research:projects

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
research:projects [2017/09/14 17:22]
Simon Haller
research:projects [2017/11/11 13:03] (current)
Justus Piater
Line 1: Line 1:
 ====== Externally-Funded,​ Collaborative Projects ====== ====== Externally-Funded,​ Collaborative Projects ======
  
-===== Current ​EU Projects =====+===== Current Projects =====
  
-{{:​research:​imagine-transparent.svg?​nolink&​200 ||}}[[https://​www.imagine-h2020.eu|IMAGINE ​Robots Understanding Their Actions by Imagining Their Effects ​]] (EU H20202017-2020): seeks to enable robots to understand the structure ​of their environment and how it is affected by its actions“Understanding” here means the ability ​of the robot (a) to determine ​the applicability ​of an action along with parameters to achieve the desired effectand (b) to discern ​to what extent an action succeeded, and to infer possible causes ​of failure ​and generate recovery actions.+{{:​research:​flexrop-logo.png?​nolink&​200 ||}}[[https://​www.profactor.at/​en/​research/​industrial-assistive-systems/​roboticassistance/​projects/​flexrop/​|FlexRoP ​Flexible, assistive robot for customized production]] (FFG (Austria) ICT of the Future2016-2018): Production ​of mass customized products ​is not easy to automate since objects and object positions remain more uncertain compared to mass production scenariosUncertainty handling motivates ​the application of advanced sensor-based control strategies which increases system complexity ​of robot applications dramatically. A possible solution ​to this conflict is the concept ​of task level or skill based programming that will render modern robot systems. Such systems can be applied without safety fenceare easier ​to programmore applicable ​and transformable into capable robot assistants. The project will implement a skill based programming framework and will apply it on selected industrial demo scenarios and evaluate research results. The main focus of the project is the application of methods to acquire process information by worker monitoring ​and thus make the robot assistants self-learning.
  
 <​html>​ <​html>​
Line 9: Line 9:
 </​html>​ </​html>​
  
-{{:​research:​squirrel.png?​nolink&​200 |}}[[http://www.squirrel-project.eu/|SQUIRREL]] (EU FP7-ICT-STREP2014-2018): Clutter in an open world is a challenge for many aspects ​of robotic systems, especially for autonomous robots deployed in unstructured domestic settings, affecting navigation, manipulation,​ vision, human robot interaction ​and planning ​SQUIRREL addresses these issues by actively controlling clutter and incrementally learning to extend ​the robot'​s capabilities while doing so. We term this the B3 (bit by bitapproach, as the robot tackles clutter one bit at a time and also extends its knowledge continuously as new bits of information become available. ​ SQUIRREL is inspired by a user driven scenario, that exhibits all the rich complexity required to convincingly drive research, but allows tractable solutions ​with high potential for exploitation. We propose a toy cleaning scenario, where a robot learns ​to collect toys scattered in loose clumps or tangled heaps on the floor in a child'​s room, and to stow them in designated target locations.+{{:​research:​imagine-transparent.png?​nolink&​200 ​||}}[[https://www.imagine-h2020.eu|IMAGINE - Robots Understanding Their Actions by Imagining Their Effects ​]] (EU H20202017-2020): seeks to enable robots to understand the structure ​of their environment ​and how it is affected by its actions“Understanding” here means the ability of the robot (ato determine ​the applicability ​of an action along with parameters ​to achieve ​the desired effect, and (b) to discern to what extent an action succeeded, and to infer possible causes of failure and generate recovery actions.
  
 <​html>​ <​html>​
Line 15: Line 15:
 </​html>​ </​html>​
  
-{{:​research:​3rdhand.png?​nolink&​110 |3rdHand}} +{{:​research:​squirrel.png?​nolink&​200 |}}[[http://​www.squirrel-project.eu/|SQUIRREL]] (EU FP7-ICT-STREP, ​2014-2018): Clutter in an open world is challenge for many aspects ​of robotic systemsespecially ​for autonomous robots deployed in unstructured domestic settings, affecting navigation, manipulation,​ vision, human robot interaction and planning ​SQUIRREL addresses these issues by actively controlling clutter and incrementally learning to extend ​the robot's capabilities while doing so. We term this the B3 (bit by bit) approachas the robot tackles clutter one bit at time and also extends its knowledge continuously as new bits of information become available. ​ SQUIRREL ​is inspired by a user driven scenario, that exhibits all the rich complexity required ​to convincingly drive researchbut allows tractable solutions with high potential for exploitation. We propose a toy cleaning scenario, where a robot learns to collect toys scattered in loose clumps or tangled heaps on the floor in a child'​s room, and to stow them in designated target locations. 
-[[http://3rdhandrobot.eu/|3rdHand]] (EU FP7-ICT-STREP, ​2013-2017develops a semi-autonomous robot assistant that acts as third hand of a human worker. It will be straightforward to instruct even by an untrained layman workerallow for efficient knowledge transfer between tasksand enable effective collaboration between a human worker with a robot third handThe main contributions of this project will be the scientific principles of semi-autonomous human-robot collaboration, a new semi-autonomous robotic system that is able to (i) learn cooperative tasks from demonstration(ii) learn from instruction, and (iii) transfer knowledge between tasks and environments.+
 <​html>​ <​html>​
 <div style="​clear:​both"><​br></​div>​ <div style="​clear:​both"><​br></​div>​
Line 23: Line 23:
  
 ===== Completed Projects (Selection) ===== ===== Completed Projects (Selection) =====
 +
 +{{:​research:​3rdhand.png?​nolink&​110 |3rdHand}}
 +[[http://​3rdhandrobot.eu/​|3rdHand]] (EU FP7-ICT-STREP,​ 2013-2017) develops a semi-autonomous robot assistant that acts as a third hand of a human worker. It will be straightforward to instruct even by an untrained layman worker, allow for efficient knowledge transfer between tasks, and enable effective collaboration between a human worker with a robot third hand. The main contributions of this project will be the scientific principles of semi-autonomous human-robot collaboration,​ a new semi-autonomous robotic system that is able to (i) learn cooperative tasks from demonstration,​ (ii) learn from instruction,​ and (iii) transfer knowledge between tasks and environments.
 +<​html>​
 +<div style="​clear:​both"><​br></​div>​
 +</​html>​
  
 {{:​research:​pacman_logo2.png?​nolink&​110 |PaCMan}} [[http://​www.pacman-project.eu/​|PaCMan]] (EU FP7-ICT-STREP,​ 2013-2016) advances methods for object perception, representation and manipulation so that a robot is able to robustly manipulate objects even when those objects are unfamiliar, and even though the robot has unreliable perception and action. The proposal is founded on two assumptions. The first of these is that the representation of the object'​s shape in particular and of other properties in general will benefit from being compositional (or very loosely hierarchical and part based). The second is that manipulation planning and execution benefits from explicitly reasoning about uncertainty in object pose, shape etcetera; how it changes under the robot'​s actions, and the robot should plan actions that not only achieve the task, but gather information to make task achievement more reliable. {{:​research:​pacman_logo2.png?​nolink&​110 |PaCMan}} [[http://​www.pacman-project.eu/​|PaCMan]] (EU FP7-ICT-STREP,​ 2013-2016) advances methods for object perception, representation and manipulation so that a robot is able to robustly manipulate objects even when those objects are unfamiliar, and even though the robot has unreliable perception and action. The proposal is founded on two assumptions. The first of these is that the representation of the object'​s shape in particular and of other properties in general will benefit from being compositional (or very loosely hierarchical and part based). The second is that manipulation planning and execution benefits from explicitly reasoning about uncertainty in object pose, shape etcetera; how it changes under the robot'​s actions, and the robot should plan actions that not only achieve the task, but gather information to make task achievement more reliable.
research/projects.1505402563.txt.gz · Last modified: 2017/09/14 17:22 by Simon Haller