H2020 MSCA Innovative Training Network for the research on Advanced Hardware/Software Components for Integrated/Embedded Vision Systems

ESR6: UC

Methods for autonomous navigation and localization in traffic environments

@ Instituto de Sistemas e Robótica (Universidade de Coimbra), Portugal

The objectives of the research activities are the development of algorithms for obstacle detection, visual odometry and “partial slam” for autonomous navigation and localization in traffic scenarios. In particular the development will be carried out taking into account the specific architectures developed in WP3, WP4 and WP5. The methods that will be developed consider multiple constraints, namely power consumption and fault tolerance. The algorithms will exploit the sensor and computational redundancy adjusting their methods to a real-time adaptive evaluation of the environment and conditions. The use of 3D and 2D data will be exploited by combining their complementary nature and the topology of the network.

Gopi Krishna Erabati

 

BIOGRAPHY

Gopi is currently an Early Stage Researcher (ESR) and a doctoral student at Institute of Systems and Robotics (ISR), University of Coimbra, Coimbra, Portugal. He holds a bachelor's degree in Electronics and Instrumentation Engineering from Kakatiya University, Warangal, India in 2013 and a master's degree in Computer Vision from Université de Bourgogne, Le Creusot, France in 2018. He worked as a Junior Research Fellow at Defence Research and Development Organization, India during 2014-2016. He did master's thesis at Laboratoire d'Analyse et d'Architecture des Systèmes (LAAS-CNRS), Toulouse, France in 2018. His research interests include computer vision, machine learning, visual perception, visual-SLAM.

  gopi.erabati@uc.pt

   linkedin.com/in/gopi231091

Host

     

Secondment

         

    MY PROJECT

"Methods for autonomous navigation and localization in traffic environments"

TASK

Development of algorithms for obstacle detection, visual odometry and “partial slam” for autonomous navigation and   localization in traffic scenarios. The methods that will be developed consider multiple constraints, namely power consumption and fault tolerance. The algorithms will exploit the sensor and computational redundancy adjusting their methods to a real-time adaptive evaluation of the environment and conditions. The use of 3D and 2D data will be exploited by combining their complementary nature and the topology of the network.

 

EXPECTED RESULTS

A set of algorithms for dynamic obstacle detection, visual odometry and partial slam and their evaluation and  implementation in the architectures developed in ACHIEVE. The ESR will acquire complementary competences in fault tolerant and distributed algorithms as well as computer vision.