What is Autonomous Racing?

No driver, just software. Driverless vehicles, autonomous go-karts, and the vehicles of tomorrow. Autonomous racing is the ultimate engineering challenge. The driver is replaced with a variety of sensors that act as the eyes and ears of the vehicle, feeding the data to a control algorithm that students develop and tune.  Machine learning (artificial intelligence) is often used to interpret sensor data.

The official vehicle of the Indy Autonomous Challenge is the Dallara-built AV-21 which has been retrofitted with hardware and controls to enable automation. The Dallara AV-21 chassis is a modified version of the Indy Lights chassis. 

Driverless – Pure Software

Autonomous racing eliminates a driver and replaces him with a variety of sensors that act as the eyes and ears of the vehicle.  Generally, the sensors are taking in lots and lots of vehicle and environment information and processing the data, and sending important command information to the control algorithm. It's within the control algorithm that the autonomous racecar uses where it is on the road, what is around it, and what path it should be following next! 

The software can be broken down into three main areas first is the "Control" the Low-level hardware controller of the steering, braking, gear shifting, and accelerator. second is "Localization" using GP, IMU fusion, Kalman filtering, and pose estimation. The third is "Perception" using LIDAR and other sensor ingest, fusion, filtering, and world state estimation. 

Ultimate Engineering Challenge

The challenge of developing a vehicle that races autonomously adds a multitude of unique requirements for students to take into account when tuning a control algorithm.  The biggest and most important challenge is the fact that, unlike a normal vehicle whose speed rarely exceeds 80 mph on a public road, a race car can go upwards of 200 mph!

 This is all accomplished by using 3 Luminar Hydra LiDAR pushing out 64 Lines and a 60-degree scanning window,  2 Novatel GPS with millimeter accuracy, 6 high definition wide-field cameras, 3 RADARs located on both sides and the front of the car, and a State-of-the -rt GPU and processing computer. 

It's because of these high speeds and mass amounts of data that students must carefully interpret sensor data in order to create the most efficient control algorithm, as a race car at a top speed of 200mph can travel about 90m or 293ft a second!

Vehicles of Tomorrow

Self-driving vehicles will revolutionize the way we all travel and perceive our infrastructure for transportation.  Autonomous Technology merges robotics, machine learning, engineering, and modern software development methods! 

When all of this comes together, it pushes the boundaries of consumer technology. Developing a racecar that can stop or avoid a collision going 200mph, makes road vehicle algorithms that much more robust. Adding a huge margin of safety to consumer autonomous vehicles that would otherwise never be developed! 

Under the Hood of Autonomous Racing: In-Depth Insights from Our Students and Team Leads

“The approach we’re using is best described as neuro-symbolic AI, a hybrid version becoming more common for increasing the robustness of AI in many industries,” ...“The idea is you feed in neural inputs into a mostly rule- and structure-based algorithm, and that enhances its robustness. The main advantage of this approach is it’s no longer a huge black box where we don’t know why something different than what we expected came out. Since the core decision making aspect of our data pipeline is rule-based, we can see the input and know what’s coming out, because we coded it.”  - Sid Saha Senior Technical team Lead & Planning Team Lead

"The essence of controls lies in their ability to adapt swiftly to ever-changing system dynamics. Our cutting-edge research focuses on optimizing runtime and speed, ensuring that our autonomous systems not only navigate complex environments but also do so with precision and efficiency. Our team employs advanced learning methods that enable us to quickly adapt to evolving system dynamics, ensuring mathematical convergence and real-time exploration of past trajectories. This approach not only guarantees safety but also fuels continuous learning from the environment" - Haoru Xue Senior Technical team Lead & Controls Team Lead

“To ensure the utmost safety in the future of autonomous vehicles, it is absolutely crucial that we deliberately push to the absolute limit” .. “Pioneering research involves finding and understanding weaknesses in the system, and Constantly improving and advancing engineering techniques.” .. “In this competition, we are operating on a unique cutting edge of autonomous research, unlike anything else in the world right now.” 

"While developing autonomous systems, we meticulously balance real-world testing with extensive simulation training, data generation and iterative testing. For every hour we spend in real-world scenarios, we dedicate at least 100 hours to simulations, ensuring that our technology is thoroughly tested, refined, and ready to meet the challenges of the road ahead." - C.K. Wolfe Simulation Team Lead

Join the Movement and Help Create the Vehicles of Tomorrow!