P.C. Based Robotic Control Systems

1993 ◽  
Vol 26 (2) ◽  
pp. 515-518
Author(s):  
E.R. Fielding ◽  
E.D. Illos
Keyword(s):  
Control Systems ◽  
Robotic Control

VERIFICATION OF A MARINE POLLUTANT SURFACE PLUME MODEL FOR USE IN THE DEVELOPMENT OF AUTONOMOUS VEHICLE TRACKING SYSTEMS

2017 ◽  
Vol 2017 (1) ◽  
pp. 1612-1628
Author(s):  
Laura M. Fitzpatrick ◽  
A Zachary Trimble ◽  
Brian S. Bingham
Keyword(s):  
Control Systems ◽  
Surface Concentration ◽  
Computational Effort ◽  
Computational Time ◽  
Type Model ◽  
Fine Scale ◽  
Multiple Model ◽  
Robotic Control ◽  
Statistical Parameters ◽  
Tuning Parameters

ABSTRACT A marine pollutant spill environmental model that can accurately predict fine scale pollutant concentration variations on a free surface is needed in early stages of testing robotic control systems for tracking pollutant spills. The model must reproduce, for use in a robotic control system simulation environment, the fine-scale surface concentration variations observed by a robot. Furthermore, to facilitate development of robotic control systems, the model must reproduce sample spill distributions in minimal computational time. A combination Eulerian-Lagrangian type model, with two tuning parameters, was developed to produce, with minimal computational effort, the fine scale concentrations that would be observed by a robot. Multiple model scenarios were run with different tuning parameters to determine the effects of those parameters on the model’s ability to reproduce an experimental measured pollutant plume’s structure. A qualitative method for analyzing the concentration variations was established using amplitude and temporal statistical parameters. The differences in the statistical parameters between the model and experiment vary from 69%–316%. After tuning, the model produces a sample spill, which includes a high frequency concentration component not observed in the experimental data, but that generally represents the real-time, fine scale pollutant plume structure and can be used for testing control algorithms.

Game Theory

2011 ◽  
Vol 3 (3) ◽  
pp. 43-51 ◽  
Author(s):  
Aodhan L. Coffey ◽  
Tomas E. Ward ◽  
Richard H. Middleton
Keyword(s):  
Game Theory ◽  
Control Systems ◽  
Therapeutic Intervention ◽  
Behavioral Patterns ◽  
Robotic Control ◽  
Motor Rehabilitation ◽  
Real Patient ◽  
Agent Based ◽  
Agent Interactions ◽  
Patient Interaction

Designing suitable robotic controllers for automating movement-based rehabilitation therapy requires an understanding of the interaction between patient and therapist. Current approaches do not take into account the highly dynamic and interdependent nature of this relationship. A better understanding can be accomplished through framing the interaction as a problem in game theory. The main strength behind this approach is the potential to develop robotic control systems which automatically adapt to patient interaction behavior. Agents learn from experiences, and adapt their behaviors so they are better suited to their environment. As the models evolve, structures, patterns and behaviors emerge that were not explicitly programmed into the original models, but which instead surface through the agent interactions with each other and their environment. This paper advocates the use of such agent based models for analysing patient-therapist interactions with a view to designing more efficient and effective robotic controllers for automated therapeutic intervention in motor rehabilitation. The authors demonstrate in a simplified implementation the effectiveness of this approach through simulating known behavioral patterns observed in real patient-therapist interactions, such as learned dependency.

Game Theory

2014 ◽  
pp. 171-180
Author(s):  
Aodhan L. Coffey ◽  
Tomas E. Ward ◽  
Richard H. Middleton
Keyword(s):  
Game Theory ◽  
Control Systems ◽  
Therapeutic Intervention ◽  
Behavioral Patterns ◽  
Robotic Control ◽  
Motor Rehabilitation ◽  
Real Patient ◽  
Agent Based ◽  
Agent Interactions ◽  
Patient Interaction

Designing suitable robotic controllers for automating movement-based rehabilitation therapy requires an understanding of the interaction between patient and therapist. Current approaches do not take into account the highly dynamic and interdependent nature of this relationship. A better understanding can be accomplished through framing the interaction as a problem in game theory. The main strength behind this approach is the potential to develop robotic control systems which automatically adapt to patient interaction behavior. Agents learn from experiences, and adapt their behaviors so they are better suited to their environment. As the models evolve, structures, patterns and behaviors emerge that were not explicitly programmed into the original models, but which instead surface through the agent interactions with each other and their environment. This paper advocates the use of such agent based models for analysing patient-therapist interactions with a view to designing more efficient and effective robotic controllers for automated therapeutic intervention in motor rehabilitation. The authors demonstrate in a simplified implementation the effectiveness of this approach through simulating known behavioral patterns observed in real patient-therapist interactions, such as learned dependency.

Q-Model: An Artificial Intelligence Based Methodology for the Development of Autonomous Robots

2020 ◽  
Vol 20 (6) ◽  
Author(s):  
Philip Kurrek ◽  
Firas Zoghlami ◽  
Mark Jocas ◽  
Martin Stoelen ◽  
Vahid Salehi
Keyword(s):  
Artificial Intelligence ◽  
Control Systems ◽  
Autonomous Robots ◽  
Learning Approaches ◽  
Robotic Control ◽  
Intelligent Robots ◽  
Development Methodology ◽  
Current State ◽  
Literature Overview ◽  
Q Model

Abstract The increasing individualization of products reinforces the importance of decoupled factories in production processes. Artificial intelligence (AI) is a recognized technology for problem solving and accelerates automation by enabling systems to act independently. In the field of robotics, there are new deep learning approaches which make robotic control systems human independent. This work provides a literature overview of the current state of development methodologies, showing that there are only limited methods available for the development of artificial intelligent robots. We present a novel development methodology based on artificial intelligence, particularly deep reinforcement learning. The so-called Q-model can enable robots to learn specific tasks independently. In summary, we show how an AI-based methodology assists the development of autonomous robots along the product lifecycle.

Sign in / Sign up

Export Citation Format

Share Document