Adaptive Perception Control for Aerial Robots with Twin Delayed DDPG

Veera Venkata Ram Murali Krishna Rao Muvva, Kunjan Theodore Joseph, Kruttidipta Samal, Marilyn Wolf, Santosh Pitla

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Robotic perception is commonly assisted by convo-lutional neural networks. However, these networks are static in nature and do not adjust to changes in the environment. Additionally, these are computationally complex and impose latency in inference. We propose an adaptive perception system that changes in response to the robot's requirements. The perception controller has been designed using a recently proposed reinforcement learning technique called Twin Delayed DDPG (TD3). Our proposed method outperformed the baseline approaches.

Original languageEnglish (US)
Title of host publication2024 Design, Automation and Test in Europe Conference and Exhibition, DATE 2024 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350348590
StatePublished - 2024
Event2024 Design, Automation and Test in Europe Conference and Exhibition, DATE 2024 - Valencia, Spain
Duration: Mar 25 2024Mar 27 2024

Publication series

NameProceedings -Design, Automation and Test in Europe, DATE
ISSN (Print)1530-1591

Conference

Conference2024 Design, Automation and Test in Europe Conference and Exhibition, DATE 2024
Country/TerritorySpain
CityValencia
Period3/25/243/27/24

Keywords

  • Closed loop systems
  • Control Systems
  • Deep Learning
  • Drone
  • Neural Networks
  • UAS
  • UAV

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Adaptive Perception Control for Aerial Robots with Twin Delayed DDPG'. Together they form a unique fingerprint.

Cite this