Conditional Imitation learning is a common and effective approach to train autonomous driving agents. However, two issues limit the full potential of this approach: (i) the inertia problem, a special case of causal confusion where the agent mistakenly correlates low speed with no acceleration, and (ii) low correlation between offline and online performance due to the accumulation of small errors that brings the agent in a previously unseen state. Both issues are critical for state-aware models, yet informing the driving agent of its internal state as well as the state of the environment is of crucial importance. In this article we propose a multi-task learning agent based on a multi-stage vision transformer with state token propagation. We feed the state of the vehicle along with the representation of the environment as a special token of the transformer and propagate it throughout the network. This allows us to tackle the aforementioned issues from different angles: guiding the driving policy with learned stop/go information, performing data augmentation directly on the state of the vehicle and visually explaining the model's decisions. We report a drastic decrease in inertia and a high correlation between offline and online metrics.
Addressing Limitations of State-Aware Imitation Learning for Autonomous Driving
IEEE Transactions on Intelligent Vehicles ; 9 , 1 ; 2946-2955
2024-01-01
9735740 byte
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Addressing Limitations of State-Aware Imitation Learning for Autonomous Driving
BASE | 2024
|Imitation Learning for Autonomous Vehicle Driving: How Does the RepresentationMatter?
British Library Conference Proceedings | 2022
|