File(s) under permanent embargo
Multi-modal feedback for affordance-driven interactive reinforcement learning
conference contribution
posted on 2018-01-01, 00:00 authored by F Cruz Naranjo, G I Parisi, S WermterInteractive reinforcement learning (IRL) extends traditional reinforcement learning (RL) by allowing an agent to interact with parent-like trainers during a task. In this paper, we present an IRL approach using dynamic audio-visual input in terms of vocal commands and hand gestures as feedback. Our architecture integrates multi-modal information to provide robust commands from multiple sensory cues along with a confidence value indicating the trustworthiness of the feedback. The integration process also considers the case in which the two modalities convey incongruent information. Additionally, we modulate the influence of sensory-driven feedback in the IRL task using goal-oriented knowledge in terms of contextual affordances. We implement a neural network architecture to predict the effect of performed actions with different objects to avoid failed-states, i.e., states from which it is not possible to accomplish the task. In our experimental setup, we explore the interplay of multi-modal feedback and task-specific affordances in a robot cleaning scenario. We compare the learning performance of the agent under four different conditions: Traditional RL, multi-modal IRL, and each of these two setups with the use of contextual affordances. Our experiments show that the best performance is obtained by using audio-visual feedback with affordance-modulated IRL. The obtained results demonstrate the importance of multi-modal sensory processing integrated with goal-oriented knowledge in IRL tasks.
History
Event
IEEE Computational Intelligence Society. Conference (2018 : Rio de Janeiro, Brazil)Series
IEEE Computational Intelligence Society ConferencePagination
1 - 8Publisher
Institute of Electrical and Electronics EngineersLocation
Rio de Janeiro, BrazilPlace of publication
Piscataway, N.J.Publisher DOI
Start date
2018-07-08End date
2018-07-13ISBN-13
9781509060146Language
engPublication classification
E1.1 Full written paper - refereedCopyright notice
2018, IEEEEditor/Contributor(s)
[Unknown]Title of proceedings
IJCNN 2018 : Proceedings of the 2018 International Joint Conference on Neural NetworksUsage metrics
Categories
No categories selectedKeywords
Robot sensing systemsTask analysisLearning (artificial intelligence)Speech recognitionComputer architectureNeural networksScience & TechnologyTechnologyComputer Science, Artificial IntelligenceComputer Science, Hardware & ArchitectureEngineering, Electrical & ElectronicComputer ScienceEngineeringROBOTICS
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC