scholarly journals Refining Abstraction Heuristics during Real-Time Planning

2019 ◽  
Vol 33 ◽  
pp. 7578-7585
Author(s):  
Rebecca Eifler ◽  
Maximilian Fickert ◽  
Jörg Hoffmann ◽  
Wheeler Ruml
Keyword(s):  
Real Time ◽  
Fixed Time ◽  
Improve Performance ◽  
Search Methods ◽  
Abstraction Refinement ◽  
The Real ◽  
Powerful Technique ◽  
Current State ◽  
On Line ◽  
Time Planning

In real-time planning, the planner must select the next action within a fixed time bound. Because a complete plan may not have been found, the selected action might not lead to a goal and the agent may need to return to its current state. To preserve completeness, real-time search methods incorporate learning, in which heuristic values are updated. Previous work in real-time search has used table-based heuristics, in which the values of states are updated individually. In this paper, we explore the use of abstraction-based heuristics. By refining the abstraction on-line, we can update the values of multiple states, including ones the agent has not yet generated. We test this idea empirically using Cartesian abstractions in the Fast Downward planner. Results on various benchmarks, including the sliding tile puzzle and several IPC domains, indicate that the approach can improve performance compared to traditional heuristic updating. This work brings abstraction refinement, a powerful technique from offline planning, into the real-time setting.

The Real-Time Prediction of Surface Roughness Based on Genetic Wavelet Network

2010 ◽  
Vol 102-104 ◽  
pp. 610-614 ◽  
Author(s):  
Jun Chi ◽  
Lian Qing Chen
Keyword(s):  
Surface Roughness ◽  
Real Time ◽  
Back Propagation ◽  
Cutting Parameters ◽  
Wavelet Network ◽  
Back Propagation Algorithm ◽  
The Real ◽  
Roughness Model ◽  
On Line ◽  
Artificial Network

A methodology based on relax-type wavelet network was proposed for predicting surface roughness. After the influencing factors of roughness model were analyzed and the modified wavelet pack algorithm for signal filtering was discussed, the structure of artificial network for prediction was developed. The real-time forecast on line was achieved by the nonlinear mapping and learning mechanism in Elman algorithm based on the vibration acceleration and cutting parameters. The weights in network were optimized using genetic algorithm before back-propagation algorithm to reduce learning time.The validation of this methodology is carried out for turning aluminum and steel in the experiments and its prediction error is measured less than 3%.

A storage scheme for the real-time database supporting the on-line commitment

2013 ◽  
Author(s):  
Hong-bin Dai ◽  
Yu-jian Jing ◽  
Hui Wang
Keyword(s):  
Real Time ◽  
The Real ◽  
Storage Scheme ◽  
On Line ◽  
Real Time Database

scholarly journals Augmented RealityAugmented Reality

2021 ◽  
Vol 9 (VII) ◽  
pp. 3510-3522
Author(s):  
Ankur Kumar
Keyword(s):  
Augmented Reality ◽  
Real Time ◽  
The Real ◽  
Time Performance ◽  
Real Environment ◽  
Augmented Reality System ◽  
Current State

Augmented Reality (AR), which blends virtual information with the real environment in real-time performance, is constantly evolving and becoming more sophisticated and robust. It is critical to ensure that the augmented reality system is accepted and successful. This paper primarily discusses the current state of AR applications and the various fields in which AR is being used.

Interactive Two-Stage Rendering Technique of Deformable Part Through Haptic Interface

2011 ◽  
Author(s):  
Zhaoguang Wang ◽  
Georges Dumont
Keyword(s):  
Real Time ◽  
Degrees Of Freedom ◽  
Rigid Body Dynamics ◽  
Haptic Interaction ◽  
Two Stage ◽  
Deformation Spaces ◽  
The Real ◽  
Time Deformation ◽  
Main Challenge ◽  
On Line

Virtual Reality technology has been widely applied in the background of industrial evaluation applications. However, a large majority of these applications are focusing on haptics-based assemblies which mainly deal with rigid-body dynamics. Here we concern the real-time haptic interaction with deformable mock-ups aiming at the industrial design evaluation of mechanical parts. The main challenge of this application is that a tradeoff between the deformation accuracy and the interaction performance has to be achieved. In this paper, we propose a two-stage method for a real-time deformation modelling by combining an off-line pre-computation phase and an on-line deformation interaction phase. The key contributions of this paper lie on two aspects. First, during off-line phase, we propose a mesh analysis method which allows us to pre-compute different deformation spaces by anticipating the evaluation scenarios. Moreover, a real-time switch among different deformation spaces is developed so that the on-line deformation computation can focus on degrees of freedom where necessary with respect to users’ interactions. Second, during on-line phase, we apply a division scheme to divide the deformation process into two separate modules which are implemented on different threads to ensure the haptic interaction performance. Experiments are carried out based on a prototype implementation concerning different models of growing complexity. The deformation accuracy and the real-time performance are discussed.

On-line Assessment of Voltage Stability using Synchrophasor Technology

2017 ◽  
Vol 8 (1) ◽  
pp. 1 ◽  
Author(s):  
Satyendra Pratap Singh ◽  
S.P. Singh
Keyword(s):  
Real Time ◽  
Voltage Stability ◽  
Measurement Unit ◽  
The Real ◽  
Minimum Number ◽  
On Line ◽  
Successive Change ◽  
Observable Data ◽  
Bus Voltage

Series of blackouts encountered in recent years in power system have been occurred because either of voltage or angle instability or both together was not detected within time and progressive voltage or angle instability further degraded the system condition, because of increase in loading. This paper presents the real-time assessment methodology of voltage stability using Phasor Measurement Unit (PMU) with observability of load buses only in power network. PMUs are placed at strategically obtained location such that minimum number of PMU’s can make all load buses observable. Data obtained by PMU’s are used for voltage stability assessment with the help of successive change in the angle of bus voltage with respect to incremental load, which is used as on-line voltage stability predictor (VSP). The real-time voltage phasors obtained by PMU’s are used as real time voltage stability indicator. The case study has been carried out on IEEE-14 bus system and IEEE-30 bus systems to demonstrate the results.

Optimisation of SFE method on-line coupled to FT-IR spectroscopy for the real-time monitoring of the extraction of tagitinin C in T. diversifolia

2007 ◽  
Vol 40 (3) ◽  
pp. 368-375 ◽  
Author(s):  
E. Ziemons ◽  
N. Wandji Mbakop ◽  
E. Rozet ◽  
R. Lejeune ◽  
L. Angenot ◽  
...  
Keyword(s):  
Ir Spectroscopy ◽  
Real Time ◽  
Real Time Monitoring ◽  
The Real ◽  
On Line ◽  
Ft Ir ◽  
Ft Ir Spectroscopy

Monitoring and control using on-line ORP on the continuous-flow activated sludge batch reactor system

1997 ◽  
Vol 35 (1) ◽  
pp. 57-66 ◽  
Author(s):  
R.-F. Yu ◽  
S.-L. Liaw ◽  
C.-N. Chang ◽  
H.-J. Lu ◽  
W.-Y. Cheng
Keyword(s):  
Process Control ◽  
Activated Sludge ◽  
Real Time ◽  
Continuous Flow ◽  
Batch Reactor ◽  
Fixed Time ◽  
Monitoring And Control ◽  
Time Control ◽  
On Line ◽  
And Control

On-line monitoring of ORP has been proved to be a practical and useful technique for process control of wastewater treatment systems. This paper presents the feasibility of using on-line ORP monitoring system on a laboratory scale single tank continuous-flow activated sludge batch reactor, which is capable of removing carbon, nitrogen and phosphorus pollutants. Two control strategies, fixed-time and real-time, are applied for process control. Results obtained from fixed-time control study indicate that the variations and the ORP profile can accurately represent dynamic characteristics of system; the pH profile can also indicate some of those characteristics. Also, the breakpoints, setpoints and settime on the ORP and pH profiles are used to establish the real-time control strategy to determine the transfer of operation stages. The real-time experiments show a better performance than fixed-time, thus, on-line ORP and pH monitoring and control is practical for continuous-flow batch activated sludge process control.

Sign in / Sign up

Export Citation Format

Share Document