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 will not be necessary in producing a plan to accomplish a objective. the knowledge, that an agent may have, is bought and kept within the DL version. therefore, the HDL is used because the major wisdom base approach for the agent.

In this paintings, a singular procedure which amalgamates Description good judgment (DL) reasoning with Hierarchical activity community (HTN) making plans is brought. An research of the functionality of the technique has been performed and the consequences express that this method yields considerably smaller making plans challenge descriptions than these generated via present representations in HTN planning.

Show description

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

Best machine theory books

Models of Massive Parallelism: Analysis of Cellular Automata and Neural Networks

Locality is a basic restrict in nature. nonetheless, adaptive advanced platforms, lifestyles particularly, express a feeling of permanence and time­ lessness amidst relentless consistent adjustments in surrounding environments that make the worldwide homes of the actual international an important difficulties in realizing their nature and constitution.

Geometric Theory of Information

This publication brings jointly geometric instruments and their functions for info research. It collects present and lots of makes use of of within the interdisciplinary fields of data Geometry Manifolds in complex sign, snapshot & Video Processing, advanced info Modeling and research, details score and Retrieval, Coding, Cognitive structures, optimum regulate, statistics on Manifolds, computer studying, Speech/sound popularity and common language therapy that are additionally considerably suitable for the undefined.

Swarm Intelligence: 9th International Conference, ANTS 2014, Brussels, Belgium, September 10-12, 2014. Proceedings

This ebook constitutes the lawsuits of the ninth overseas convention on Swarm Intelligence, held in Brussels, Belgium, in September 2014. This quantity includes 17 complete papers, nine brief papers, and seven prolonged abstracts conscientiously chosen out of fifty five submissions. The papers hide empirical and theoretical examine in swarm intelligence akin to: behavioral versions of social bugs or different animal societies, ant colony optimization, particle swarm optimization, swarm robotics platforms.

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

Sample text

However, during the planning time it might change such that during execution time the door is not open and the plan might fail. Most robot 26 2 The Hybrid Deliberative Layer Description of  Initial state Planner Objectives Plans Controller Observations Actions System  Events Fig. 6. A simple conceptual model for planning [82, chapter 1] actions are not instantaneous, but rather need some time to execute. This might be in seconds or minutes. Modelling the real world to create the planning domain is not a trivial problem.

The first robot planning system that was used for “Shakey” the robot was called strips. It worked under specific constraints: only one action can occur at a time, actions are instantaneous, and nothing changes except as the result of planned actions [56]. In strips, actions are represented as operators. The operators are specified by pre- and post-conditions. The environment is defined in the world model. These operators act upon the world model and trigger events which change the state from one into another.

The global metrical adds metric information to the topological map such that the robot can estimate the travel distance from one place to another. In 2007, Galindo et al. developed Semantic Hierarchical Planning through World Abstraction (shpwa) [20]. shpwa is based on their previous work on hierarchical planning called hpwa. It runs with an embedded planner, such as Metric-FF. shpwa uses a multi-hierarchical symbolic representation of its workspace. It entails two hierarchies that represent the environment from two different perspectives, namely spatial perspective and semantic perspective [21].

Download PDF sample

Rated 4.55 of 5 – based on 50 votes