2019 ICRA

posted Feb 13, 2020, 1:53 AM by 박주현   [ updated Feb 13, 2020, 1:53 AM ]

2019 ICRA학회 참석 후기와 논문을 간단히 소개한 세미나자료를 공유합니다.

I share the seminar material that has briefly introduced the 2019 ICRA conference and paper.

2019 IROS

posted Feb 13, 2020, 1:47 AM by 임형태   [ updated Feb 13, 2020, 1:55 AM ]

2019 IROS 및 최근 SLAM에서의 딥러닝의 동향에 대한 논문을 간단히 소개한 세미나자료를 공유합니다.

I share the seminar material that briefly introduced the 2019 IROS conference and paper! It's about

- R2D2: Repeatable and Reliable Detector and Descriptor
- SuMa++: Efficient LiDAR-based Semantic SLAM
- DeepPCO: End-to-End Point Cloud through Deep Parallel Neural Network

2019 ICRA - workshop

posted Feb 13, 2020, 1:46 AM by 현지음   [ updated Feb 13, 2020, 3:00 AM ]

2019년 ICRA 학회 workshop에서 발표한 자료를 정리한 내용입니다.

Workshop: Dataset Generation and Benchmarking of SLAM Algorithms for Robotics and VR/AR

2019 IROS

posted Feb 13, 2020, 12:45 AM by 이준석   [ updated Feb 13, 2020, 1:23 AM ]

2019 IROS 학회 참석 후기와 보행 로봇의 메커니즘에 관련한 논문을 간단히 소개한 세미나자료를 공유합니다.

I share the seminar material that have briefly introduced the 2019 IROS conference and paper on the mechanism of legged robots.

2019 IROS

posted Feb 12, 2020, 10:25 PM by CK S   [ updated Feb 12, 2020, 11:13 PM ]

2019 IROS에 다녀온후 2개의 논문을 정리하여 소개합니다.

Papers that are published in 2019 IROS will be introduced briefly.

1. Exploiting Sparse Semantic HD Maps for Self-Driving Vehicle Localization
    - The authors work at the UBER.
    - The Camera, LiDAR, GPS, Wheel Encoder, IMU, and HD map are used for the localization.
        - HD map
            The HD map needs only about 0.3% storage comparing to the LiDAR map.
            HD map contains the Lane and traffic sign position. (Lane: Lateral position & Heading, Sign: Longitudinal Position)
        - Lane Extracting
            The Lane can be extracted with the front-view camera image with raw LiDAR intensity.
        - Detecting Traffic Sign
            The traffic sign can be detected by a convolutional network. (Backbone as PSPNet)
        - Matching Process
            It matches between the extracted lane and lane data from the HD Map.
            It matches the detected traffic sign with the traffic sign data from the HD Map.
            Each probability (Weight) is calculated with GPS and IMU + Encoder.
            The location of the vehicle is estimated through the calculated probability.

    - Result
    They tested the vehicle about 312 km on the highway in the United States. Then, they only got 0.05m of lateral error and 1.12m longitudinal error.
    The algorithm runs at roughly 7Hz.

2. RangeNet++: Fast and Accurate LiDAR Semantic Segmentation
    - Semantic Segmentation with Only Rotational LiDAR
    - The point clouds are projected into the spherical image.
    - The RangeNet53 uses the KarKnet53 as the backbone.
    - The Network is trained with Semantic KITTI data.
    - About 130,000 points are converted into the 32,728 pixels.
    - The pixel contains the point clouds' index information to bring all the estimated semantic information.
    - There could be artifacts at the border of the object. To get rid of the artifacts, they used post-processing.
    - In a 3D coordinate (PointCloud), the K-NN search is adapted to filter the artifacts at the border.
    - The algorithm is running in real-time with the graphic card such as gtx1080.

    - Results











64 x 2048 px









64 x 1024 px









64 x 512 px









                                                                                                                                                                                            IoU [%]                                                                                                                           
Here is the Video which they posted on Youtube

2019 NeurIPS

posted Feb 12, 2020, 9:46 PM by 김윤수

2019 NeurIPS에 다녀온 후기 및 2 개의 논문을 소개한 세미나자료를 공유합니다.

Two papers presented at NeurIPS 2019 and some information about the NeurIPS 2019 are shaered.

2019 ICRA

posted Feb 12, 2020, 9:43 PM by 유병호   [ updated Feb 12, 2020, 9:49 PM ]

ICRA 2019(캐나다의 몬트리올, 2019년 5월 20일 - 24일)에 참석한 후기, 그리고 인상 깊었던 논문을 간략히 소개한 세미나 발표자료를 공유합니다.

Among the papers seen at the ICRA 2019(which was held on May 20-24, 2019 in Montreal, Canada.), a summary of what was impressive is shared.

2019 ICCV

posted Feb 12, 2020, 9:43 PM by 김윤수

2019 ICCV에 accept된 2 개의 논문을 소개한 세미나자료를 공유합니다.

Two papers presented at ICCV 2019 are shaered.

2019 ICCV

posted Jan 31, 2020, 6:47 AM by Seung Hee Lee   [ updated Feb 2, 2020, 12:10 AM ]

2019 ICCV 참석 후기와 몇개의 논문을 간단히 소개한 세미나자료를 공유합니다.

I share my slides introducing a few papers presented at ICCV 2019 briefly and the experience after attending the conference.

Lab seminar material

posted Jan 30, 2020, 11:18 PM by Hyun Myung

여기에 로보틱스 및 기계학습, 인공지능 관련한 랩 세미나 자료와 주요 국제 학회 survey 노트 자료를 공유합니다.

We share the recent lab seminar materials and survey notes for international conferences related to robotics, machine learning, and AI.

1-10 of 10