Here - Agents Lab - University of Nottingham

Recommendations

Info

An Agent-Based Cognitive Robot ArchitectureChangyun Wei and Koen V. HindriksInteractive Intelligence, Delft University of Technology, The Netherlands{C.Wei,K.V.Hindriks}@tudelft.nlAbstract. We propose a new cognitive robot control architecture inwhich the cognitive layer can be programmed by means of the agent programminglanguage Goal. The architecture exploits the support thatagent-oriented programming offers for creating cognitive robotic agents,including symbolic knowledge representation, deliberation via modular,high-level action selection, and support for multiple, declarative goals.The benefits of the architecture are that it provides a flexible approachto develop cognitive robots and support for a clean and clear separationof concerns about symbolic reasoning and sub-symbolic processing. Wediscuss the design of our architecture and discuss the issue of translatingsub-symbolic information and behaviour control into symbolic representationsneeded at the cognitive layer. An interactive navigation task ispresented as a proof of concept.1 IntroductionThe main motivation for our work is the need for a flexible, generic, high-levelcontrol framework that facilitates the development of re-taskable robot systemsand provides a feasible alternative to the usual task- and domain-dependentdevelopment of high-level robot control. We believe that agent-oriented programmingoffers such an approach as it supports the programming of cognitiveagents. Using agent programs to create the cognitive layer in a robot control architectureis natural and provides several benefits. It becomes relatively easy toadapt the control at the cognitive layer itself to various domains by exchangingone agent program with another. This approach is flexible and, if functionalityof other layers is generic and can be used in multiple task domains, facilitatesreuse. An agent-based approach, moreover, provides support for autonomous,reactive, and proactive behaviours and also endows a robot with the requireddeliberation mechanism to decide what to do next [1]. Of course, generality maycome at a trade-off and does not imply that a generic architecture will alwaysperform better than a dedicated robot control architecture [2].Designing and developing a cognitive robot control architecture poses severalchallenges. Robots are embedded systems that operate in physical, dynamicenvironments and need to be capable of operating in real-time. A range of perceptionand motor control activities need to be integrated into the architecture.This poses a particular challenge for a cognitive, symbolic architecture as “it canbe particularly difficult to generate meaningful symbols for the symbolic componentsof cognitive architectures to reason about from (potentially noisy) sensor55
data or to perform some low-level tasks such as control of motors” [3]. Ideally,moreover, such an architecture should provide support for the integration orexchange of new and different sensors and behaviours when needed. Given thecomplexity and the number of components needed in a robot control architecture,one also needs to consider how all the processing components in the systemcommunicate and interact with each other [4].In this paper, we propose an agent-based cognitive robot control architecturethat combines low-level sub-symbolic control with high-level symbolic control intothe robot control framework. We use the agent programming language Goal [5,6] to realize the cognitive layer, whereas low-level execution control and processingof sensor data are delegated to components in other layers in the proposedarchitecture. Goal, among others, supports the goal-oriented behavior and thedecomposition of complex behavior by means of modules that can focus theirattention on relevant sub-goals. Goal has already been successfully applied tocontrol real-time, dynamic environments [7], and here we demonstrate that italso provides a feasible approach for controlling robots. In our approach, thecognitive layer is cleanly separated from the other layers by using the EnvironmentInterface Standard (EIS; [8]).The paper is structured as follows. Section 2 briefly discusses some relatedwork. Section 3 presents and discusses the design of the cognitive robot architecture.Section 4 presents a proof of concept implementation. Section 5 concludesthe paper and discusses future work.2 Related WorkCognitive robots are autonomous and intelligent robot systems that can performtasks in real world environments without any external control, and are able tomake decisions and select actions in dynamic environments [9]. Here we discusssome related work that either explicitly aims to develop a cognitive architectureor uses some kind of symbolic representation for controlling a robot.The work that is most similar in spirit to our own is that of [10] and [11].In [10] the high-level language Golog is used for controlling a robot. Golog supportswriting control programs in a high-level, logical language, and providesan interpreter that, given a logical axiomatization of a domain, will determinea plan. Golog, however, does not provide a BDI perspective on programmingagents, and in [10] it does not discuss the robot control architecture itself. Ateleo-reactive program, consisting of multiple prioritized condition-action rules,is used to control a robot in [11] the proposed robot architecture in is not discussedin any detail.CRAM [1] is a software toolbox designed for controlling the Rosie robot platformdeveloped at the Technische Universität München. It makes use of Prologand includes a plan language that provides a construct for concurrent actions.The CRAM approach also aims at providing a flexible alternative to preprogrammedrobot control programs. The main difference with our approach isthat the reasoning and planning components are separated.56
Page 2 and 3:
Proceedings of the Tenth Internatio
Page 4 and 5:
OrganisationOrganising CommitteeMeh
Page 6: Table of ContentseJason: an impleme
Page 10 and 11: in Sect. 3 the translation of the J
Page 12 and 13: init_count(0).max_count(2000).(a)(b
Page 14 and 15: For instance, a failure in the ERES
Page 16 and 17: {plan, fun start_count_trigger/1,fu
Page 18 and 19: single parameter, an Erlang record
Page 20 and 21: 1. Belief annotations. Even though
Page 22 and 23: decisions taken during the design a
Page 24 and 25: Conceptual Integration of Agents wi
Page 26 and 27: Fig. 2. Active component structurep
Page 28 and 29: the service provider component. As
Page 30 and 31: Fig. 4. Web Service Invocationretri
Page 32 and 33: 01: public interface IBankingServic
Page 34 and 35: tate them in the same way as in the
Page 36 and 37: 01: public interface IChartService
Page 38 and 39: implementations being available for
Page 41: deliberative behavior in BDI archit
Page 44 and 45: layer modules (i.e. nodes) can be d
Page 46 and 47: different methods to choose the cur
Page 48 and 49: also a single scheduler module, imp
Page 50 and 51: andom choice (OR), conditional choi
Page 52 and 53: - Dealing with conflicts based on p
Page 54 and 55: 5. Brooks, R. A. (1991) Intelligenc
Page 58 and 59: It has been argued that building ro
Page 60 and 61: EnvironmentHardwareLocal SoftwareC+
Page 62 and 63: a cognitive layer can connect as a
Page 64 and 65: can reliably be differentiated and
Page 66 and 67: 4 ExperimentTo evaluate the feasibi
Page 68 and 69: learn or gain knowledge from experi
Page 70 and 71: A Programming Framework for Multi-A
Page 72 and 73: exchange and storage of tuples (key
Page 74 and 75: Although some success [13] [14] hav
Page 76 and 77: as well as important non-functional
Page 78 and 79: component plans have been instantia
Page 80 and 81: A in the example) can evaluate all
Page 83 and 84: 1. robot-1 issues a Localization(ro
Page 85 and 86: ACKNOWLEDGMENTThis work has been su
Page 87 and 88: The code was analysed both objectiv
Page 89 and 90: a conversation is following. Additi
Page 91 and 92: the context of a communication-heav
Page 93 and 94: Table 1. Core Agent ProtocolsAgent
Page 95 and 96: statistically significant using an
Page 97 and 98: to the conversation and has a perfo
Page 99 and 100: principal reasons. Firstly, it is a
Page 101 and 102: 2. Muldoon, C., O’Hare, G.M.P., C
Page 103 and 104: In the following section we will at
Page 105 and 106: DevelopmentProductionHuman Readabil
Page 107 and 108:
will then evaluate this new format
Page 109 and 110:
encoder, it is first checked if the
Page 111 and 112:
nents themselves. However, since th
Page 113 and 114:
optimized for this format feature s
Page 115 and 116:
Java serialization and Jadex Binary
Page 117 and 118:
10. P. Hoffman and F. Yergeau, “U
Page 119 and 120:
Caching the results of previous que
Page 121 and 122:
querying an agent’s beliefs and g
Page 123 and 124:
or relative performance of each pla
Page 125 and 126:
were run for 1.5 minutes; 1.5 minut
Page 127 and 128:
Size N K n p c qry U c upd Update c
Page 129 and 130:
epresentation. The cache simply act
Page 131 and 132:
6 ConclusionWe presented an abstrac
Page 133 and 134:
Typing Multi-Agent Programs in simp
Page 135 and 136:
1 // agent ag02 iterations (" zero
Page 137 and 138:
3.1 simpAL OverviewThe main inspira
Page 139 and 140:
3.2 Typing Agents with Tasks and Ro
Page 141 and 142:
Defining Agent Scripts in simpAL (F
Page 143 and 144:
that sends a message to the receive
Page 145 and 146:
* error: wrong type for the param v
Page 147 and 148:
Given an organization model, it is
Page 149 and 150:
Learning to Improve Agent Behaviour
Page 151 and 152:
2.1 Agent Programming LanguagesAgen
Page 153 and 154:
choosing actions is to find a good
Page 155 and 156:
1 init module {2 knowledge{3 block(
Page 157 and 158:
of a module. For example, to change
Page 159 and 160:
if bel(on(X,Y), clear(X)), a-goal(c
Page 161 and 162:
mance. Figure 2d shows the same A f
Page 163 and 164:
the current percepts of the agent.
Page 165:
Author IndexAbdel-Naby, S., 69Alelc
show all

Here - Agents Lab - University of Nottingham

Create successful ePaper yourself

Delete template?

Save as template?