DeFIX: Detecting and Fixing Failure Scenarios with Reinforcement Learning in Imitation Learning Based Autonomous Driving
October 29, 2022 ยท Entered Twilight ยท ๐ 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)
Repo contents: .gitignore, .gitmodules, LICENSE, README.md, carla, data, defix, figures, imitation-learning, leaderboard, reinforcement-learning, scenario_runner
Authors
Resul Dagdanov, Feyza Eksen, Halil Durmus, Ferhat Yurdakul, Nazim Kemal Ure
arXiv ID
2210.16567
Category
cs.RO: Robotics
Cross-listed
cs.AI,
cs.CV,
cs.LG
Citations
5
Venue
2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)
Repository
https://github.com/data-and-decision-lab/DeFIX
โญ 14
Last Checked
3 months ago
Abstract
Safely navigating through an urban environment without violating any traffic rules is a crucial performance target for reliable autonomous driving. In this paper, we present a Reinforcement Learning (RL) based methodology to DEtect and FIX (DeFIX) failures of an Imitation Learning (IL) agent by extracting infraction spots and re-constructing mini-scenarios on these infraction areas to train an RL agent for fixing the shortcomings of the IL approach. DeFIX is a continuous learning framework, where extraction of failure scenarios and training of RL agents are executed in an infinite loop. After each new policy is trained and added to the library of policies, a policy classifier method effectively decides on which policy to activate at each step during the evaluation. It is demonstrated that even with only one RL agent trained on failure scenario of an IL agent, DeFIX method is either competitive or does outperform state-of-the-art IL and RL based autonomous urban driving benchmarks. We trained and validated our approach on the most challenging map (Town05) of CARLA simulator which involves complex, realistic, and adversarial driving scenarios. The source code is publicly available at https://github.com/data-and-decision-lab/DeFIX
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Robotics
R.I.P.
๐ป
Ghosted
R.I.P.
๐ป
Ghosted
AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles
๐
๐
The Cartographer
A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehicles
๐
๐
The Cartographer
Unmanned Aerial Vehicles: A Survey on Civil Applications and Key Research Challenges
๐
๐
The Cartographer
A Survey of Autonomous Driving: Common Practices and Emerging Technologies
R.I.P.
๐ป
Ghosted