Learning to Drive a Real Car in 20 Minutes
By Martin A. Riedmiller, Michael Montemerlo, Hendrik Dahlkamp. 2007
102 citations recorded by the source corpus.
Subfields: Automotive Engineering, Control and Systems Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Automotive Engineering
- Edouard Leurent
- Pieter Abbeel
- Sergey Levine
- Sascha Lange
- Thomas Gabel
- Maksym Semikin
- Wolfram Burgard
- Alex Bewley
In Control and Systems Engineering
- Sergey Levine
- Pieter Abbeel
- Martin A. Riedmiller
- Chelsea Finn
- Wolfram Burgard
- Sascha Lange
- Edouard Leurent
- Roland Hafner
Citations in the corpus
- BADGR: An Autonomous Self-Supervised Learning-Based Navigation System (2020, background): “…learning navigation policies directly from real-world experience, but typically require a person [18], [21] or SLAM algorithm [22] to gather the data, assume access to the ground-truth robot state [23], learn using low-bandwidth sensors [24], or only perform collision avoidance [4], [25].”
- Learning to Drive in a Day (2018, background): “[25] who train a reinforcement learning agent which drives a vehicle to follow a GPS trajectory in an obstacle-free environment.”
- Learning driving styles for autonomous vehicles from demonstration (2015, background): “Riedmiller et al. [16] use reinforcement learning to learn a steering controller from scratch.”
- A Survey of End-to-End Driving: Architectures and Training Methods (2020, methodology): “[58] used an analytically derived steering controller for taking”
- Reinforcement learning for robot soccer (2009, background): “Some positive results of applying these methods to real-world problems already have been reported, for example naming steering an automobile (Riedmiller et al. 2007), controlling power systems (Wehenkel et al. 2005) and solving job-shop scheduling tasks (Gabel and Riedmiller 2007).”
- A Survey of State-Action Representations for Autonomous Driving (2018, methodology): “In (Riedmiller et al., 2007), the track-coordinate system is used to represent not only the vehicle’s position but also heading and yaw rate, which are relative the the lane curve heading and yaw rate at the projected position.”
- Batch Reinforcement Learning (2012, methodology): “This was the driving idea behind the proposal of Neural Fitted Q Iteration (NFQ, Riedmiller (2005)).”