Here - Agents Lab - University of Nottingham

Recommendations

Info

can reliably be differentiated and some assumptions about the environment canbe made.Another issue that needs to be handled by the EIS layer concerns the actionsthat are sent by the cognitive layer to the behavioural layer. Because behaviourshave duration and the cognitive layer runs in parallel with the behavioural layer,the cognitive layer may send the same action multiple times to the behaviourallayer or may send another action while an earlier action has not yet been completed.Because only some actions can be run in parallel, a decision may haveto be made about which action has priority. For example, a robot can walk andtalk at the same time but this is not the case for walking and sitting down. Inthe latter case, the behavioural layer needs to be able to gracefully terminateone behaviour in favour of another, or, in exceptional cases, ignore an actioncommand from the cognitive layer.3.4 Other Distinctive Properties of Our ArchitectureIn this section, we briefly discuss some distinctive properties of our architecture.Decoupled Reactive and Deliberative Control Similar to most hierarchicalarchitectures, we also distinguish reactive and deliberative control in ourarchitecture. As usual, reactive control resides in the behavioural layer that isresponsible for sub-symbolic information processing and behaviour execution,whereas deliberative control resides in the cognitive layer that is responsible forsymbolic reasoning and decision making. In fact, these layers have been rigidlyseparated in our architecture by means of the EIS layer. In other words, in ourdesign these layers have been completely decoupled. The main benefit of such adesign consist of a clean separation of concerns. The price that needs to be paidfor this strict separation is duplication of information and an additional effortof developers to design a well-defined interface between the two layers.Decoupling of these layers facilitates the more or less independent programmingof high-level, cognitive agents that control a robot as well as of lower-levelbehavioural functions. An agent programmer, for example, does not need tospend time handling object recognition. Similarly, a behaviour programmer whocodes in C++ does not have to consider decision making nor even master theagent programming language used in the cognitive layer.Multi-Goal Maintenance Often when robots try to accomplish a complextask, they will have to fulfil multiple goals [28]. Robots, however, cannot performall of these goals at the same time either because goals may conflict witheach other, or achieving a goal presupposes the achievement of others. As asimple example, when a robot needs to execute a command "Pick up objectB in place A", it actually has to fulfil two sub-goals in order to accomplishthe goal; the robot needs to figure out that it first has to perform the actiongoto(place(A)) and thereafter perform pickup(object(B)).63
The cognitive layer realized by an agent programming language such as Goalis able to handle multiple, possibly conflicting goals. Goal [5] has a specialoperator to express that a goal needs to be achieved: a-goal(ϕ) as well as that(part of) a goal has been achieved goal-a(ϕ). For instance, goto(place(A))can be expressed as an achievement goal as follows:a-goal(goto(place(A))) df = goal(goto(place(A))), not(bel(in(place(A)))Goal achievement can be expressed by:goal-a(goto(place(A)) df = goal(goto(place(A)), bel(in(place(A))The handling of multiple goals has been demonstrated already successfully inreal-time gaming environments [7].Multi-Modal Communication Our architecture endows robots with multiplechannels of communication with humans or other robots.– Semantic Representation for Human Robot Interaction Since one ofthe objectives of developing intelligent robots is to offer better lives to humans,robots should be able to operate and help humans in daily activities.When interacting with humans, robots are required to incorporate communicationand collaboration abilities. Human-robot interaction imposes specialrequirements on robot systems, and such interaction should be natural andintuitive for a human user. In particular, human-oriented interaction needs totake human abilities for effectively interacting into account. Symbolic knowledgerepresentations could be accessible for human interpretation throughprecept-symbol identification by the designer [29]. Generally speaking, robotcontrol systems need to adapt to humans by facilitating interaction that humanscan understand. Our architecture supports knowledge processing andcan produce semantic messages to facilitate interaction at the knowledgelevel with humans.– Shared Perceptions and Beliefs for Multi-Robot Interaction Fromthe perspective of multi-robot systems, robot systems are seldom standalonesystems; however, robots should share their perceptions in order tointeract with each other. For an individual robot, the perception messageswill be transmitted from the sub-symbolic layers to the symbolic layers via aninner-communication channel, where the connection is constructed based onServer/Client structure in the TCP/IP protocol. The sub-symbolic layer ineach robot starts a server that is unique for that robot, whereas the symboliclayer itself can have several clients, each of which can connect to either theserver of its own or other robots. In this way, the robots cannot only receivethe information from its own perceptions but also exchange their perceptionswith other robots.Our architecture provides the communication mechanisms for both innercommunicationand external-communication, enabling robots to send and receiveperception messages, and exchange mental beliefs present in the cognitive layer.64
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 56 and 57: An Agent-Based Cognitive Robot Arch
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 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?