Download e-book for kindle: A Hybrid Deliberative Layer for Robotic Agents: Fusing DL by Ronny Hartanto

By Ronny Hartanto

The Hybrid Deliberative Layer (HDL) solves the matter that an clever agent faces in facing a large number of info which could or is probably not necessary in producing a plan to accomplish a aim. the knowledge, that an agent may have, is got and kept within the DL version. hence, the HDL is used because the major wisdom base procedure for the agent.

In this paintings, a unique method which amalgamates Description common sense (DL) reasoning with Hierarchical job community (HTN) making plans is brought. An research of the functionality of the technique has been performed and the consequences convey that this method yields considerably smaller making plans challenge descriptions than these generated through present representations in HTN planning.

Show description

Read Online or Download A Hybrid Deliberative Layer for Robotic Agents: Fusing DL Reasoning with HTN Planning in Autonomous Robots PDF

Similar machine theory books

Read e-book online Swarm Intelligence: Introduction and Applications PDF

The book’s contributing authors are one of the best researchers in swarm intelligence. The publication is meant to supply an outline of the topic to newbies, and to supply researchers an replace on attention-grabbing fresh advancements. Introductory chapters care for the organic foundations, optimization, swarm robotics, and purposes in new-generation telecommunication networks, whereas the second one half comprises chapters on extra particular themes of swarm intelligence study.

Read e-book online Progress in Artificial Intelligence: 12th Portuguese PDF

This e-book constitutes the refereed lawsuits of the twelfth Portuguese convention on synthetic Intelligence, EPIA 2005, held in Covilhã, Portugal in December 2005 as 9 built-in workshops. The fifty eight revised complete papers provided have been rigorously reviewed and chosen from a complete of 167 submissions. in keeping with the 9 constituting workshops, the papers are equipped in topical sections on common man made intelligence (GAIW 2005), affective computing (AC 2005), synthetic lifestyles and evolutionary algorithms (ALEA 2005), development and making use of ontologies for the semantic net (BAOSW 2005), computational equipment in bioinformatics (CMB 2005), extracting wisdom from databases and warehouses (EKDB&W 2005), clever robotics (IROBOT 2005), multi-agent platforms: conception and functions (MASTA 2005), and textual content mining and purposes (TEMA 2005).

New PDF release: Evolvable Components: From Theory to Hardware

At the start of the Nineties learn began in easy methods to mix smooth comput­ ing with reconfigurable in a really distinct manner. one of many equipment that used to be constructed has been referred to as evolvable undefined. due to evolution­ ary algorithms researchers have began to evolve digital circuits mostly.

Additional resources for A Hybrid Deliberative Layer for Robotic Agents: Fusing DL Reasoning with HTN Planning in Autonomous Robots

Example text

Pi } be the set of all preconditions in o. 12 as example, the Succ1 (o2) = {o5, o6}. 15 or as follows: Operator(o2), hasOperator(o2,o5), hasOperator(o2,o6), useState(o2,s1), useState(o2,s2), useState(o2,s3), shop2code(o2,sc2) 36 2 The Hybrid Deliberative Layer Operator(o2) hasOperator(o5) hasOperator(o6) useState(s1) useState(s2) useState(s3) shop2code(sc2) Fig. 15.

Let m be a method in htn and w = (U, E) be a graph that represents a task network of m. The hdl system’s immediate successors of m are Succ1 (m) = {u |u ∈ U ∧ u = m ∧ (m, u ) ∈ E} where u can either be a method or an operator in the htn. m1 Immediate Successor of m1 m2 m3 o3 o4 m1 o2 o1 o5 o6 m1 o1 Fig. 12. Task network of method m1 succ(m) is the set of all immediate successors of m. 12. The immediate successor of m1 is succ(m1) = {m1, m2, m3, o1, o2}. Although succ(m1) contains method m1, the hdl system’s immediate successor, Succ1 (m1), does not.

One approach to cope with this problem is to divide the goal into subgoals. The overall goal might be seen as a hierarchy. The extension approach to the hierarchical approach was implemented with “abstrips”. This approach minimises the size of the problem. Another approach, used to make the search faster, is the use of heuristics. A Hierarchical Task Network (htn) is a planning scheme which uses heuristics and a hierarchical approach to solve planning problems. The heuristic in this case is defined by the human who designs the planning problem.

Download PDF sample

Rated 4.32 of 5 – based on 50 votes

About the Author