no code implementations • 15 Jan 2025 • Weizhen Wang, Chenda Duan, Zhenghao Peng, Yuxin Liu, Bolei Zhou
Vision Language Models (VLMs) demonstrate significant potential as embodied AI agents for various mobility applications.
no code implementations • 12 Jan 2025 • Ziyang Xie, Zhizheng Liu, Zhenghao Peng, Wayne Wu, Bolei Zhou
Sim-to-real gap has long posed a significant challenge for robot learning in simulation, preventing the deployment of learned models in the real world.
no code implementations • 26 Sep 2024 • Zhenghao Peng, Wenjie Luo, Yiren Lu, Tianyi Shen, Cole Gulino, Ari Seff, Justin Fu
A major challenge in autonomous vehicle research is modeling agent behaviors, which has critical applications including constructing realistic and reliable simulations for off-board evaluation and forecasting traffic agents motion for onboard planning.
no code implementations • 13 Jun 2024 • Yunsong Zhou, Michael Simon, Zhenghao Peng, Sicheng Mo, Hongzi Zhu, Minyi Guo, Bolei Zhou
In this work, we introduce a simulator-conditioned scene generation framework called SimGen that can learn to generate diverse driving scenes by mixing data from the simulator and the real world.
no code implementations • 15 Jan 2024 • Mingxin Huang, Dezhi Peng, Hongliang Li, Zhenghao Peng, Chongyu Liu, Dahua Lin, Yuliang Liu, Xiang Bai, Lianwen Jin
In this paper, we propose a new end-to-end scene text spotting framework termed SwinTextSpotter v2, which seeks to find a better synergy between text detection and recognition.
no code implementations • 19 Oct 2023 • Linrui Zhang, Zhenghao Peng, Quanyi Li, Bolei Zhou
Driving safety is a top priority for autonomous vehicles.
no code implementations • 3 Mar 2023 • Zhenghai Xue, Zhenghao Peng, Quanyi Li, Zhihan Liu, Bolei Zhou
Assuming optimal, the teacher policy has the perfect timing and capability to intervene in the learning process of the student agent, providing safety guarantee and exploration guidance.
1 code implementation • 31 May 2022 • Quanyi Li, Zhenghao Peng, Haibin Wu, Lan Feng, Bolei Zhou
Inspired by the neuroscience approach to investigate the motor cortex in primates, we develop a simple yet effective frequency-based approach called \textit{Policy Dissection} to align the intermediate representation of the learned neural controller with the kinematic attributes of the agent behavior.
1 code implementation • 5 Apr 2022 • Qihang Zhang, Zhenghao Peng, Bolei Zhou
Specifically, we train an inverse dynamic model with a small amount of labeled data and use it to predict action labels for all the YouTube video frames.
2 code implementations • CVPR 2022 • Mingxin Huang, Yuliang Liu, Zhenghao Peng, Chongyu Liu, Dahua Lin, Shenggao Zhu, Nicholas Yuan, Kai Ding, Lianwen Jin
End-to-end scene text spotting has attracted great attention in recent years due to the success of excavating the intrinsic synergy of the scene text detection and recognition.
Ranked #3 on
Text Spotting
on Inverse-Text
no code implementations • ICLR 2022 • Quanyi Li, Zhenghao Peng, Bolei Zhou
HACO can train agents to drive in unseen traffic scenarios with a handful of human intervention budget and achieve high safety and generalizability, outperforming both reinforcement learning and imitation learning baselines with a large margin.
1 code implementation • NeurIPS 2021 • Zhenghao Peng, Quanyi Li, Ka Ming Hui, Chunxiao Liu, Bolei Zhou
Self-Driven Particles (SDP) describe a category of multi-agent systems common in everyday life, such as flocking birds and traffic flows.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
1 code implementation • 13 Oct 2021 • Zhenghao Peng, Quanyi Li, Chunxiao Liu, Bolei Zhou
Offline RL technique is further used to learn from the partial demonstration generated by the expert.
2 code implementations • 26 Sep 2021 • Quanyi Li, Zhenghao Peng, Lan Feng, Qihang Zhang, Zhenghai Xue, Bolei Zhou
Based on MetaDrive, we construct a variety of RL tasks and baselines in both single-agent and multi-agent settings, including benchmarking generalizability across unseen scenes, safe exploration, and learning multi-agent traffic.
no code implementations • 9 Jul 2021 • Hao Sun, Ziping Xu, Meng Fang, Zhenghao Peng, Jiadong Guo, Bo Dai, Bolei Zhou
Safe exploration is crucial for the real-world application of reinforcement learning (RL).
2 code implementations • 26 Dec 2020 • Quanyi Li, Zhenghao Peng, Qihang Zhang, Chunxiao Liu, Bolei Zhou
We validate that training with the increasing number of procedurally generated scenes significantly improves the generalization of the agent across scenarios of different traffic densities and road networks.
no code implementations • 14 Jun 2020 • Zhenghao Peng, Hao Sun, Bolei Zhou
Conventional Reinforcement Learning (RL) algorithms usually have one single agent learning to solve the task independently.
1 code implementation • 21 May 2020 • Hao Sun, Zhenghao Peng, Bo Dai, Jian Guo, Dahua Lin, Bolei Zhou
In problem-solving, we humans can come up with multiple novel solutions to the same problem.
no code implementations • 25 Sep 2019 • Hao Sun, Bo Dai, Jiankai Sun, Zhenghao Peng, Guodong Xu, Dahua Lin, Bolei Zhou
In this work we model the social influence into the scheme of reinforcement learning, enabling the agents to learn both from the environment and from their peers.
2 code implementations • 27 Jul 2018 • Zhenghao Peng, Xuyang Chen, Chengwen Xu, Naifeng Jing, Xiaoyao Liang, Cewu Lu, Li Jiang
To guarantee the approximation quality, existing works deploy two neural networks (NNs), e. g., an approximator and a predictor.
no code implementations • 23 May 2018 • Zhuoran Song, Ru Wang, Dongyu Ru, Hongru Huang, Zhenghao Peng, Jing Ke, Xiaoyao Liang, Li Jiang
In this paper, we propose the Approximate Random Dropout that replaces the conventional random dropout of neurons and synapses with a regular and predefined patterns to eliminate the unnecessary computation and data access.