no code implementations • 7 Mar 2024 • Vindula Jayawardana, Sirui Li, Cathy Wu, Yashar Farid, Kentaro Oguchi
To address this, we introduce Multi-residual Task Learning (MRTL), a generic learning framework based on multi-task learning that, for a set of task scenarios, decomposes the control into nominal components that are effectively solved by conventional control methods and residual terms which are solved using learning.
no code implementations • 6 Feb 2023 • Zhengwei Bai, Guoyuan Wu, Matthew J. Barth, Yongkang Liu, Emrah Akin Sisbot, Kentaro Oguchi
A Dynamic Feature Sharing (DFS) methodology is introduced to support this CP system under certain constraints and a Random Priority Filtering (RPF) method is proposed to conduct DFS with high performance.
no code implementations • 14 Dec 2022 • Zhengwei Bai, Guoyuan Wu, Matthew J. Barth, Yongkang Liu, Emrah Akin Sisbot, Kentaro Oguchi
Utilizing the latest advances in Artificial Intelligence (AI), the computer vision community is now witnessing an unprecedented evolution in all kinds of perception tasks, particularly in object detection.
no code implementations • 21 Oct 2022 • Shiqi Liu, Mengdi Xu, Piede Huang, Yongkang Liu, Kentaro Oguchi, Ding Zhao
Continual reinforcement learning aims to sequentially learn a variety of tasks, retaining the ability to perform previously encountered tasks while simultaneously developing new policies for novel tasks.
no code implementations • 22 Aug 2022 • Zhengwei Bai, Guoyuan Wu, Matthew J. Barth, Yongkang Liu, Emrah Akin Sisbot, Kentaro Oguchi, Zhitong Huang
Perceiving the environment is one of the most fundamental keys to enabling Cooperative Driving Automation (CDA), which is regarded as the revolutionary solution to addressing the safety, mobility, and sustainability issues of contemporary transportation systems.
no code implementations • 29 Jun 2022 • Abdul Rahman Kreidieh, Yashar Farid, Kentaro Oguchi
The prevalence of high-speed vehicle-to-everything (V2X) communication will likely significantly influence the future of vehicle autonomy.
1 code implementation • 12 Mar 2022 • Zhengwei Bai, Guoyuan Wu, Matthew J. Barth, Yongkang Liu, Emrah Akin Sisbot, Kentaro Oguchi
3D object detection plays a fundamental role in enabling autonomous driving, which is regarded as the significant key to unlocking the bottleneck of contemporary transportation systems from the perspectives of safety, mobility, and sustainability.
no code implementations • 28 Feb 2022 • Zhensong Wei, Xuewei Qi, Zhengwei Bai, Guoyuan Wu, Saswat Nayak, Peng Hao, Matthew Barth, Yongkang Liu, Kentaro Oguchi
The current challenges of this solution are how to effectively combine different perception tasks into a single backbone and how to efficiently learn the spatiotemporal features directly from point cloud sequences.
no code implementations • 28 Feb 2022 • Zhengwei Bai, Saswat Priyadarshi Nayak, Xuanpeng Zhao, Guoyuan Wu, Matthew J. Barth, Xuewei Qi, Yongkang Liu, Emrah Akin Sisbot, Kentaro Oguchi
Object perception plays a fundamental role in Cooperative Driving Automation (CDA) which is regarded as a revolutionary promoter for the next-generation transportation systems.
no code implementations • 28 Jan 2022 • Zhengwei Bai, Guoyuan Wu, Xuewei Qi, Yongkang Liu, Kentaro Oguchi, Matthew J. Barth
Object detection plays a fundamental role in enabling Cooperative Driving Automation (CDA), which is regarded as the revolutionary solution to addressing safety, mobility, and sustainability issues of contemporary transportation systems.
no code implementations • 24 Jan 2022 • Zhengwei Bai, Guoyuan Wu, Xuewei Qi, Yongkang Liu, Kentaro Oguchi, Matthew J. Barth
In this study, a \textit{Cyber Mobility Mirror (CMM)} Co-Simulation Platform is designed for enabling CDA by providing authentic perception information.
1 code implementation • 19 Jun 2021 • Mengdi Xu, Peide Huang, Fengpei Li, Jiacheng Zhu, Xuewei Qi, Kentaro Oguchi, Zhiyuan Huang, Henry Lam, Ding Zhao
Evaluating rare but high-stakes events is one of the main challenges in obtaining reliable reinforcement learning policies, especially in large or infinite state/action spaces where limited scalability dictates a prohibitively large number of testing iterations.