Transferring Autonomous Driving Knowledge on Simulated and Real Intersections

By David Isele, Akansel Cosgun. 2017

23 citations recorded by the source corpus.

We view intersection handling on autonomous vehicles as a reinforcement learning problem, and study its behavior in a transfer learning setting. We show that a network trained on one type of intersection generally is not able to generalize to other intersections. However, a network that is pre-trained on one intersection and fine-tuned on another performs better on the new task compared to training in isolation. This network also retains knowledge of the prior task, even though some forgetting occurs. Finally, we show that the benefits of fine-tuning hold when transferring simulated intersection handling knowledge to a real autonomous vehicle.

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

In Automotive Engineering

Citations in the corpus

Deep Reinforcement Learning for Autonomous Driving: A Survey (2020, background): “Authors in [131] transferred policies learnt to handle simulated intersections to real world examples between DQN agents.”
Selective Experience Replay for Lifelong Learning (2018, background): “The Sumo simulator (Krajzewicz et al. 2012) allows for the creation of a variety of different driving tasks with varying levels of difﬁculty, many of which beneﬁt from transfer while being sufﬁciently different that adaptation is necessary for good performance (Isele and Cosgun 2017).”