ROAR Spring 2022 Seminar (2/18) – Reinforcement Learning

Abstract: In this week’s ROAR Seminar, the Berkeley Reinforcement Learning team will present the latest results in training an end-to-end autonomous driving agent using neural networks to directly control a vehicle’s steering and breaking. The talk will start by giving an introduction to basic reinforcement learning setting to play Atari games, and will also cover techniques to make the training of autonomous driving agent more efficient for the robot control applications.

ROAR Spring 2022 Seminar (1/28) – The Indy Autonomous Challenge  – a global autonomous competition with a $1.5 million dollar prize. — How University of Hawai’i, UCSD, and UC Berkeley students teamed up to go toe to toe with 9 international teams.

Abstract:

What happens when your code controls a race car at 100mph? The AI Racing Tech team has been pushing these boundaries…

Imagine The Dallara AV-21 rounds the lap breaking 100mph, you can hear the direct mount engine roar past in a precision turn as your high level controls algorithms execute perfectly. The team’s lidar processing algorithms work with the GPS data bounding the track edges as a keep out zone. You stand with the pitt-crew on the edge of the track holding your breath watching across multiple monitors with the rest of the team as you approach the passing zone to overtake the competition. At this point it’s all strategy, your team’s software is everything…  

The first history making IAC was held on Oct. 23, 2021 at the Indianapolis Motor Speedway where 21 universities from 9 countries forming 9 teams competed for the $1 million grand prize, in October of 2021.

Indy Autonomous Challenge global university teams returned to action at CES in January of 2022 when they competed at the Las Vegas Motor Speedway in the first high-speed, head-to-head autonomous racecar competition IAC showcase.

The IAC taps into the power of incentive prize competitions to inspire the best and brightest in universities worldwide to eliminate barriers to innovation, overcome complex challenges, and increase public awareness of the transformational impact that automation can have to improve vehicle safety and performance.

This Friday the UC Berkeley members Chris Battista, Cake Deng, and C.K. Wolfe will talk about their race experience, the challenges, recruiting, and what it will take to prepare for October 2022 to race again.