On-Line Programming of Robot Skills

2019 ◽  
Author(s):  
Tapio Heikkilä ◽  
Janne Saukkoriipi ◽  
Jari M. Ahola ◽  
Tuomas Seppälä
Keyword(s):  
Object Localization ◽  
Sensor Data ◽  
Robot Systems ◽  
On Line ◽  
Robot Tasks ◽  
Skill Modeling

Abstract Robot skills provide a way to model and reuse sensor and robot technologies in effective ways. Skills can integrate and synchronize robot actions and sensor data in a consistent way and provide a framework for configurable robot systems, enabling quick setups of applications. Skills and skill modeling can be used not only for representing the composition of sensor based robot tasks, but also for programming on-line such tasks. In this paper we will introduce a skill based approach for representing on-line programming of skill based tasks. We will also give a practical example for modelling and implementing on-line programming of a handling skill relying on use of object localization sensors.

scholarly journals DOLARS, a Distributed On-Line Activity Recognition System by Means of Heterogeneous Sensors in Real-Life Deployments—A Case Study in the Smart Lab of The University of Almería

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 405
Author(s):  
Marcos Lupión ◽  
Javier Medina-Quero ◽  
Juan F. Sanjuan ◽  
Pilar M. Ortigosa
Keyword(s):  
Real Time ◽  
Activity Recognition ◽  
Real Life ◽  
Recognition System ◽  
Machine Learning Algorithms ◽  
Sensor Data ◽  
Heterogeneous Sensors ◽  
On Line ◽  
The University

Activity Recognition (AR) is an active research topic focused on detecting human actions and behaviours in smart environments. In this work, we present the on-line activity recognition platform DOLARS (Distributed On-line Activity Recognition System) where data from heterogeneous sensors are evaluated in real time, including binary, wearable and location sensors. Different descriptors and metrics from the heterogeneous sensor data are integrated in a common feature vector whose extraction is developed by a sliding window approach under real-time conditions. DOLARS provides a distributed architecture where: (i) stages for processing data in AR are deployed in distributed nodes, (ii) temporal cache modules compute metrics which aggregate sensor data for computing feature vectors in an efficient way; (iii) publish-subscribe models are integrated both to spread data from sensors and orchestrate the nodes (communication and replication) for computing AR and (iv) machine learning algorithms are used to classify and recognize the activities. A successful case study of daily activities recognition developed in the Smart Lab of The University of Almería (UAL) is presented in this paper. Results present an encouraging performance in recognition of sequences of activities and show the need for distributed architectures to achieve real time recognition.

scholarly journals Exploring Robot Connectivity and Collaborative Sensing in a High-School Enrichment Program

Robotics ◽  
2021 ◽  
Vol 10 (1) ◽  
pp. 13
Author(s):  
Igor M. Verner ◽  
Dan Cuperman ◽  
Michael Reitman
Keyword(s):  
High School ◽  
Positive Contribution ◽  
Smart Transportation ◽  
Sensory Data ◽  
Robot Systems ◽  
Enrichment Program ◽  
Collaborative Sensing ◽  
Robot Tasks ◽  
Value Of Learning ◽  
Multi Robot

Education is facing challenges to keep pace with the widespread introduction of robots and digital technologies in industry and everyday life. These challenges necessitate new approaches to impart students at all levels of education with the knowledge of smart connected robot systems. This paper presents the high-school enrichment program Intelligent Robotics and Smart Transportation, which implements an approach to teaching the concepts and skills of robot connectivity, collaborative sensing, and artificial intelligence, through practice with multi-robot systems. The students used a simple control language to program Bioloid wheeled robots and utilized Phyton and Robot Operating System (ROS) to program Tello drones and TurtleBots in a Linux environment. In their projects, the students implemented multi-robot tasks in which the robots exchanged sensory data via the internet. Our educational study evaluated the contribution of the program to students’ learning of connectivity and collaborative sensing of robot systems and their interest in modern robotics. The students’ responses indicated that the program had a high positive contribution to their knowledge and skills and fostered their interest in the learned subjects. The study revealed the value of learning of internet of things and collaborative sensing for enhancing this contribution.

On-Line Coordination Tasks for Multi-robot Systems Using Adaptive Informative Sampling

2020 ◽  
pp. 318-327
Author(s):  
Carlos Nieto-Granda ◽  
John G. Rogers III ◽  
Nicholas Fung ◽  
Stephanie Kemna ◽  
Henrik I. Christensen ◽  
...  
Keyword(s):  
Robot Systems ◽  
On Line ◽  
Informative Sampling ◽  
Multi Robot

On-Line Component Map Adaptive Procedure Based on Sensor Data

2020 ◽  
Author(s):  
Xuesen Yang ◽  
Xiaofeng Guo ◽  
Wei Dong
Keyword(s):  
Finite Difference ◽  
Gas Turbine ◽  
Optimization Procedure ◽  
Measured Data ◽  
Sensor Data ◽  
Mode Switching ◽  
Correction Factors ◽  
Adaptive Procedure ◽  
Primal Dual ◽  
On Line

Abstract A key challenge in the gas turbine community is to adapt the engine model by matching measured data with simulation data. This study presents a procedure aiming to calibrate a certain type of gas turbine for power generation. To reproduce degradation, disturbance is injected into the healthy components maps at different time. Subsequently, six correction factors along with measured data and unmeasured parameters are coupled together using cooperative working equations and optimized based on primal-dual interior point method. When performing the adaptive procedure, Jacobian and hessian matrices are calculated using finite difference since the component maps have external, mapped, functions implemented as lookup-tables, and mode-switching statements. To improve the accuracy of first-order and second-order partial derivatives, the finite difference is enhanced by Richardson extrapolation method. The search scope of correction factors and unmeasured parameters are determined by the whole working conditions. Meanwhile, an adaptive update method of initial solution is proposed to make sure the convergence of the optimization procedure as quickly as possible. Finally, the proposed method is further applied to the on-line adaptation in case of performance degradation. The influence of measurement noise on optimization is also studied. It is demonstrated that the procedure is capable of refining the component maps progressively, which is significant for the model-based gas path diagnostics and prognostics.

A Study on a Foraging Behavior of Interacting Simple Robots

2003 ◽  
Vol 7 (2) ◽  
pp. 108-114 ◽  
Author(s):  
Ken Sugawara ◽  
◽  
Masaki Sano ◽  
Toshinori Watanabe ◽  
◽  
...  
Keyword(s):  
Light Signal ◽  
Home Location ◽  
Considerable Research ◽  
Robot Systems ◽  
Point Field ◽  
Robot Tasks ◽  
Foraging Task ◽  
Robot Group ◽  
Simple Interaction ◽  
Multi Robot

Considerable research is currently being conducted in the area of multi-robot systems. The most remarkable characteristic of these types of systems is that the robots are able to work cooperatively to complete a task that a single robot cannot accomplish by itself. This characteristic is essential in the investigation of the effect of the number of robots in a given system. Out of the various possible multi-robot tasks, a foraging task was chosen for these experiments. The robots used in the experiments referenced by this paper had a simple interaction method with a light signal. The robots’ behavior in a one feeding point field was first discussed. This behavior was analyzed by both a robot simulation and a mathematical model. In the next experiment, numerous feeding points, equidistant from the home location, were arranged in the foraging field. The performance of the robots in this arrangement was then discussed. This report highlights the ordered behavior of the robot group, which greatly depends upon the number of robots and the strength of their interaction.

Sign in / Sign up

Export Citation Format

Share Document