Agile Autonomous Driving using End-to-End Deep Imitation Learning
Open accessAbstract
We present an end-to-end imitation learning system for agile, off-road autonomous driving using only low-cost on-board sensors.By imitating a model predictive controller equipped with advanced sensors, we train a deep neural network control policy to map raw, high-dimensional observations to continuous steering and throttle commands.Compared with recent approaches to similar tasks, our method requires neither state estimation nor on-the-fly planning to navigate the vehicle.Our approach relies on, and experimentally validates, recent imitation learning theory.Empirically, we show that policies trained with online imitation learning overcome well-known challenges related to covariate shift and generalize better than policies trained with batch imitation learning.Built on these insights, our autonomous driving system demonstrates successful high-speed off-road driving, matching the state-of-the-art performance.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
IL using real-world demonstration data has become one of the most popular and robust control algorithms in research and industry.
“In this era, IL using real-world demonstration data has become one of the most popular and robust control algorithms in research and industry [59,60].”
From Data-Driven Robotic Manipulation of Cloth-like Deformable Objects: The Present, Challenges and Future Prospects (2023) · cites this paper as [59]
The Introduction and Data Collection sections describe imitation learning from expert demonstrations collected on a real-world driving track. They support its use as a control approach in this research study, but do not establish that it is among the most popular or robust algorithms across research and industry. (LLM, conf=0.83)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 35 · Cited by 257
Research works printed but not linked: 3
- A René Geist, Andreas Hansen, Eugen Solowjow, Shun Yang, and Edwin Kreuzer. Data collection for robust end- to-end lateral vehicle control. In ASME 2017 Dynamic Systems and Control Conference, pages V001T45A007- V001T45A007. American Society of Mechanical Engi- neers, 2017.
- Urs Muller, Jan Ben, Eric Cosatto, Beat Flepp, and Yann L Cun. Off-road obstacle avoidance through end- to-end learning. In Advances in Neural Information Processing Systems, pages 739-746, 2006.
- Dean A Pomerleau. Alvinn: An autonomous land vehicle in a neural network. In Advances in Neural Information Processing Systems, pages 305-313, 1989.
- Authors
- Pan, Y., Cheng, C.-A., Saigol, K., Lee, K., Yan, X., Theodorou, E., & Boots, B.
- Affiliations
- Georgia Institute of Technology (US)
- Venue
- Robotics: Science and Systems XIV
- Published
- 2018-06-26
- OpenAlex
- W2806163172
- Cited by
- 257
- References
- 35
- Citations by year
- 2026: 6 · 2025: 21 · 2024: 26 · 2023: 26 · 2022: 43 · 2021: 61 · 2020: 38 · 2019: 33 · 2018: 3
- FWCI
- 34.39
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Robotics: Science and Systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1637758, 1426945)
- Topics
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Engineering › Automotive Engineering › Vehicle Dynamics and Control Systems
- Keywords
- model predictive control, covariate shift, high-speed driving
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
