no code implementations • 26 Mar 2024 • Ke Guo, Zhenwei Miao, Wei Jing, Weiwei Liu, Weizi Li, Dayang Hao, Jia Pan
Due to the covariate shift issue, existing imitation learning-based simulators often fail to generate stable long-term simulations.
2 code implementations • 21 Nov 2023 • Bibek Poudel, Weizi Li, Kevin Heaslip
To address this, we introduce a reinforcement learning based RV that employs a congestion stage classifier to optimize the safety, efficiency, and stability of mixed traffic.
no code implementations • 20 Nov 2023 • Michael Villarreal, Dawei Wang, Jia Pan, Weizi Li
With at least 30% RVs, CO and HC emissions are reduced by up to 42% and 43%, respectively.
no code implementations • 30 Oct 2023 • Bing Wang, Weizi Li, Anthony Bradlow, Antoni T. Y. Chan, Eghosa Bazuaye
But in practice, blood testing data is not always available at the point of referrals, so we need methods to leverage multimodal data such as semi-structured and unstructured data for early detection of IA.
1 code implementation • 13 Jun 2023 • Michael Villarreal, Bibek Poudel, Weizi Li
However, defining objectives of RL agents in traffic control and management tasks, as well as aligning policies with these goals through an effective formulation of Markov Decision Process (MDP), can be challenging and often require domain experts in both RL and ITS.
1 code implementation • 14 Apr 2023 • Ryan Wickman, Bibek Poudel, Michael Villarreal, Xiaofei Zhang, Weizi Li
This can be rectified by Quality-Diversity (QD) algorithms, where a population of high-quality and diverse solutions to a problem is preferred.
no code implementations • 17 Feb 2023 • Michael Villarreal, Bibek Poudel, Jia Pan, Weizi Li
In certain scenarios, our approach even outperforms using precision observations, e. g., up to 8% increase in average vehicle velocity in the merge environment, despite only using local traffic information as opposed to global traffic information.
1 code implementation • 12 Jan 2023 • Dawei Wang, Weizi Li, Lei Zhu, Jia Pan
In contrast, without RVs, congestion starts to develop when the traffic demand reaches as low as 200 vehicles per hour.
no code implementations • 22 May 2022 • Michael Villarreal, Bibek Poudel, Ryan Wickman, Yu Shen, Weizi Li
As a result of increasingly adopted machine learning algorithms and ubiquitous sensors, many 'perception-to-control' systems are developed and deployed.
1 code implementation • 2 Dec 2021 • Ryan Wickman, Xiaofei Zhang, Weizi Li
The interconnectedness and interdependence of modern graphs are growing ever more complex, causing enormous resources for processing, storage, communication, and decision-making of these graphs.
no code implementations • NeurIPS 2021 • Yu Shen, Laura Zheng, Manli Shu, Weizi Li, Tom Goldstein, Ming Lin
We introduce a simple yet effective framework for improving the robustness of learning algorithms against image corruptions for autonomous driving.
1 code implementation • 22 Nov 2021 • Lei Lin, Weizi Li, Lei Zhu
For instance, our model reduces MAE by 25. 3%, RMSE by 29. 2%, and MAPE by 20. 2%, compared to the state-of-the-art Diffusion Convolutional Recurrent Neural Network (DCRNN) model using the hourly dataset.
1 code implementation • 17 Oct 2021 • Bibek Poudel, Weizi Li
While the prediction accuracy of deep learning models is high, these models' robustness has raised many safety concerns, given that imperceptible perturbations added to input can substantially degrade the model performance.
no code implementations • 29 Sep 2021 • Ryan Wickman, Xiaofei Zhang, Weizi Li
Multi-task learning (MTL) is a field involved with learning multiple tasks simultaneously typically through using shared model parameters.
no code implementations • 10 Aug 2021 • Lahari Karadla, Weizi Li
The COVID-19 pandemic has resulted in significant social and economic impacts throughout the world.
no code implementations • 31 Jul 2021 • Bibek Poudel, Thomas Watson, Weizi Li
Autonomous micromobility has been attracting the attention of researchers and practitioners in recent years.
no code implementations • 26 Feb 2021 • Yu Shen, Laura Zheng, Manli Shu, Weizi Li, Tom Goldstein, Ming C. Lin
For safety of autonomous driving, vehicles need to be able to drive under various lighting, weather, and visibility conditions in different environments.
no code implementations • 1 Jan 2021 • Yu Shen, Laura Yu Zheng, Manli Shu, Weizi Li, Tom Goldstein, Ming Lin
To ensure the wide adoption and safety of autonomous driving, the vehicles need to be able to drive under various lighting, weather, and visibility conditions in different environments.
no code implementations • 19 Apr 2020 • Weizi Li, Jan M. Allbeck
Seemingly since the inception of virtual humans, there has been an effort to make their behaviors more natural and human-like.