Abhishek Vivekanandan

Abhishek Vivekanandan

Research Fellow at FZI Forschungszentrum Informatik

Karlsruhe Institute of Technology


As a Research Fellow at Forschung Zentrum Informatik, I am working on projects aimed at overcoming challenges in the deployment of automated vehicles. My focus is on ensuring safety, which is a crucial aspect of deployment and a significant hurdle in achieving provable safety. I am experienced in developing and implementing deterministic characteristics that conform to industry standards, to ensure the safe and successful deployment of automated vehicles at scale.

  • Machine Learning
  • Highly Automated Driving
  • Perception and Motion Systems
  • Automotive Software Systems
  • Safety for Automated Vehicles
  • PhD in Artificial Intelligence, 2019 - Present

    Karlsruhe Institute of Technology

  • MSc in Computer Science, 2018

    Technische Universität Chemnitz, Germany

  • B.Eng in Electronics and Instrumentation Engineering, 2015

    Anna University, India


Research Scientist
Jan 2019 – Present Karlsruhe,Germany

Working towards functional safety and conformance aspects of deploying Neural Networks for Autonomous Driving applications.

  • Developed motion prediction model for actors in the ego space using LIDAR and HD maps information through sensor fusion architecture.
  • Current Resarch focuses towards developing Neural Network architecture to constraint the outputs of motion prediction model via kinematic and environmental priors.
Volkswagen AG
Master Thesis
Volkswagen AG
Jan 2018 – Oct 2018 Wolfsburg, Germany

Model Uncertainty estimation on Semantic Segmentation Network with a real time deployment on Nvidia Drive PX2 for Autonomous Vehicles.

  • Parallelization of MC Dropouts for real time sampling of Uncertainty.
  • Custom layer optimization of Network model using TensorRT optimizer.
  • Deployment of optimized model into Drive PX2 for real time segmentation.
Volkswagen AG
Volkswagen AG
Jun 2017 – Jan 2018 Wolfsburg, Germany

Worked on,

  • Design of Segmentation Network architectures for Deep Neural Network.
  • Development of training Pipeline for DNN using TensorFlow.
  • Uncertainty Estimation of DNN models resulting in a boost in performance of the pixel wise classification accuracy.
  • Benchmarking of IBM cluster GPUs for training performance evaluation.

Recent Publications

Quickly discover relevant content by filtering publications.
(2023). KI-PMF: Knowledge Integrated Plausible Motion Forecasting.


(2022). Plausibility Verification for 3d Object Detectors Using Energy-based Optimization. ECCVW 2022.

PDF Cite Video

(2022). Knowledge Augmented Machine Learning with Applications in Autonomous Driving.

PDF Cite