An Object SLAM Framework for Association, Mapping, and High-Level Tasks

no code implementations • 12 May 2023 • Yanmin Wu, Yunzhou Zhang, Delong Zhu, Zhiqiang Deng, Wenkai Sun, Xin Chen, Jian Zhang

Taking into consideration the semantic invariance of objects, we convert the object map to a topological map to provide semantic descriptors to enable multi-map matching.

Decision Making Object +2

A Large-Scale Dataset for Benchmarking Elevator Button Segmentation and Character Recognition

1 code implementation • 16 Mar 2021 • Jianbang Liu, Yuqi Fang, Delong Zhu, Nachuan Ma, Jin Pan, Max Q. -H. Meng

Human activities are hugely restricted by COVID-19, recently.

Benchmarking Position +1

Accurate and Robust Scale Recovery for Monocular Visual Odometry Based on Plane Geometry

no code implementations • 15 Jan 2021 • Rui Tian, Yunzhou Zhang, Delong Zhu, Shiwen Liang, Sonya Coleman, Dermot Kerr

In this paper, with the assumption of a constant height of the camera above the ground, we develop a light-weight scale recovery framework leveraging an accurate and robust estimation of the ground plane.

Loop Closure Detection Monocular Visual Odometry +2

Object SLAM-Based Active Mapping and Robotic Grasping

1 code implementation • 3 Dec 2020 • Yanmin Wu, Yunzhou Zhang, Delong Zhu, Xin Chen, Sonya Coleman, Wenkai Sun, Xinggang Hu, Zhiqiang Deng

The framework is built on an object SLAM system integrated with a simultaneous multi-object pose estimation process that is optimized for robotic grasping.

Object Object SLAM +2

Autonomous Removal of Perspective Distortion of Elevator Button Images based on Corner Detection

no code implementations • 23 Jul 2020 • Nachuan Ma, Jianbang Liu, Delong Zhu

First, we leverage a novel image segmentation model and the Hough Transform method to obtain button segmentation and button corner detection results.

Image Segmentation Segmentation +1

EAO-SLAM: Monocular Semi-Dense Object SLAM Based on Ensemble Data Association

2 code implementations • 27 Apr 2020 • Yanmin Wu, Yunzhou Zhang, Delong Zhu, Yonghui Feng, Sonya Coleman, Dermot Kerr

Object-level data association and pose estimation play a fundamental role in semantic SLAM, which remain unsolved due to the lack of robust and accurate algorithms.

Object Object SLAM +2

TartanAir: A Dataset to Push the Limits of Visual SLAM

1 code implementation • 31 Mar 2020 • Wenshan Wang, Delong Zhu, Xiangwei Wang, Yaoyu Hu, Yuheng Qiu, Chen Wang, Yafei Hu, Ashish Kapoor, Sebastian Scherer

We present a challenging dataset, the TartanAir, for robot navigation task and more.

Robotics

Autonomous Removal of Perspective Distortion for Robotic Elevator Button Recognition

no code implementations • 26 Dec 2019 • Delong Zhu, Jianbang Liu, Nachuan Ma, Zhe Min, Max Q. -H. Meng

To verify the effectiveness of the algorithm, we collect an elevator panel dataset of 50 images captured from different angles of view.

HouseExpo: A Large-scale 2D Indoor Layout Dataset for Learning-based Algorithms on Mobile Robots

3 code implementations • 23 Mar 2019 • Tingguang Li, Danny Ho, Chenming Li, Delong Zhu, Chaoqun Wang, Max Q. -H. Meng

As one of the most promising areas, mobile robots draw much attention these years.

Robotics

Learning to Interrupt: A Hierarchical Deep Reinforcement Learning Framework for Efficient Exploration

no code implementations • 30 Jul 2018 • Tingguang Li, Jin Pan, Delong Zhu, Max Q. -H. Meng

Our architecture has two key components: options, represented by existing human-designed methods, can significantly speed up the training process and interruption mechanism, based on learnable termination functions, enables our system to quickly respond to the external environment.

Efficient Exploration Hierarchical Reinforcement Learning +3