Summary
Industry and society are increasingly automating processes, which requires solving constrained optimisation problems. This includes vehicle routing problems in transportation, scheduling of tasks in electricity demand-response programs, rostering of personnel and more. However, the solutions found by state-of-the-art constraint programming solvers are often found to not match user expectations. Solutions
are regularly critiqued by domain experts as impractical, frustrating for people involved or creating unfair situations that a human planner would never propose. As a result, the technology is not accepted or workarounds like manual processing is done which reduces its potential.
This project is based on the idea that we must shift away from the concept of the optimal solution, and must move to that of the desired solution. To make the solutions more humane, we must make the solution process more human-aware. The key to this is to integrate techniques from machine learning that can learn about the context of the environment and user.
This can move the problem formulation process from a one-shot model + solve paradigm to a dialogue-based conversation paradigm between the end-user and the solver. The focus here is not on the use of natural language, but rather on making the constrained programming technology ready for such interactions. This project aims to fundamentally advance it on three fronts:
1) to learn from the environment and integrate the learning and the predictive models into the optimisation;
2) to learn the implicit preferences form the user by letting her/him interact with the solutions; and ultimately
3) to develop a conversational constraint solver that can answer unambiguous questions of the users in terms of explanations and alternatives.
The end goal is a system that lets the user co-create a solution that she/he desires, and that system can adapt to changing needs and preferences over time.
are regularly critiqued by domain experts as impractical, frustrating for people involved or creating unfair situations that a human planner would never propose. As a result, the technology is not accepted or workarounds like manual processing is done which reduces its potential.
This project is based on the idea that we must shift away from the concept of the optimal solution, and must move to that of the desired solution. To make the solutions more humane, we must make the solution process more human-aware. The key to this is to integrate techniques from machine learning that can learn about the context of the environment and user.
This can move the problem formulation process from a one-shot model + solve paradigm to a dialogue-based conversation paradigm between the end-user and the solver. The focus here is not on the use of natural language, but rather on making the constrained programming technology ready for such interactions. This project aims to fundamentally advance it on three fronts:
1) to learn from the environment and integrate the learning and the predictive models into the optimisation;
2) to learn the implicit preferences form the user by letting her/him interact with the solutions; and ultimately
3) to develop a conversational constraint solver that can answer unambiguous questions of the users in terms of explanations and alternatives.
The end goal is a system that lets the user co-create a solution that she/he desires, and that system can adapt to changing needs and preferences over time.
Unfold all
/
Fold all
More information & hyperlinks
| Web resources: | https://cordis.europa.eu/project/id/101002802 |
| Start date: | 01-06-2021 |
| End date: | 31-05-2026 |
| Total budget - Public funding: | 1 893 125,00 Euro - 1 893 125,00 Euro |
Cordis data
Original description
Industry and society are increasingly automating processes, which requires solving constrained optimisation problems. This includes vehicle routing problems in transportation, scheduling of tasks in electricity demand-response programs, rostering of personnel and more. However, the solutions found by state-of-the-art constraint programming solvers are often found to not match user expectations. Solutionsare regularly critiqued by domain experts as impractical, frustrating for people involved or creating unfair situations that a human planner would never propose. As a result, the technology is not accepted or workarounds like manual processing is done which reduces its potential.
This project is based on the idea that we must shift away from the concept of the optimal solution, and must move to that of the desired solution. To make the solutions more humane, we must make the solution process more human-aware. The key to this is to integrate techniques from machine learning that can learn about the context of the environment and user.
This can move the problem formulation process from a one-shot model + solve paradigm to a dialogue-based conversation paradigm between the end-user and the solver. The focus here is not on the use of natural language, but rather on making the constrained programming technology ready for such interactions. This project aims to fundamentally advance it on three fronts:
1) to learn from the environment and integrate the learning and the predictive models into the optimisation;
2) to learn the implicit preferences form the user by letting her/him interact with the solutions; and ultimately
3) to develop a conversational constraint solver that can answer unambiguous questions of the users in terms of explanations and alternatives.
The end goal is a system that lets the user co-create a solution that she/he desires, and that system can adapt to changing needs and preferences over time.
Status
SIGNEDCall topic
ERC-2020-COGUpdate Date
27-04-2024
Images
No images available.
Geographical location(s)
