Imperial College London
Alternate

ProfessorMirkoKovac

Faculty of Engineering, Department of Aeronautics

Professor in Aerial Robotics
 
 
 
//

Contact

 

+44 (0)20 7594 5063m.kovac Website

 
 
//

Location

 

326City and Guilds BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Kocer:2021,
author = {Kocer, B and Hady, A and Kandath, H and Pratama, M and Kovac, M},
pages = {110--116},
publisher = {IEEE},
title = {Deep neuromorphic controller with dynamic topology for aerial robots},
url = {http://hdl.handle.net/10044/1/88763},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Current  aerial  robots  are  increasingly  adaptive; they  can  morph  to  enable  operation  in  changing  conditions  to complete diverse missions. Each mission may require the robot to  conduct  a  different  task.  A  conventional  learning  approach can  handle  these  variations  when  the  system  is  trained  for similar tasks in a representative environment. However, it may result  in  overfitting  to  the  new  data  stream  or  the  failure to  adapt,  leading  to  degradation  or  a  potential  crash.  These problems  can  be  mitigated  with  an  excessive  amount  of  data and  embedded  model,  but  the  computational  power  and  the memory  of  the  aerial  robots  are  limited.  In  order  to  address the  variations  in  the  model,  environment  as  well  as  the  tasks within  onboard  computation  limitations,  we  propose  a  deep neuromorphic  controller  approach  with  variable  topologies  to handle  each  different  condition  and  the  data  stream  with  a feasible  computation  and  memory  allocation.  The  proposed approach is based on a deep neuromorphic (multi and variable layered  neural  network)  controller  with  dynamic  depth  and progressive  layer  adaptation  for  each  new  data  stream.  This adaptive  structure  is  combined  with  a  switching  function  to form a sliding mode controller. The network parameter update rule  guarantees  the  stability  of  the  closed  loop  system  by the  convergence  of  the  error  dynamics  to  the  sliding  surface. Being   the   first   implementation   on   an   aerial   robot   in   this context, the results illustrate the adaptation capability, stability, computational  efficiency  as  well  as  the  real-time  validation.
AU  - Kocer,B
AU  - Hady,A
AU  - Kandath,H
AU  - Pratama,M
AU  - Kovac,M
EP  - 116
PB  - IEEE
PY  - 2021///
SP  - 110
TI  - Deep neuromorphic controller with dynamic topology for aerial robots
UR  - http://hdl.handle.net/10044/1/88763
ER  -
Download