Depalletizing, the process of unloading objects from pallets, is a critical task in warehouse automation. Robotic systems face challenges due to the diverse shapes and sizes of objects, often leading to failed grasps ...
详细信息
ISBN:
(纸本)9783031693434;9783031693441
Depalletizing, the process of unloading objects from pallets, is a critical task in warehouse automation. Robotic systems face challenges due to the diverse shapes and sizes of objects, often leading to failed grasps in cluttered environments. Pushing actions offer a promising solution to facilitate object singulation. In this work, we employ reinforcement learning (RL) for obtaining optimal pushing policies in depalletizing. We formulate the singulation task as goal reaching, where the target object is moved towards a goal area free from obstacles. Our approach, Goal-FCN (Goal-Driven Fully Convolutional Network), combines feature extraction with a fully convolutional neural network to predict effective pushing actions based on RGB-D images and scene segmentation. Experiments demonstrate the efficacy of our RL-based approach in achieving high success rates in challenging depalletization scenarios.
the proceedings contain 73 papers. the topics discussed include: real time diagnostics, prognostics, & process modeling;synchronization of multi-agent systems;binary optimization: a relation between the depth of a...
the proceedings contain 73 papers. the topics discussed include: real time diagnostics, prognostics, & process modeling;synchronization of multi-agent systems;binary optimization: a relation between the depth of a local minimum and the probability of its detection;DC motor fault diagnosis by means of artificial neural networks;target value prediction for online optimization at engine test beds;feasibility of subspace identification for bipeds - an innovative approach for Kino-dynamic systems;a hybrid intelligent multi-agent method for monitoring and fault diagnosis;piecewise constant reinforcement learning for robotic applications;discrete dynamic sliding surface control for robust speed control of induction machine drive;nonlinear fuzzy selftuning PID control technology and its applications in automated programming robotics;and heuristic algorithms for scheduling in a multiprocessor two-stage flowshop with 0-1 resource requirements.
the proceedings contain 89 papers. the topics discussed include: convexification of semi-activity constraints applied to minimum-time optimal control for vehicles with semi-active limited-slip differential;a novel mod...
ISBN:
(纸本)9789897584428
the proceedings contain 89 papers. the topics discussed include: convexification of semi-activity constraints applied to minimum-time optimal control for vehicles with semi-active limited-slip differential;a novel model to analyze the effect of deterioration on machine parts in the line throughput;using semi-implicit iterations in the periodic QZ algorithm;definition of a walking with starting and stopping motions for the humanoid Romeo;implementation of centralized MPC on the quadruple-tank process with guaranteeing stability;towards fully automated inspection of large components with UAVs: offline path planning;adaptive fault-tolerant control allocation schemes for overactuated systems with actuator and bias faults;and RBF neural network based trajectory control and impedance control of a upper limb tele-rehabilitation process.
the proceedings contain 8 papers. the special focus in this conference is on informatics in control, automation and robotics. the topics include: Improving 2D Scanning Radar and 3D Lidar Calibration;mobile Robots...
ISBN:
(纸本)9783031483028
the proceedings contain 8 papers. the special focus in this conference is on informatics in control, automation and robotics. the topics include: Improving 2D Scanning Radar and 3D Lidar Calibration;mobile Robots for Teleoperated Radiation Protection Tasks in the Super Proton Synchrotron;a Review of Classical and Learning Based Approaches in Task and Motion Planning;Multi-objective Ranking to Optimize CNN’s Encoding Features: Application to the Optimization of Tracer Dose for Scintigraphic Imagery;Linear Delta Kinematics Feedrate Planning for NURBS Toolpaths Implemented in a Real-Time Linux control System;automatic Fault Detection in Soldering Process During Semiconductor Encapsulation.
the proceedings contain 79 papers. the topics discussed include: sensitivity based generalization error for supervised learning problem with applications in model selection and feature selection;impact of the ICT on t...
ISBN:
(纸本)9789898111999
the proceedings contain 79 papers. the topics discussed include: sensitivity based generalization error for supervised learning problem with applications in model selection and feature selection;impact of the ICT on the management and performance of intelligent transportation systems;discrete event diagnosis using Petri nets;LMI-based trajectory planning for closed-loop control of robotic systems with visual feedback;automatic approach for rectifying building facades from a single uncalibrated image;interference reduction through task partitioning in a robotic swarm;an adaptive classifier design for accurate speech data classification;three dimensional tracking using object defocus - in two dimensional scanning electron microscope images;mobile platform self-localization in partially unknown dynamic environments;and model and approaches for tension of parallel structures with elastic joints for micro and nano manipulators.
the proceedings contain 42 papers. the topics discussed include: European standards and perspectives for e-voting in Bulgaria;a formula driven incremental construction of web service compositions;evaluating a framewor...
ISBN:
(纸本)9789898111999
the proceedings contain 42 papers. the topics discussed include: European standards and perspectives for e-voting in Bulgaria;a formula driven incremental construction of web service compositions;evaluating a framework for the development and deployment of evolving applications as a software maintenance tool;modeling the evolution of software engineering trends - a bottom up approach;resolving traceability issues in product derivation for software product lines;detecting regulatory vulnerability in functional requirements specifications;model transformation using adaptive systems;a self-adaptive architecture for autonomic systems developed with ASSL;aggregated accounting of memory usage in java;model driven testing with time augmented Markov chain usage models - computations and test case generation algorithms for time augmented Markov chain usage models;and refactoring of C/C++ preprocessor constructs at the model level.
the proceedings contain 196 papers. the topics discussed include: data-based tuning of pi controllers for vertical three-tank systems;differential evolution in parameter identification - fuel cell as an example;a prop...
ISBN:
(纸本)9789898565211
the proceedings contain 196 papers. the topics discussed include: data-based tuning of pi controllers for vertical three-tank systems;differential evolution in parameter identification - fuel cell as an example;a proposal of multiobjective fuzzy regulator design for state space nonlinear systems;rotor speed sensor fault detection in induction motors;visual anomaly detection in production plants;global optimal solution to SLAM problem with unknown initial estimates;spacecrafts' control systems effective variants choice with self-configuring genetic algorithm;robust arbitrary reference command tracking with application to hydraulic actuators;an application of goal programming technique for reconfiguration of transfer lines;a control strategy for reducing fuel consumption in a hybrid electric vehicle;and towards manufacturing execution systems for the food and beverage packaging industry.
the proceedings contain 196 papers. the topics discussed include: data-based tuning of pi controllers for vertical three-tank systems;differential evolution in parameter identification - fuel cell as an example;a prop...
ISBN:
(纸本)9789898565211
the proceedings contain 196 papers. the topics discussed include: data-based tuning of pi controllers for vertical three-tank systems;differential evolution in parameter identification - fuel cell as an example;a proposal of multiobjective fuzzy regulator design for state space nonlinear systems;rotor speed sensor fault detection in induction motors;visual anomaly detection in production plants;global optimal solution to SLAM problem with unknown initial estimates;spacecrafts' control systems effective variants choice with self-configuring genetic algorithm;robust arbitrary reference command tracking with application to hydraulic actuators;an application of goal programming technique for reconfiguration of transfer lines;a control strategy for reducing fuel consumption in a hybrid electric vehicle;and towards manufacturing execution systems for the food and beverage packaging industry.
Recently, there has been a surge in the development of advanced warehouse management systems that seamlessly incorporate robotized technologies. these robots have the capability to operate independently or collaborate...
详细信息
ISBN:
(纸本)9783031693434;9783031693441
Recently, there has been a surge in the development of advanced warehouse management systems that seamlessly incorporate robotized technologies. these robots have the capability to operate independently or collaborate with human staff to enhance the efficiency of items picking and storage. the paper at hand, introduces an intelligent Warehouse Management System, denoted as iWMS, designed for a goods-to-person warehouse environment. the system is configured to retrieve data of standard format compatible with commercial WMS through an application programming interface (API), while maintaining control over the robotic processes. this work aims to address the development of a software that will analyze incoming and outgoing orders and allocate the task of collecting and distributing bins with an Autonomous Mobile Robot (AMR). the proposed software performs a systematic analysis of incoming orders, linking them withthe respective fiducial markers that contain detailed information about the precise location of the relevant bin within the warehouse. Subsequently, the system assigns the task of orders collection to one or more AMRs, taking into account their availability and current positions within the warehouse. this is achieved using an algorithm that maximizes efficiency by optimizing both execution time and travel distances. Additionally, the application consistently updates the stock in the database based on the products identified within the bins, ensuring accurate and real-time stock counting in the warehouse database. the ultimate goal of the iWMS is to provide an easy-to-use tool, allowing the seamless co-existence between the workers and the robotic platforms in a common workplace. this iWMS is part of a robotic warehouse solution currently undergoing testing in simulation.
the proceedings contain 150 papers. the topics discussed include: an interpolation approach for constrained output feedback;target-aware anomaly detection and diagnosis;optimization learning method for discrete proces...
ISBN:
(纸本)9789898425744
the proceedings contain 150 papers. the topics discussed include: an interpolation approach for constrained output feedback;target-aware anomaly detection and diagnosis;optimization learning method for discrete process control;inner and outer capture basin approximation with support vector machines;a study for manufacturing cell formation approach considering setup;cost-optimal strong planning in non-deterministic domains;interactive sketch design recognition system using evolutionary techniques;generation of process variants;intelligent fault detection, identification and control of satellite formation flying;computational experience with structure-preserving Hamiltonian solvers in optimal control;personal advanced traveler assistant;building visual maps with a single omnidirectional camera;visual servoing of a multi-robotic system for manipulation tasks;and performance verification of the head/eye integrated tracker.
暂无评论