scholarly journals Measuring and Tracking Externalized Work to Support Industrialized Construction

2016 ◽  
Author(s):  
Perry Daneshgari ◽  
Heather Moore ◽  
Hisham Said
Keyword(s):  
Tacit Knowledge ◽  
Performance Outcomes ◽  
The Novel ◽  
Construction Operations ◽  
Planning And Control ◽  
Expected Performance ◽  
Control Framework ◽  
Novel Concept ◽  
And Control ◽  
The Impact

The same principles that have made other skilled-trade-based industries more efficient are being deployed in construction through Industrialization, which requires understanding skilled trade work and segregating/externalizing the work from the jobsite. The construction industry still relies heavily on skilled trades and their tacit knowledge, while most of the information available at the points of installation is not passed on. A significant increase of work externalization requires a measuring and tracking method that can: 1) tap into this tacit knowledge as the basis for work planning and control; and 2) understand, quantify, and minimize the manipulation effort done onsite for the prefabricated assemblies. As such, this paper presents a planning and control framework for industrialized construction operations that integrates information entropy and the novel concept of work manipulations to monitor and measure the expected performance outcomes, in a more sophisticated approach beyond measuring äóìhoursäó� and äóìquantitiesäó� of the work. The development of the proposed framework is based on the analysis of a set of case studies that illustrate the impact of information predictability manipulation strategies on construction prefabrication decisions.

On-Line Reconfigurable Machines

AI Magazine ◽  
2013 ◽  
Vol 34 (3) ◽  
Author(s):  
Lara S. Crawford
Keyword(s):  
Manufacturing Systems ◽  
Reconfigurable Manufacturing ◽  
Planning And Scheduling ◽  
Model Based ◽  
Planning And Control ◽  
Resource Reasoning ◽  
On Line ◽  
Scheduling Heuristic ◽  
High Level ◽  
And Control

A recent trend in intelligent machines and manufacturing has been toward reconfigurable manufacturing systems, which move away from the idea of a fixed factory line executing an unchanging set of operations, and toward the goal of an adaptable factory structure. The logical next challenge in this area is that of on-line reconfigurability. With this capability, machines can reconfigure while running, enable or disable capabilities in real time, and respond quickly to changes in the system or the environment (including faults). We propose an approach to achieving on-line reconfigurability based on a high level of system modularity supported by integrated, model-based planning and control software. Our software capitalizes on many advanced techniques from the artificial intelligence research community, particularly in model-based domain-independent planning and scheduling, heuristic search, and temporal resource reasoning. We describe the implementation of this design in a prototype highly modular, parallel printing system.

scholarly journals A Fast Integrated Planning and Control Framework for Autonomous Driving via Imitation Learning

2018 ◽  
Author(s):  
Liting Sun ◽  
Cheng Peng ◽  
Wei Zhan ◽  
Masayoshi Tomizuka
Keyword(s):  
Nonlinear Models ◽  
Autonomous Driving ◽  
Optimization Methods ◽  
Imitation Learning ◽  
Short Term ◽  
Model Based ◽  
Planning And Control ◽  
And Control ◽  
Optimal Driving

Safety and efficiency are two key elements for planning and control in autonomous driving. Theoretically, model-based optimization methods, such as Model Predictive Control (MPC), can provide such optimal driving policies. Their computational complexity, however, grows exponentially with horizon length and number of surrounding vehicles. This makes them impractical for real-time implementation, particularly when nonlinear models are considered. To enable a fast and approximately optimal driving policy, we propose a safe imitation framework, which contains two hierarchical layers. The first layer, defined as the policy layer, is represented by a neural network that imitates a long-term expert driving policy via imitation learning. The second layer, called the execution layer, is a short-term model-based optimal controller that tracks and further fine-tunes the reference trajectories proposed by the policy layer with guaranteed short-term collision avoidance. Moreover, to reduce the distribution mismatch between the training set and the real world, Dataset Aggregation is utilized so that the performance of the policy layer can be improved from iteration to iteration. Several highway driving scenarios are demonstrated in simulations, and the results show that the proposed framework can achieve similar performance as sophisticated long-term optimization approaches but with significantly improved computational efficiency.

Sign in / Sign up

Export Citation Format

Share Document