no code implementations • 26 Dec 2022 • Bumgeun Park, TaeYoung Kim, Woohyeon Moon, Luiz Felipe Vecchietti, Dongsoo Har
We propose a novel method that introduces a weighting factor for each experience when calculating the loss function at the learning stage.
no code implementations • 20 Nov 2022 • Praveen Kumar Rajendran, Quoc-Vinh Lai-Dang, Luiz Felipe Vecchietti, Dongsoo Har
In this paper, a domain adaptive training framework for absolute pose regression is introduced.
1 code implementation • 25 Feb 2022 • Sumit Mishra, Praveen Kumar Rajendran, Luiz Felipe Vecchietti, Dongsoo Har
To avoid accidents due to missing these visual cues, this paper proposes a visual notification of AP-features to drivers based on real-time images obtained via dashcam.
no code implementations • 25 Feb 2022 • Praveen Kumar Rajendran, Sumit Mishra, Luiz Felipe Vecchietti, Dongsoo Har
For proving texture invariance, we investigate the generalization of the proposed method augmenting the datasets to different scene styles, as ablation studies, using generative adversarial networks.
no code implementations • 13 Apr 2021 • TaeYoung Kim, Luiz Felipe Vecchietti, Kyujin Choi, Sanem Sariel, Dongsoo Har
Because these two training processes are conducted in a series in every timestep, agents can learn how to maximize role rewards and team rewards simultaneously.
Multi-agent Reinforcement Learning reinforcement-learning +2