SARAV

Systems and Architectures for Robotics and Autonomous Vehicles

SARAV is an undergraduate oriented research group that focuses on systems and architecture for robotics and autonomous vehicles. The group members are mainly from Georgia Tech undergraduate students and advised by Ramyad Hadidi (PhD candidate), Jiashen Cao (MS student) and Prof. Hyesoon Kim. The group belongs to HpArch group at Georgia Tech.

You can check our demos, publications, and a short description of previous/current projects below.

Spring'20 Demo Day

Fall'19 Demo Day

Summer'19 Demo Day

Demos

Publications

  • Quantifying the Design-Space Tradeoffs in Autonomous Drones [Paper]
    Ramyad Hadidi, Bahar Asgari, Sam Jijina, Adriana Amyette, Nima Shoghi, Hyesoon Kim
    International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), Detroit, MI (2021)

  • Secure Location-Aware Authentication and Communication for Intelligent Transportation Systems [Paper]
    Nima Shoghi Ghalehshahi, Ramyad Hadidi, Lee Jaewon, Jun Chen, Arthur Siqueria, Rahul Rajan, Shaan Dhawan, Pooya Shoghi Ghalehshahi, Hyesoon Kim
    arXiv preprint arXiv:2011.07092 (2020)

  • Understanding the Software and Hardware Stacks of a General-Purpose Cognitive Drone [Poster]
    Sam Jijina, Adriana Amyette, Nima Shoghi, Ramyad Hadidi, Hyesoon Kim
    IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), Boston, MA (2020)

  • Towards a General Purpose Cognitive Drone
    Sam Jijina, Adriana Amyette,, Ramyad Hadidi, Hyesoon Kim
    The Fourth Workshop on Cognitive Architectures (CogArch 2020), co-located with HPCA 2020, San Diego, CA (2020)

  • SLAM Performance on Embedded Robots [Paper]
    Nima Shoghi, Ramyad Hadidi, Hyesoon Kim
    Student Research Competition at Embedded System Week (SRC ESWEEK), New York, NY (2019)
    ACM SRC Bronze Winner

  • Enabling Speech to Text on Embedded Systems [Paper]
    Mohan Dodda, Taejoon Park, Sayuj Shajith, Ramyad Hadidi, Hyesoon Kim
    Student Research Competition at Embedded System Week (SRC ESWEEK), New York, NY (2019)

  • Capella: Customizing Perception for Edge Devices by Efficiently Allocating FPGAs to DNNs [Demo Site] [Slides] [Paper]
    Younmin Bae, Ramyad Hadidi, Bahar Asgari, Jiashen Cao, Hyesoon Kim
    International Conference on Field-Programmable Logic and Applications (FPL), Demo, Barcelona, Spain (2019)

  • Characterizing the Execution of Deep Neural Networks on Collaborative Robots and Edge Devices [Slides] [Paper]
    Matthew Merck, Bingyao Wang, Lixing Liu, Chunjun Jia, Arthur Siqueira, Qiusen Huang, Abhijeet Saraha, Dongsuk Lim, Jiashen Cao, Ramyad Hadidi, Hyesoon Kim
    ACM Practice and Experience in Advanced Research Computing (PEARC), Chicago, IL (2019)

  • Understanding the Power Consumption of Executing Deep Neural Networks on a Distributed Robot System [Slides] [Paper]
    Ramyad Hadidi, Jiashen Cao, Matthew Merck, Arthur Siqueira, Qiusen Huang, Abhijeet Saraha, Chunjun Jia, Bingyao Wang, Dongsuk Lim, Lixing Liu and Hyesoon Kim
    Algorithms and Architectures for Learning in-the-Loop Systems in Autonomous Flight Workshop - Co-located with IEEE International Conference on Robotics and Automation (ICRA), Montreal, QC (2019)

  • An Edge-Centric Scalable Intelligent Framework To Collaboratively Execute DNN [Demo Site] [Paper]
    Jiashen Cao, Fei Wu, Ramyad Hadidi, Lixing Liu, Tushar Krishna, Micheal S. Ryoo, Hyesoon Kim
    Conference on Systems and Machine Learning (SysML), Demo Palo Alto, CA (2019)

Admin Members

How To Apply

Please fill out the this form if you are interested in working with us. We usually start working with new members every semester. If you want to get credits for your research, here are the forms (please confirm with us first): CS Form ECE Form

Collaborative RobotsRobots collabrate together to achieve a single goal

Connected CarsAn Autonomous Vehicles Oriented Project

DroneStarting a Raspberry-Pi-based Drone for Future Projects

FPGA-Based RoboticImplementing Robotics on Custom Hardware

KlaubaGreeting Robot Helping Visitors Navigate Klaus