| EPSRC Reference: |
EP/D054419/1 |
| Title: |
Lifelong Adaptation and Failure Recovery by Evolutionary Computation for Multiple Heterogeneous Robots |
| Principal Investigator: |
Wilson, Dr MS |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Computer Science |
| Organisation: |
Aberystwyth University |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
01 October 2006 |
Ends: |
30 June 2010 |
Value (£): |
223,359
|
| EPSRC Research Topic Classifications: |
| Artificial Intelligence |
Robotics & Autonomy |
|
| EPSRC Industrial Sector Classifications: |
| No relevance to Underpinning Sectors |
|
|
| Related Grants: |
|
| Panel History: |
| Panel Date | Panel Name | Outcome |
|
16 Nov 2005
|
Engineering Systems
|
Deferred
|
|
|
Summary on Grant Application Form |
|
The need for autonomy in the area of mobile robotics is increasing. With more applications relating to areas where robots may be out of contact for extended periods of time (such as during planetary or geographically remote earth-based exploration tasks), it is becoming increasingly important that they continue to work effectively and autonomously adapt to different environments without performing inappropriate actions which could jeopardise the robot or its surroundings. Multi-robot teams consisting of heterogeneous robots offer several advantages over single robots or homogeneous groups. These include the ability to use their individual capabilities to deal with a more diverse set of tasks, to complete a task when an individual robot fails through its own degradation, or to take over a task if environmental changes mean that the original robot assigned to the task can no longer perform it.This proposal envisions a multiple, heterogeneous robot system that is able to operate without external assistance for an extended period of time. The system should be able to identify when a robot has degraded and is unable to complete a task. The task can then be reallocated to another robot with a similar competence. Where the environment has changed and the robot is no longer appropriate for the task, this should be recognised and the task reassigned to another robot and the original robot reassigned elsewhere.This proposal intends using genetic and evolutionary computation (GEC) methods to achieve the above adaptation and failure recognition. GEC algorithms are a biologically inspired method of optimisation and search based on the concept of natural selection. Although GECs have been applied to the design of robots and their controllers in the past, they have rarely been applied to the problem of lifelong optimisation and adaptation of robots in dynamic environments. This proposal aims to use a GEC training phase to develop robot behaviour for diverse environments, and to determine whether different robots have the ability to perform specific tasks, and at what stage the robots fail within a particular environment. Using simulation for the training phase allows a faster, safer, evolution than on a real robot, then running these optimised chromosomes on a physical robot with lifelong evolutionary adaptation allows grounding in the real world. As multiple robots provide redundancy, and heterogeneous robots provide an ability to perform a wider range of tasks, this proposal intends to use a group of robots with different sensory and manipulation capabilities, and different control strategies to function together to achieve tasks in circumstances where an individual robot may fail, or where homogeneous robots may not have the capability to deal with a changed environment or task. Lifelong adaptation using GEC will be used to deal with limited changes in the environment. Determining at the training phase how well individual robots perform within specific environments can provide information as to which robots may be able to take over from a robot which has failed at a task due to its own degradation.
|
|
Key Findings |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Potential use in non-academic contexts |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Impacts |
|
| Description |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk |
| Summary |
|
| Date Materialised |
|
|
|
|
Sectors submitted by the Researcher |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
| Project URL: |
|
| Further Information: |
|
| Organisation Website: |
http://www.aber.ac.uk |