AutoRally: An Open Platform for Aggressive Autonomous Driving

By Brian Goldfain, Paul Drews, Changxi You, Matthew Barulic, Orlin D. Velev, Panagiotis Tsiotras, James M. Rehg. 2019

122 citations recorded by the source corpus.

The technical challenge of creating a self-driving vehicle remains an open problem despite significant advancements from universities, car manufacturers, and technology companies. Full autonomy, known as level 5 (see "Society of Automotive Engineers Levels of Driving Automation"), is defined as full-time performance by an automated driving system of all aspects of the dynamic driving task under all roadway and environmental conditions that can be managed by a human driver. It is estimated that level 5 autonomous vehicles on public roads will help eliminate more than 90% [1] of the 35,000 annual traffic fatalities caused by human error in the United States [2]; reduce commute time, road congestion, and pollution; and increase driving resource utilization [3].

Subfields: Artificial Intelligence, Automotive Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Evangelos A. Theodorou
2. Sergey Levine
3. Byron Boots
4. James M. Rehg
5. Ching-An Cheng
6. Paul Drews
7. Brian Goldfain
8. Grady Williams

In Automotive Engineering

1. Keuntaek Lee
2. Evangelos A. Theodorou
3. Byron Boots
4. Ching-An Cheng
5. Kamil Saigol

Citations in the corpus

• Ensemble Bayesian Decision Making with Redundant Deep Perceptual Control Policies (2018, neutral): “Left: The AutoRally [9] vehicle for autonomous driving and racing.”
• Autonomous Vehicles on the Edge: A Survey on Autonomous Vehicle Racing (2022, unknown): “A special version of an autonomous small-scale vehicle is the so called AutoRally [66] vehicle, a 1:5 scale autonomous racecar developed by a team of researchers from Giorgia Tech.”
• An Online Learning Approach to Model Predictive Control (2019, methodology): “1) Platform Description: We use the autonomous AutoRally platform [13] to run a high-speed driving task on a dirt track, with the goal of the task to achieve as low a lap time as possible.”
• Information-Theoretic Model Predictive Control: Theory and Applications to Autonomous Driving (2017, background): “5) is an electric autonomous vehicle testbed 1/5 the size of a full-scale car that is designed to be robust, safe, and easy to use [38].”
• Early Failure Detection of Deep End-to-End Control Policy by Reinforcement Learning (2019, methodology): “Here, we demonstrate the success of our framework on the autonomous navigation and obstacle avoidance task using the simulator provided by the AutoRally project [19].”