Search results

The evolution of production systems has established major challenges in internal logistics. In order to overcome these challenges, new automation solutions have been developed and implemented. This paper is a literature review and analysis of selected scientific studies, which has as the main focus the existing solutions in robotics for internal logistics. The review aims to provide a broad perspective of the existing robotic systems for internal logistics to determine which research paths have been followed to date and highlight the current and future research directions. The survey has been subdivided into the following topics: localisation and path planning; task planning; optimisation and knowledge representation in robotic systems; and applications. The analysis of the works developed until the date of this review highlights the appearance of strategies in the different disciplines based on meta-heuristics. These are replacing the classical and heuristic approaches due to their limitations in dealing with a large amount of information in internal logistic systems. Due to the increase of information that robotic agents have to process, strategies based on semantic knowledge have been gaining prominence to make the domain knowledge explicit and eliminate ambiguities, allowing agents to reason and facilitate knowledge sharing between robotic agents and humans.

Autonomous mobile robotic agents are increasingly present in highly dynamic environments, thus making the planning and execution of their tasks challenging. Task planning is vital in directing the actions of a robotic agent in domains where a causal chain could lock the agent into a dead-end state. This paper proposes a framework that integrates a domain ontology (home environment ontology) with a task planner (ROSPlan) to translate the objectives coming from a given agent (robot or human) into executable actions by a robotic agent.

(c) 2007 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.

The aim of this work was to develop computational intelligence models based on neural networks (NN), fuzzy models (FM), and support vector machines (SVM) to predict physicochemical composition of bee pollen mixture given their botanical origin. To obtain the predominant plant genus of pollen (was the output variable), based on physicochemical composition (were the input variables of the predictive model), prediction models were learned from data. For the inverse case study, input/output variables were swapped. The probabilistic NN prediction model obtained 98.4% of correct classification of the predominant plant genus of pollen. To obtain the secondary and tertiary plant genus of pollen, the results present a lower accuracy. To predict the physicochemical characteristic of a mixture of bee pollen, given their botanical origin, fuzzy models proven the best results with small prediction errors, and variability lower than 10%.