Search Results for author: Songan Zhang

Found 7 papers, 3 papers with code

Dream to Adapt: Meta Reinforcement Learning by Latent Context Imagination and MDP Imagination

no code implementations11 Nov 2023 Lu Wen, Songan Zhang, H. Eric Tseng, Huei Peng

Meta reinforcement learning (Meta RL) has been amply explored to quickly learn an unseen task by transferring previously learned knowledge from similar tasks.

Meta Reinforcement Learning

A Hybrid Partitioning Strategy for Backward Reachability of Neural Feedback Loops

no code implementations14 Oct 2022 Nicholas Rober, Michael Everett, Songan Zhang, Jonathan P. How

We introduce a hybrid partitioning method that uses both target set partitioning (TSP) and backreachable set partitioning (BRSP) to overcome a lower bound on estimation error that is present when using BRSP.

Improved Robustness and Safety for Pre-Adaptation of Meta Reinforcement Learning with Prior Regularization

no code implementations19 Aug 2021 Lu Wen, Songan Zhang, H. Eric Tseng, Baljeet Singh, Dimitar Filev, Huei Peng

The performance of PEARL$^+$ is validated by solving three safety-critical problems related to robots and AVs, including two MuJoCo benchmark problems.

Autonomous Vehicles Decision Making +1

Quick Learner Automated Vehicle Adapting its Roadmanship to Varying Traffic Cultures with Meta Reinforcement Learning

1 code implementation18 Apr 2021 Songan Zhang, Lu Wen, Huei Peng, H. Eric Tseng

It is essential for an automated vehicle in the field to perform discretionary lane changes with appropriate roadmanship - driving safely and efficiently without annoying or endangering other road users - under a wide range of traffic cultures and driving conditions.

Meta Reinforcement Learning reinforcement-learning +1

Monocular 3D Vehicle Detection Using Uncalibrated Traffic Cameras through Homography

1 code implementation29 Mar 2021 Minghan Zhu, Songan Zhang, Yuanxin Zhong, Pingping Lu, Huei Peng, John Lenneman

This paper proposes a method to extract the position and pose of vehicles in the 3D world from a single traffic camera.

Driving-Policy Adaptive Safeguard for Autonomous Vehicles Using Reinforcement Learning

no code implementations2 Dec 2020 Zhong Cao, Shaobing Xu, Songan Zhang, Huei Peng, Diange Yang

This paper proposes a driving-policy adaptive safeguard (DPAS) design, including a collision avoidance strategy and an activation function.

Autonomous Vehicles Collision Avoidance +2

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