Applied AI Pod

Reinforcement Learning, Intelligent vehicles & Acquiring Data, with Praveen Palanisamy - AI Engineer Microsoft AI + Research, E15

Episode Summary

AI is here to solve real world and serious problems. In this episode we explore reinforcement learning applied to the automotive industry. We focus on autonomous systems and do a deep dive into data, challenges, methods to evaluate robustness of a solution, deploying into the real world and the role of simulators in training agents in this space. We're joined by Praveen Palanisamy, Senior AI Engineer in Autonomous Systems with Microsoft AI + Research. Praveen is working on developing the core end-to-end platform and services for real-world AI applications using Simulation, Reinforcement Learning and Machine Teaching. Prior to that, Praveen was an Autonomous Driving AI Researcher at General Motors R&D in Michigan, and he was also with the Robotics Institute, Carnegie Mellon University, where he worked on Autonomous Navigation, Perception and Artificial Intelligence Read more about Praveen's contributions in this space:

Episode Notes


  1. Deep Reinforcement Learning (DRL or DeepRL) applied to the automotive industry
  2. Simulation platforms and the role of simulators in training agents
  3. Obtaining data to prepare the autonomous vehicle
  4. Methods to evaluate robustness of the solution
  5. Deploying in real world
  6. Startups to use DL or be at the forefront of DL
  7. Techcrunch Disrupt Hackathon win & engineers at hackathons as a practice