Search Results for author: Yue Meng

Found 14 papers, 3 papers with code

Signal Temporal Logic Neural Predictive Control

no code implementations10 Sep 2023 Yue Meng, Chuchu Fan

We conduct experiments on six tasks, where our method with the backup policy outperforms the classical methods (MPC, STL-solver), model-free and model-based RL methods in STL satisfaction rate, especially on tasks with complex STL specifications while being 10X-100X faster than the classical methods.

Model Predictive Control Reinforcement Learning (RL)

Hybrid Systems Neural Control with Region-of-Attraction Planner

no code implementations18 Mar 2023 Yue Meng, Chuchu Fan

For each system mode, we first learn an NN Lyapunov function and an NN controller to ensure the states within the region of attraction (RoA) can be stabilized.

Model Predictive Control Reinforcement Learning (RL)

ConBaT: Control Barrier Transformer for Safe Policy Learning

no code implementations7 Mar 2023 Yue Meng, Sai Vemprala, Rogerio Bonatti, Chuchu Fan, Ashish Kapoor

In this work, we propose Control Barrier Transformer (ConBaT), an approach that learns safe behaviors from demonstrations in a self-supervised fashion.

Imitation Learning Model Predictive Control

Case Studies for Computing Density of Reachable States for Safe Autonomous Motion Planning

no code implementations16 Sep 2022 Yue Meng, Zeng Qiu, Md Tawhid Bin Waez, Chuchu Fan

Recent work provides a data-driven approach to compute the density distribution of autonomous systems' forward reachable states online.

Autonomous Driving Density Estimation +2

Decentralized Coordinated State Estimation in Integrated Transmission and Distribution Systems

no code implementations8 Nov 2021 Ying Zhang, Yanbo Chen, Jianhui Wang, Yue Meng, Tianqiao Zhao

Current transmission and distribution system states are mostly unobservable to each other, and state estimation is separately conducted in the two systems owing to the differences in network structures and analytical models.

Reactive and Safe Road User Simulations using Neural Barrier Certificates

1 code implementation14 Sep 2021 Yue Meng, Zengyi Qin, Chuchu Fan

Reactive and safe agent modelings are important for nowadays traffic simulator designs and safe planning applications.

Imitation Learning User Simulation

Learning Density Distribution of Reachable States for Autonomous Systems

no code implementations14 Sep 2021 Yue Meng, Dawei Sun, Zeng Qiu, Md Tawhid Bin Waez, Chuchu Fan

State density distribution, in contrast to worst-case reachability, can be leveraged for safety-related problems to better quantify the likelihood of the risk for potentially hazardous situations.

Localization and Mapping using Instance-specific Mesh Models

no code implementations8 Mar 2021 Qiaojun Feng, Yue Meng, Mo Shan, Nikolay Atanasov

We show that the errors between projections of the mesh model and the observed keypoints and masks can be differentiated in order to obtain accurate instance-specific object shapes.


VA-RED$^2$: Video Adaptive Redundancy Reduction

no code implementations ICLR 2021 Bowen Pan, Rameswar Panda, Camilo Fosco, Chung-Ching Lin, Alex Andonian, Yue Meng, Kate Saenko, Aude Oliva, Rogerio Feris

An inherent property of real-world videos is the high correlation of information across frames which can translate into redundancy in either temporal or spatial feature maps of the models, or both.

Effects of impulsive harvesting and an evolving domain in a diffusive logistic model

no code implementations22 Dec 2020 Yue Meng, Zhigui Lin, Michael Pedersen

In order to understand how the combination of domain evolution and impulsive harvesting affect the dynamics of a population, we propose a diffusive logistic population model with impulsive harvesting on a periodically evolving domain.

Analysis of PDEs

AR-Net: Adaptive Frame Resolution for Efficient Action Recognition

1 code implementation ECCV 2020 Yue Meng, Chung-Ching Lin, Rameswar Panda, Prasanna Sattigeri, Leonid Karlinsky, Aude Oliva, Kate Saenko, Rogerio Feris

Specifically, given a video frame, a policy network is used to decide what input resolution should be used for processing by the action recognition model, with the goal of improving both accuracy and efficiency.

Action Recognition

Learning 3D-aware Egocentric Spatial-Temporal Interaction via Graph Convolutional Networks

no code implementations20 Sep 2019 Chengxi Li, Yue Meng, Stanley H. Chan, Yi-Ting Chen

First, we decompose egocentric interactions into ego-thing and ego-stuff interaction, modeled by two GCNs.

Novel Concepts

Cannot find the paper you are looking for? You can Submit a new open access paper.