Prof Emma Hart E.Hart@napier.ac.uk
Professor
Autonomous Robot Evolution: Cradle to Grave
People Involved
Project Description
Robotics is changing the landscape of innovation. But traditional design approaches are not suited to novel or unknown habitats and contexts, for instance: robot colonies for ore mining, exploring or developing other planets or asteroids, or robot swarms for monitoring extreme environments on Earth. New design methodologies are needed that support optimising robot behaviour under different conditions for different purposes. It is accepted that behaviour is determined by a combination of the body (morphology, hardware) and the mind (controller, software). Embodied AI and morphological computing have made major progress in engineering artificial agents (i.e., robots) by focusing on the links between morphology and intelligence of natural agents (i.e., animals). While such a holistic body-mind approach has been hailed for its merits, we still lack an actual pathway to achieve this.
While this goal is ambitious, it is achievable by introducing a unique methodology: a hybridisation of the physical evolutionary system with a virtual one. On the one hand, it is appreciated that an effective design methodology requires the use and testing of physical robots. This is because simulations are prone to hidden biases, errors and simplifications in the underlying models. Simulating populations of robots (rather than just simulating specific parts) leads to accumulated errors and a lack of physical plausibility: the evolved designs will not work in the real system. This is the notorious reality gap of evolutionary robotics. On the other hand, evolving everything in hardware is time and resource consuming. One of our major innovations is to run simulated evolution concurrently with the physical and hybridise them by cross-breeding, where a physical and a virtual robot can parent a child that may be born in the real world, in the virtual world or in both. The advantages of such a hybrid system are significant. Physical evolution is accelerated by the virtual component that can run faster to find good robot features with less time and resources; simulated evolution benefits from the influx of genes that are tested favourably in the real world. Furthermore, monitoring of and feedback from the physical system can improve the simulator, reducing the reality gap.
Project Acronym | ARE |
---|---|
Status | Project Complete |
Funder(s) | Engineering and Physical Sciences Research Council |
Value | £366,412.00 |
Project Dates | Aug 1, 2018 - Dec 31, 2022 |
You might also like
Life Long Learning Hyper Heuristic Optimisation Oct 1, 2012 - Dec 31, 2015
This project aims to improve the current state of the art in developing optimisation tools which are relevant and acceptable to industry.
This will be achieved by addressing industrial current concerns regarding the ability of academic optimisatio...
Read More about Life Long Learning Hyper Heuristic Optimisation.
FOCAS Jan 1, 2013 - Feb 28, 2016
FOCAS is a coordination action in the area of collective adaptive systems. It provides increased visibility to the research carried out by projects funded by the FOCAS FET Proactive Initiative and others in research fields related to collective adapt...
Read More about FOCAS.
Ensembles for Optimisation Sep 1, 2015 - Aug 31, 2016
Optimisation – finding cost-effective or high-performing solutions - is a key economic driver for business today. However, academic literature on search-based optimisation techniques reflects an escalating arms race to produce highly specialized algo...
Read More about Ensembles for Optimisation.
An Investigation of Hyper-Heuristic Methods: A New Generation of Problems-Solvers Nov 1, 2000 - Jul 31, 2004
The project made significant advances in discovering new automated methods for combining heuristics to solve bin-packing problems, outperforming results obtained by any individual heuristic.
Advances were made using learning classifier systems and...
Read More about An Investigation of Hyper-Heuristic Methods: A New Generation of Problems-Solvers.
SIGNAL Oct 1, 2001 - Dec 31, 2004
This is an EU-funded research project to develop basic methodologies and principles of systemic intelligence for artefacts such as robots that will be capable of steadily growing their knowledge through continued experience. The project involves four...
Read More about SIGNAL.