出平滑的目标轨迹,泛化效果优于单一演示轨迹,提高了机器人任务泛化的能力.     

基于市场法及能力分类的多机器人任务分配方法

针对多机器人系统研究中如何有效地实现复杂任务的分布式动态分配这个基础性问题，提出了一种对这类问题进行形式化描述的一般方法．该方法从能力分类的角度出发，提出了机器人及任务能力向量的概念，并对多机器人任务分配问题进行了形式化描述，讨论了单个及多个机器人合作完成任务的能力条件．基于这种形式化描述方法，提出了一种采用市场机制的完全分布式的多机器人任务分配方法．仿真实验结果表明该方法能够有效地实现多机器人复杂任务的动态分布式分配．     

Application of SONQL for real-time learning of robot behaviors

This paper describes the Semi-Online Neural-Q-learning (SONQL) algorithm designed for real-time learning of reactive robot behaviors. The Q-function is generalized by a multilayer neural network allowing the use of continuous states. The algorithm uses a database of the most recent learning samples to accelerate and improve the convergence. Each SONQL algorithm represents an independent, reactive and adaptive state-action mapping, which implements the function of a robot behavior for one degree of freedom (DOF). The generalization capability of the SONQL algorithm was demonstrated by computer simulation with the “mountain–car” benchmark. The SONQL was also investigated by experiment on a mobile robot for a target-following task. Experimental results show that the SONQL is promising for online robot learning.     

全驱动轮式机器人越障过程模型及影响因素分析

根据全驱动轮式机器人的基本结构构造了越障过程极限状态的动力学模型,该模型体现了多个驱动轮输出转矩之间的关系以及重心分布等影响因素．根据此模型，能够确定系统所需的最低驱动能力和重心分布的限制条件，以满足全驱动轮式机器人的越障性能需求．     

面向协同任务的多UCAV分布式任务分配与协调技术

对多架无人作战飞机 (Unmanned combat aerial vehicle, UCAV) 分布式控制中的任务分配与任务协调问题开展研究. 采用合同网实现任务执行过程中的任务分配. 通过对合同网进行扩展, 使 UCAV 能够在招标和竞标的同时处理任务间的时间约束. 设计了一种新的部分全局规划协商机制, 能够更有效地对执行相关任务的 UCAV 的任务计划进行协调. 通过 Petri 网建模方法, 将两种协商机制模型化为 Petri 网并分析了协商过程的正确性与协商结果的可行性. 仿真实验验证了方法的有效性.     

RoboCup Rescue as multiagent task allocation among teams: experiments with task interdependencies

This paper addresses distributed task allocation among teams of agents in a RoboCup Rescue scenario. We are primarily concerned with testing different mechanisms that formalize issues underlying implicit coordination among teams of agents. These mechanisms are developed, implemented, and evaluated using two algorithms: Swarm-GAP and LA-DCOP. The latter bases task allocation on a comparison between an agent’s capability to perform a task and the capability demanded by this task. Swarm-GAP is a probabilistic approach in which an agent selects a task using a model inspired by task allocation among social insects. Both algorithms were also compared to another one that allocates tasks in a greedy way. Departing from previous works that tackle task allocation in the rescue scenario only among fire brigades, here we consider the various actors in the RoboCup Rescue, a step forward in the direction of realizing the concept of extreme teams. Tasks are allocated to teams of agents without explicit negotiation and using only local information. Our results show that the performance of Swarm-GAP and LA-DCOP are similar and that they outperform a greedy strategy. Also, it is possible to see that using more sophisticated mechanisms for task selection does pay off in terms of score.     

Robot introspection through learned hidden Markov models

In this paper we describe a machine learning approach for acquiring a model of a robot behaviour from raw sensor data. We are interested in automating the acquisition of behavioural models to provide a robot with an introspective capability. We assume that the behaviour of a robot in achieving a task can be modelled as a finite stochastic state transition system.Beginning with data recorded by a robot in the execution of a task, we use unsupervised learning techniques to estimate a hidden Markov model (HMM) that can be used both for predicting and explaining the behaviour of the robot in subsequent executions of the task. We demonstrate that it is feasible to automate the entire process of learning a high quality HMM from the data recorded by the robot during execution of its task.The learned HMM can be used both for monitoring and controlling the behaviour of the robot. The ultimate purpose of our work is to learn models for the full set of tasks associated with a given problem domain, and to integrate these models with a generative task planner. We want to show that these models can be used successfully in controlling the execution of a plan. However, this paper does not develop the planning and control aspects of our work, focussing instead on the learning methodology and the evaluation of a learned model. The essential property of the models we seek to construct is that the most probable trajectory through a model, given the observations made by the robot, accurately diagnoses, or explains, the behaviour that the robot actually performed when making these observations. In the work reported here we consider a navigation task. We explain the learning process, the experimental setup and the structure of the resulting learned behavioural models. We then evaluate the extent to which explanations proposed by the learned models accord with a human observer's interpretation of the behaviour exhibited by the robot in its execution of the task.     

RoboCup标准平台组中基于改进合同网协议的任务分配算法

针对RoboCup标准平台组SPL中多机器人之间的协同问题,提出了基于改进合同网协议的任务分配算法。首先对RoboCup多机器人系统建立层次结构分解模型和单体机器人行为任务树模型,并采用AHP层次分析法确定各个任务权重。其次,提出基于改进合同网协议的任务分配策略,相对于传统合同网协议,改进的合同网协议将标书公示机制引入任务分配模型;同时,提出了优先招标策略并对合同网协议流程和评价函数进行了改进和扩展。     

基于积极团队情感基调的情感机器人协作任务分配拍卖算法

多机器人系统(Multi Robot System,MRS)通过引入机器人个体情感因素,可以有效提高个体的自主协作能力、决策能力以及多机器人系统的整体智能化水平。然而,以往研究主要集中于个体情感状态(情绪、个性等),缺乏从团队情感层面来探索积极团队情感基调(Positive Group Affective Tone,PGAT)对团队协作能力和团队有效性的影响。为了发挥PGAT在任务分配中的积极作用,降低因为团队成员情绪衰减而导致团队解散的风险,并增加团队协作能力和团队有效性,提出了基于PGAT的情感机器人协作任务分配拍卖算法。仿真追捕对比实验表明,相对于基于焦虑情感模型的改进合同网协议多机器人任务分配算法和基于自主意识的分布式情感机器人任务分配算法,基于PGAT的情感机器人协作任务分配拍卖算法的追捕成功率分别提高了269.3%和6.5%,任务分配成功率分别提高了138.7%和5.1%,平均追捕时间分别缩短了14.5%和26.3%,并且在150场追捕对比实验中,追捕时间小于对比算法的场次占比分别达到87.3%和90.7%。     

Grasp capability analysis of multifingered robot hands

This paper addresses the problem of grasp capability analysis of multifingered robot hands. The aim of the grasp capability analysis is to find the maximum external wrench that the multifingered robot hands can withstand, which is an important criterion in the evaluation of robotic systems. The study of grasp capability provides a basis for the task planning of force control of multifingered robot hands. For a given multifingered hand geometry, the grasp capability depends on the joint driving torque limits, grasp configuration, contact model and so on. A systematic method of the grasp capability analysis, which is in fact a constrained optimization algorithm, is presented. In this optimization, the optimality criterion is the maximum external wrench, and the constraints include the equality constraints and the inequality constraints. The equality constraints are for the grasp to balance the given external wrench, and the inequality constraints are to prevent the slippage of fingertips, the overload of joint actuators, the excessive forces over the physical limits of the object, etc. The advantages of this method are the ability to accomodate diverse areas such as multiple robot arms, intelligent fixtures and so on. The effectiveness of the proposed method is confirmed with a numerical example of a trifingered grasp.