Imperial College London
Portrait Picture

Professor Aldo Faisal

Faculty of Engineering, Department of Bioengineering

Professor of AI & Neuroscience
 
 
 
//

Contact

 

+44 (0)20 7594 6373a.faisal Website

 
 
//

Assistant

 

Miss Teresa Ng +44 (0)20 7594 8300

 
//

Location

 

4.08Royal School of MinesSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Beyret:2020:10.1109/IROS40897.2019.8968488,
author = {Beyret, B and Shafti, SA and Faisal, A},
doi = {10.1109/IROS40897.2019.8968488},
pages = {1--6},
publisher = {IEEE},
title = {Dot-to-dot: explainable hierarchical reinforcement learning for robotic manipulation},
url = {http://dx.doi.org/10.1109/IROS40897.2019.8968488},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Robotic systems are ever more capable of automationand fulfilment of complex tasks, particularly withreliance on recent advances in intelligent systems, deep learningand artificial intelligence in general. However, as robots andhumans come closer together in their interactions, the matterof interpretability, or explainability of robot decision-makingprocesses for the human grows in importance. A successfulinteraction and collaboration would only be possible throughmutual understanding of underlying representations of theenvironment and the task at hand. This is currently a challengein deep learning systems. We present a hierarchical deepreinforcement learning system, consisting of a low-level agenthandling the large actions/states space of a robotic systemefficiently, by following the directives of a high-level agent whichis learning the high-level dynamics of the environment and task.This high-level agent forms a representation of the world andtask at hand that is interpretable for a human operator. Themethod, which we call Dot-to-Dot, is tested on a MuJoCo-basedmodel of the Fetch Robotics Manipulator, as well as a ShadowHand, to test its performance. Results show efficient learningof complex actions/states spaces by the low-level agent, and aninterpretable representation of the task and decision-makingprocess learned by the high-level agent.
AU  - Beyret,B
AU  - Shafti,SA
AU  - Faisal,A
DO  - 10.1109/IROS40897.2019.8968488
EP  - 6
PB  - IEEE
PY  - 2020///
SN  - 2153-0866
SP  - 1
TI  - Dot-to-dot: explainable hierarchical reinforcement learning for robotic manipulation
UR  - http://dx.doi.org/10.1109/IROS40897.2019.8968488
UR  - https://ieeexplore.ieee.org/document/8968488
UR  - http://hdl.handle.net/10044/1/72142
ER  -
Download