Sumeet Batra

Sumeet Batra

PhD Candidate in Machine Learning, Robotics

University of Southern California Robotics Embedded Systems Laboratory

Biography

I am a PhD candidate at the University of Southern California advised by Gaurav Sukhatme in the Robotics Embedded Systems Laboratory (RESL). I’m interested in creating intelligent systems following neuroscientific perspectives on intelligence. That is, agents that learn predictive models of the world that learn from and actively seek out surprising or novel experiences. In the past I’ve worked on Reinforcement Learning (RL), improving exploration in RL via Quality Diversity / Novelty Search methods, and generative models for robot planning and control. I’m currently working on biologically plausible learning algorithms to create more robust and truly generalizable models deployable on real robots.

Over the past two summers, I’ve had the immense privilege of working with the Autonomous Vehicles team at NVIDIA as a research scientist intern on Reinforcement Learning and Diffusion generative models for automatic scenario generation. Before that, I was an intern at the National Institute of Standards and Technology (NIST), where I worked on Generative Adversarial Networks for generating realistic 4G LTE signals.

Interests
  • Reinforcement Learning
  • Novelty Search
  • Generative World Models (predictive coding, diffusion models)
  • Neuroscience and NeuroAI
Education
  • PhD Candidate, in progress

    University of Southern California

  • BSc in Computer Science, Minor in Applied Mathematics, 2020

    University of Colorado Boulder

Experience

 
 
 
 
 
NVIDIA
Research Scientist Intern - Autonomous Driving
NVIDIA
May 2023 – August 2023 Seattle
I worked on generating diverse and realistic traffic scenarios using Diffusion generative models and Quality Diversity optimization. The diffusion model was trained on egocentric collected real driving data. We investigated using Differentiable Quality Diversity to further improve the realism and diversity of the generated scenarios, for example by varying the accelerations of the agents and the number of lane changes made in the scenario.
 
 
 
 
 
NVIDIA
Research Scientist Intern - Autonomous Driving
NVIDIA
May 2022 – September 2020 California
I developed a fast, parallelized reinforcement learning framework for simulating different driving scenarios with high sample throughput. In addition, I implemented the AV team’s learned prediction and planning pipeline in NVIDIA DriveSim, which was demoed at CVPR'23.

Contact