1 code implementation • 11 Jul 2022 • Dooseop Choi, Kyoungwook Min
We observe that a similar problem, in which the generated trajectory is located between adjacent lanes, often arises in VAE-based trajectory forecasting models.
1 code implementation • 8 Jul 2020 • Dooseop Choi, Seung-jun Han, Kyoungwook Min, Jeongdan Choi
To achieve autonomous driving without high-definition maps, we present a model capable of generating multiple plausible paths from egocentric images for autonomous vehicles.
1 code implementation • 10 Jul 2019 • Dooseop Choi, Kyoungwook Min, Jeongdan Choi
We train the networks of the proposed model to produce a future trajectory, which is the closest to the true trajectory, while maximizing a reward from a reward function.
no code implementations • 6 Sep 2018 • Dooseop Choi, Taeg-Hyun An, Kyounghwan Ahn, Jeongdan Choi
In this paper, we present a transfer learning method for the end-to-end control of self-driving cars, which enables a convolutional neural network (CNN) trained on a source domain to be utilized for the same task in a different target domain.