scholarly journals Knowledge-Based Control for Robot Arm

Robot Arms ◽  
10.5772/20203 ◽  
2011 ◽  
Author(s):  
Aboubekeur Hamdi-Cherif
Keyword(s):  
Robot Arm ◽  
Knowledge Based

scholarly journals Knowledge-Based Trajectory Error Pattern Method Applied to an Active Force Control Scheme

1970 ◽  
Vol 3 (1) ◽  
Author(s):  
Endra Pitowarno, Musa Mailah, Hishamuddin Jamaluddin
Keyword(s):  
Force Control ◽  
Error Pattern ◽  
Robot Arm ◽  
Active Force ◽  
Trajectory Error ◽  
Track Error ◽  
Knowledge Based ◽  
Inertia Matrix ◽  
Active Force Control ◽  
Control Scheme

The active force control (AFC) method is known as a robust control scheme that dramatically enhances the performance of a robot arm particularly in compensating the disturbance effects. The main task of the AFC method is to estimate the inertia matrix in the feedback loop to provide the correct (motor) torque required to cancel out these disturbances. Several intelligent control schemes have already been introduced to enhance the estimation methods of acquiring the inertia matrix such as those using neural network, iterative learning and fuzzy logic. In this paper, we propose an alternative scheme called Knowledge-Based Trajectory Error Pattern Method (KBTEPM) to suppress the trajectory track error of the AFC scheme. The knowledge is developed from the trajectory track error characteristic based on the previous experimental results of the crude approximation method. It produces a unique, new and desirable error pattern when a trajectory command is forced. An experimental study was performed using simulation work on the AFC scheme with KBTEPM applied to a two-planar manipulator in which a set of rule-based algorithm is derived. A number of previous AFC schemes are also reviewed as benchmark. The simulation results show that the AFC-KBTEPM scheme successfully reduces the trajectory track error significantly even in the presence of the introduced disturbances.Key Words:  Active force control, estimated inertia matrix, robot arm, trajectory error pattern, knowledge-based.

scholarly journals Intrinsically Motivated Open-Ended Multi-Task Learning Using Transfer Learning to Discover Task Hierarchy

2021 ◽  
Vol 11 (3) ◽  
pp. 975
Author(s):  
Nicolas Duminy ◽  
Sao Mai Nguyen ◽  
Junshuai Zhu ◽  
Dominique Duhaut ◽  
Jerome Kerdreux
Keyword(s):  
Reinforcement Learning ◽  
Learning Process ◽  
Industrial Robot ◽  
Imitation Learning ◽  
Robot Arm ◽  
Transfer Of Knowledge ◽  
Complex Tasks ◽  
Hierarchical Reinforcement Learning ◽  
Knowledge Based ◽  
Task Oriented

In open-ended continuous environments, robots need to learn multiple parameterised control tasks in hierarchical reinforcement learning. We hypothesise that the most complex tasks can be learned more easily by transferring knowledge from simpler tasks, and faster by adapting the complexity of the actions to the task. We propose a task-oriented representation of complex actions, called procedures, to learn online task relationships and unbounded sequences of action primitives to control the different observables of the environment. Combining both goal-babbling with imitation learning, and active learning with transfer of knowledge based on intrinsic motivation, our algorithm self-organises its learning process. It chooses at any given time a task to focus on; and what, how, when and from whom to transfer knowledge. We show with a simulation and a real industrial robot arm, in cross-task and cross-learner transfer settings, that task composition is key to tackle highly complex tasks. Task decomposition is also efficiently transferred across different embodied learners and by active imitation, where the robot requests just a small amount of demonstrations and the adequate type of information. The robot learns and exploits task dependencies so as to learn tasks of every complexity.

Is the Personal Always Political?

2017 ◽  
Vol 38 (3) ◽  
pp. 133-143 ◽  
Author(s):  
Danny Osborne ◽  
Yannick Dufresne ◽  
Gregory Eady ◽  
Jennifer Lees-Marshment ◽  
Cliff van der Linden
Keyword(s):  
Survey Data ◽  
National Survey ◽  
Negative Relationship ◽  
Openness To Experience ◽  
Political Sophistication ◽  
Knowledge Based

Abstract. Research demonstrates that the negative relationship between Openness to Experience and conservatism is heightened among the informed. We extend this literature using national survey data (Study 1; N = 13,203) and data from students (Study 2; N = 311). As predicted, education – a correlate of political sophistication – strengthened the negative relationship between Openness and conservatism (Study 1). Study 2 employed a knowledge-based measure of political sophistication to show that the Openness × Political Sophistication interaction was restricted to the Openness aspect of Openness. These studies demonstrate that knowledge helps people align their ideology with their personality, but that the Openness × Political Sophistication interaction is specific to one aspect of Openness – nuances that are overlooked in the literature.

Connectives Increase Knowledge-Based Inferences

1994 ◽  
Author(s):  
Gregory Barker ◽  
Keith Millis ◽  
Jonathan M. Golding
Keyword(s):  
Knowledge Based

The contribution of low-level sensory features versus knowledge-based factors for encoding of objects in working memory

2013 ◽  
Author(s):  
Valerio Santangelo ◽  
Simona Arianna Di Francesco ◽  
Serena Mastroberardino ◽  
Emiliano Macaluso
Keyword(s):  
Working Memory ◽  
Low Level ◽  
Knowledge Based ◽  
Sensory Features
Sign in / Sign up

Export Citation Format

Share Document