Explanipedia

Sample-efficient Unsupervised Policy Cloning from Ensemble Self-supervised Labeled Videos Open

Xin Liu, Yaran Chen · 2024

Current advanced policy learning methodologies have demonstrated the ability to develop expert-level strategies when provided enough information. However, their requirements, including task-specific rewards, action-labeled expert trajector…

GAPartManip: A Large-scale Part-centric Dataset for Material-Agnostic Articulated Object Manipulation Open

Wenbo Cui, Chengyang Zhao, Songlin Wei, Jiazhao Zhang, Haoran Geng , et al. · 2024

Effectively manipulating articulated objects in household scenarios is a crucial step toward achieving general embodied artificial intelligence. Mainstream research in 3D vision has primarily focused on manipulation through depth perceptio…

PlanAgent: A Multi-modal Large Language Agent for Closed-loop Vehicle Motion Planning Open

Yupeng Zheng, Zebin Xing, Qichao Zhang, Bu Jin, Pengfei Li , et al. · 2024

Vehicle motion planning is an essential component of autonomous driving technology. Current rule-based vehicle motion planning methods perform satisfactorily in common scenarios but struggle to generalize to long-tailed situations. Meanwhi…

Learning Future Representation with Synthetic Observations for Sample-efficient Reinforcement Learning Open

Xin Liu, Yaran Chen, Dongbin Zhao · 2024

In visual Reinforcement Learning (RL), upstream representation learning largely determines the effect of downstream policy learning. Employing auxiliary tasks allows the agent to enhance visual representation in a targeted manner, thereby …

Advancing Object Goal Navigation Through LLM-enhanced Object Affinities Transfer Open

Mengying Lin, Yaran Chen, Dongbin Zhao, Zhaoran Wang · 2024

In object goal navigation, agents navigate towards objects identified by category labels using visual and spatial information. Previously, solely network-based methods typically rely on historical data for object affinities estimation, lac…

RoboGPT: an intelligent agent of making embodied long-term decisions for daily instruction tasks Open

Yaran Chen, Wenbo Cui, Yuanwen Chen, Mining Tan, Xinyao Zhang , et al. · 2023

Robotic agents must master common sense and long-term sequential decisions to solve daily tasks through natural language instruction. The developments in Large Language Models (LLMs) in natural language processing have inspired efforts to …

ComSD: Balancing Behavioral Quality and Diversity in Unsupervised Skill Discovery Open

Xin Liu, Yaran Chen, Dongbin Zhao · 2023

This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. Unsupervised skill discovery seeks to acquire different useful skills wit…

Multi-modal Learning based Prediction for Disease Open

Yaran Chen, Xueyu Chen, Yu Han, Haoran Li, Dongbin Zhao , et al. · 2023

Non alcoholic fatty liver disease (NAFLD) is the most common cause of chronic liver disease, which can be predicted accurately to prevent advanced fibrosis and cirrhosis. While, a liver biopsy, the gold standard for NAFLD diagnosis, is inv…

Cross-domain Random Pre-training with Prototypes for Reinforcement Learning Open

Xin Liu, Yaran Chen, Haoran Li, Boyu Li, Dongbin Zhao · 2023

This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. Unsupervised cross-domain Reinforcement Learning (RL) pre-training shows …

NeuronsGym: A Hybrid Framework and Benchmark for Robot Tasks with Sim2Real Policy Learning Open

Haoran Li, Shasha Liu, Mingjun Ma, Hu Guangzheng, Yaran Chen , et al. · 2023

The rise of embodied AI has greatly improved the possibility of general mobile agent systems. At present, many evaluation platforms with rich scenes, high visual fidelity and various application scenarios have been developed. In this paper…

BViT: Broad Attention based Vision Transformer Open

Nannan Li, Yaran Chen, Weifan Li, Zixiang Ding, Dongbin Zhao · 2022

Recent works have demonstrated that transformer can achieve promising performance in computer vision, by exploiting the relationship among image patches with self-attention. While they only consider the attention in a single feature layer,…

Stacked BNAS: Rethinking Broad Convolutional Neural Network for Neural Architecture Search Open

Zixiang Ding, Yaran Chen, Nannan Li, Dongbin Zhao · 2021

Different from other deep scalable architecture-based NAS approaches, Broad Neural Architecture Search (BNAS) proposes a broad scalable architecture which consists of convolution and enhancement blocks, dubbed Broad Convolutional Neural Ne…

ABCP: Automatic Block-wise and Channel-wise Network Pruning via Joint Search Open

Jiaqi Li, Haoran Li, Yaran Chen, Zixiang Ding, Nannan Li , et al. · 2021

Currently, an increasing number of model pruning methods are proposed to resolve the contradictions between the computer powers required by the deep learning models and the resource-constrained devices. However, most of the traditional rul…

MVM3Det: A Novel Method for Multi-view Monocular 3D Detection Open

Haoran Li, Zicheng Duan, Mingjun Ma, Yaran Chen, Jiaqi Li , et al. · 2021

Monocular 3D object detection encounters occlusion problems in many application scenarios, such as traffic monitoring, pedestrian monitoring, etc., which leads to serious false negative. Multi-view object detection effectively solves this …

BNAS: Efficient Neural Architecture Search Using Broad Scalable Architecture Open

Zixiang Ding, Yaran Chen, Nannan Li, Dongbin Zhao, Zhiquan Sun , et al. · 2021

Efficient neural architecture search (ENAS) achieves novel efficiency for learning architecture with high-performance via parameter sharing and reinforcement learning (RL). In the phase of architecture search, ENAS employs deep scalable ar…

Heuristic rank selection with progressively searching tensor ring network Open

Nannan Li, Yu Pan, Yaran Chen, Zixiang Ding, Dongbin Zhao , et al. · 2021

Recently, tensor ring networks (TRNs) have been applied in deep networks, achieving remarkable successes in compression ratio and accuracy. Although highly related to the performance of TRNs, rank selection is seldom studied in previous wo…

Heuristic Rank Selection with Progressively Searching Tensor Ring Network Open

Nannan Li, Yu Pan, Yaran Chen, Zixiang Ding, Dongbin Zhao , et al. · 2020

Recently, Tensor Ring Networks (TRNs) have been applied in deep networks, achieving remarkable successes in compression ratio and accuracy. Although highly related to the performance of TRNs, rank selection is seldom studied in previous wo…

BNAS-v2: Memory-efficient and Performance-collapse-prevented Broad Neural Architecture Search Open

Zixiang Ding, Yaran Chen, Nannan Li, Dongbin Zhao · 2020

In this paper, we propose BNAS-v2 to further improve the efficiency of NAS, embodying both superiorities of BCNN simultaneously. To mitigate the unfair training issue of BNAS, we employ continuous relaxation strategy to make each edge of c…

Faster Gradient-based NAS Pipeline Combining Broad Scalable Architecture with Confident Learning Rate. Open

Zixiang Ding, Yaran Chen, Nannan Li, Dongbin Zhao · 2020

In order to further improve the search efficiency of Neural Architecture Search (NAS), we propose B-DARTS, a novel pipeline combining broad scalable architecture with Confident Learning Rate (CLR). In B-DARTS, Broad Convolutional Neural Ne…

ContourRend: A Segmentation Method for Improving Contours by Rendering Open

Junwen Chen, Yi Lu, Yaran Chen, Dongbin Zhao, Zhong‐Hua Pang · 2020

A good object segmentation should contain clear contours and complete regions. However, mask-based segmentation can not handle contour features well on a coarse prediction grid, thus causing problems of blurry edges. While contour-based se…

BiFNet: Bidirectional Fusion Network for Road Segmentation Open

Haoran Li, Yaran Chen, Qichao Zhang, Dongbin Zhao · 2020

Multi-sensor fusion-based road segmentation plays an important role in the intelligent driving system since it provides a drivable area. The existing mainstream fusion method is mainly to feature fusion in the image space domain which caus…

ModuleNet: Knowledge-inherited Neural Architecture Search Open

Yaran Chen, Ruiyuan Gao, Fenggang Liu, Dongbin Zhao · 2020

Although Neural Architecture Search (NAS) can bring improvement to deep models, they always neglect precious knowledge of existing models. The computation and time costing property in NAS also means that we should not start from scratch to…

Graph-FCN for image semantic segmentation Open

Yi Lu, Yaran Chen, Dongbin Zhao, Jianxin Chen · 2020

Semantic segmentation with deep learning has achieved great progress in classifying the pixels in the image. However, the local location information is usually ignored in the high-level feature extraction by the deep learning, which is imp…

Reinforcement Learning and Deep Learning Based Lateral Control for Autonomous Driving [Application Notes] Open

Dong Li, Dongbin Zhao, Qichao Zhang, Yaran Chen · 2019

t his paper investigates the vision- based autonomous driving with deep learning and reinforcement learning methods.Different from the end-to-end learning method, our method breaks the vision-based lateral control system down into a percep…

Table of Contents Open

Nikhil R. Pal, P. A. Estévez, Gary Newly, José C. Prı́ncipe, Haibo He , et al. · 2019

Lane Change Decision-making through Deep Reinforcement Learning with Rule-based Constraints Open

Junjie Wang, Qichao Zhang, Dongbin Zhao, Yaran Chen · 2019

Autonomous driving decision-making is a great challenge due to the complexity and uncertainty of the traffic environment. Combined with the rule-based constraints, a Deep Q-Network (DQN) based method is applied for autonomous driving lane …

Reinforcement Learning and Deep Learning based Lateral Control for Autonomous Driving Open

Dong Li, Dongbin Zhao, Qichao Zhang, Yaran Chen · 2018

This paper investigates the vision-based autonomous driving with deep learning and reinforcement learning methods. Different from the end-to-end learning method, our method breaks the vision-based lateral control system down into a percept…

OxyR2 Modulates OxyR1 Activity and Vibrio cholerae Oxidative Stress Response Open

Hui Wang, Nawar Naseer, Yaran Chen, Anthony Zhu, Xuewen Kuai , et al. · 2017

Bacteria have developed capacities to deal with different stresses and adapt to different environmental niches. The human pathogen Vibrio cholerae , the causative agent of the severe diarrheal disease cholera, utilizes the transcriptional …

Yaran Chen YOU? Author Swipe