졸업작품 주제 조사 및 공부 계획 (2)

<blockquote data-ke-style="style3">1. Stereo Camera > 3D map (Visual SLAM) 2. AI로 객체 인지 3. Jetson 환경에 임베딩   이 세 가지를 합쳐서 작품을 구성해보려고 함 3D LiDAR 사용 없이 3D 재구성 + Segmentation https://cafe.daum.net/SmartRobot/RoVa/2424</blockquote><hr data-ke-style="style6">1. ros2 자율주행 패키지 nav2에서 지원하는 slam 형식인지? Nav2는 만들어진 지도를 소비해서 주행하는 역할그래서 SLAM 패키지가 Nav2가 이해할 수 있는 언어(표준 메시지)로 데이터(지도)를 주면 돌아가는 형식임  <hr data-ke-style="style6"> 2. ros2 nav2에서 RTAB-MAP SLAM 패키지를 지원하는지?  Nav2는 nav_msgs/OccupancyGrid 형식으로 2D 지도를 요구함이전에 찾았던 RTAB-Map이 Nav2를 위해 3D 지도를 2D 격자 지도로 만들어서 /map 토픽으로 쏘는 역할임 <a href="https://github.com/introlab/rtabmap_ros" target="_top" class="ke-link">https://github.com/introlab/rtabmap_ros</a><div class="figure-open" contenteditable="false" data-ke-type="opengraph" data-ke-align="alignCenter" data-og-type="website" data-og-title="GitHub - introlab/rtabmap_ros: RTAB-Map's ROS package." data-og-description="RTAB-Map's ROS package. Contribute to introlab/rtabmap_ros development by creating an account on GitHub." data-og-host="github.com" data-og-source-url="https://github.com/introlab/rtabmap_ros" data-og-url="https://github.com/introlab/rtabmap_ros" data-og-image="https://scrap.kakaocdn.net/dn/InXQe/hyZOfjhFh1/6y3qiVujq9aF8IC9llJZW1/img.png?width=1200&height=600&face=0_0_1200_600,https://scrap.kakaocdn.net/dn/cweYaK/hyZOPC4owM/KDWKczVb6VrX73Xk4KX5I1/img.png?width=1200&height=600&face=0_0_1200_600"><a href="https://github.com/introlab/rtabmap_ros" target="_blank" data-source-url="https://github.com/introlab/rtabmap_ros"><div class="og-image"><img class="thumb_img" src="https://scrap.kakaocdn.net/dn/InXQe/hyZOfjhFh1/6y3qiVujq9aF8IC9llJZW1/img.png?width=1200&height=600&face=0_0_1200_600,https://scrap.kakaocdn.net/dn/cweYaK/hyZOPC4owM/KDWKczVb6VrX73Xk4KX5I1/img.png?width=1200&height=600&face=0_0_1200_600" alt="" xxxxonerror="this.src="//img1.kakaocdn.net/thumb/C200x200/?fname=https%3A%2F%2Ft1.daumcdn.net%2Fcafe_image%2Fcafe_meta_image_190529.png""></div><div class="og-text">GitHub - introlab/rtabmap_ros: RTAB-Map's ROS package.RTAB-Map's ROS package. Contribute to introlab/rtabmap_ros development by creating an account on GitHub.github.com</div></a></div> 또한 지도가 기준일 때 로봇이 어디 있는지 좌표 변환 관계도 알려줘야 함이것 또한 RTAB-Map이 실시간으로 위치 추정을 지원해주는 듯...  Nav2가 지도를 어떻게 받아들이는지<a href="https://docs.nav2.org/configuration/packages/map_server/configuring-map-server.html" target="_blank" class="ke-link">https://docs.nav2.org/configuration/packages/map_server/configuring-map-server.html</a><div class="figure-open" contenteditable="false" data-ke-type="opengraph" data-ke-align="alignCenter" data-og-type="website" data-og-title="Map Server — Nav2 1.0.0 documentation" data-og-description="© Copyright 2025, Open Navigation LLC." data-og-host="docs.nav2.org" data-og-source-url="https://docs.nav2.org/configuration/packages/map_server/configuring-map-server.html" data-og-url="https://docs.nav2.org/configuration/packages/map_server/configuring-map-server.html" data-og-image="https://scrap.kakaocdn.net/dn/gSiDo/hyZOpdwZU2/JvPMZsqojGZ6RypkIfbn61/img.png?width=533&height=801&face=0_0_533_801"><a href="https://docs.nav2.org/configuration/packages/map_server/configuring-map-server.html" target="_blank" data-source-url="https://docs.nav2.org/configuration/packages/map_server/configuring-map-server.html"><div class="og-image"><img class="thumb_img" src="https://scrap.kakaocdn.net/dn/gSiDo/hyZOpdwZU2/JvPMZsqojGZ6RypkIfbn61/img.png?width=533&height=801&face=0_0_533_801" alt="" xxxxonerror="this.src="//img1.kakaocdn.net/thumb/C200x200/?fname=https%3A%2F%2Ft1.daumcdn.net%2Fcafe_image%2Fcafe_meta_image_190529.png""></div><div class="og-text">Map Server — Nav2 1.0.0 documentation© Copyright 2025, Open Navigation LLC.docs.nav2.org</div></a></div>  <div class="figure-img" data-ke-type="image" data-ke-style="alignLeft" data-ke-mobilestyle="widthOrigin"><img src="https://t1.daumcdn.net/cafeattach/1RgNt/7a5e39cd8e7f0fef6a19c6abf462cd910cda3f0a_re_1763973787480" class="txc-image" width="700" height="212" data-img-src="https://t1.daumcdn.net/cafeattach/1RgNt/7a5e39cd8e7f0fef6a19c6abf462cd910cda3f0a_re_1763973787480" data-origin-width="963" data-origin-height="292"></div>Obstacle Layer: 실시간 장애물 처리하는 곳 (여기가 ZED 카메라가 들어갈 곳인 듯)Inflation Layer: Padding 만드는 곳Voxel Layer: 3D Point Cloud 처리하는 곳 <a href="https://docs.nav2.org/configuration/packages/configuring-costmaps.html" target="_blank" class="ke-link">https://docs.nav2.org/configuration/packages/configuring-costmaps.html</a><div class="figure-open" contenteditable="false" data-ke-type="opengraph" data-ke-align="alignCenter" data-og-type="website" data-og-title="Costmap 2D — Nav2 1.0.0 documentation" data-og-description="Ordered set of footprint points passed in as a string, must be closed set. For example, the following defines a square base with side lengths of 0.2 meters footprint: “[ [0.1, 0.1], [0.1, -0.1], [-0.1, -0.1], [-0.1, 0.1] ]”. Note that this can also be " data-og-host="docs.nav2.org" data-og-source-url="https://docs.nav2.org/configuration/packages/configuring-costmaps.html" data-og-url="https://docs.nav2.org/configuration/packages/configuring-costmaps.html" data-og-image="https://scrap.kakaocdn.net/dn/D7R2W/hyZOM7pS0y/82vVYus6TwKdqrTKsapKAK/img.png?width=533&height=801&face=0_0_533_801"><a href="https://docs.nav2.org/configuration/packages/configuring-costmaps.html" target="_blank" data-source-url="https://docs.nav2.org/configuration/packages/configuring-costmaps.html"><div class="og-image"><img class="thumb_img" src="https://scrap.kakaocdn.net/dn/D7R2W/hyZOM7pS0y/82vVYus6TwKdqrTKsapKAK/img.png?width=533&height=801&face=0_0_533_801" alt="" xxxxonerror="this.src="//img1.kakaocdn.net/thumb/C200x200/?fname=https%3A%2F%2Ft1.daumcdn.net%2Fcafe_image%2Fcafe_meta_image_190529.png""></div><div class="og-text">Costmap 2D — Nav2 1.0.0 documentationOrdered set of footprint points passed in as a string, must be closed set. For example, the following defines a square base with side lengths of 0.2 meters footprint: “[ [0.1, 0.1], [0.1, -0.1], [-0.1, -0.1], [-0.1, 0.1] ]”. Note that this can also be docs.nav2.org</div></a></div>  Nav2 전체 아키텍쳐 (개념 설명인 듯)<a href="https://docs.nav2.org/concepts/index.html" target="_top" class="ke-link">https://docs.nav2.org/concepts/index.html</a><div class="figure-open" contenteditable="false" data-ke-type="opengraph" data-ke-align="alignCenter" data-og-type="website" data-og-title="Navigation Concepts — Nav2 1.0.0 documentation" data-og-description="This page is to help familiarize new roboticists to the concepts of mobile robot navigation, in particular, with the concepts required to appreciating and working with this project. Behavior Trees Behavior trees (BT) are becoming increasingly common in com" data-og-host="docs.nav2.org" data-og-source-url="https://docs.nav2.org/concepts/index.html" data-og-url="https://docs.nav2.org/concepts/index.html" data-og-image="https://scrap.kakaocdn.net/dn/bD91AS/hyZN4hKboM/jKLCtvKzu9Jf4YeDfqvRXk/img.png?width=533&height=801&face=0_0_533_801"><a href="https://docs.nav2.org/concepts/index.html" target="_blank" data-source-url="https://docs.nav2.org/concepts/index.html"><div class="og-image"><img class="thumb_img" src="https://scrap.kakaocdn.net/dn/bD91AS/hyZN4hKboM/jKLCtvKzu9Jf4YeDfqvRXk/img.png?width=533&height=801&face=0_0_533_801" alt="" xxxxonerror="this.src="//img1.kakaocdn.net/thumb/C200x200/?fname=https%3A%2F%2Ft1.daumcdn.net%2Fcafe_image%2Fcafe_meta_image_190529.png""></div><div class="og-text">Navigation Concepts — Nav2 1.0.0 documentationThis page is to help familiarize new roboticists to the concepts of mobile robot navigation, in particular, with the concepts required to appreciating and working with this project. Behavior Trees Behavior trees (BT) are becoming increasingly common in comdocs.nav2.org</div></a></div>    RTAB-Map으로 지도 그리면서 동시에 Nav2로 자율주행시키는 예제<a href="https://wiki.ros.org/rtabmap_ros/Tutorials/MappingAndNavigationOnTurtlebot" target="_blank" class="ke-link">https://wiki.ros.org/rtabmap_ros/Tutorials/MappingAndNavigationOnTurtlebot</a><div class="figure-open" contenteditable="false" data-ke-type="opengraph" data-ke-align="alignCenter" data-og-type="website" data-og-title="rtabmap_ros/Tutorials/MappingAndNavigationOnTurtlebot - ROS Wiki" data-og-description="Please ask about problems and questions regarding this tutorial on answers.ros.org. Don't forget to include in your question the link to this page, the versions of your OS & ROS, and also add appropriate tags. Mapping and Navigation with Turtlebot Descript" data-og-host="wiki.ros.org" data-og-source-url="https://wiki.ros.org/rtabmap_ros/Tutorials/MappingAndNavigationOnTurtlebot" data-og-url="https://wiki.ros.org/rtabmap_ros/Tutorials/MappingAndNavigationOnTurtlebot" data-og-image="https://scrap.kakaocdn.net/dn/eSKlM/hyZOgicLSw/K26L7PuA0MTgXtGj8ES2P1/img.png?width=750&height=410&face=0_0_750_410"><a href="https://wiki.ros.org/rtabmap_ros/Tutorials/MappingAndNavigationOnTurtlebot" target="_blank" data-source-url="https://wiki.ros.org/rtabmap_ros/Tutorials/MappingAndNavigationOnTurtlebot"><div class="og-image"><img class="thumb_img" src="https://scrap.kakaocdn.net/dn/eSKlM/hyZOgicLSw/K26L7PuA0MTgXtGj8ES2P1/img.png?width=750&height=410&face=0_0_750_410" alt="" xxxxonerror="this.src="//img1.kakaocdn.net/thumb/C200x200/?fname=https%3A%2F%2Ft1.daumcdn.net%2Fcafe_image%2Fcafe_meta_image_190529.png""></div><div class="og-text">rtabmap_ros/Tutorials/MappingAndNavigationOnTurtlebot - ROS WikiPlease ask about problems and questions regarding this tutorial on answers.ros.org. Don't forget to include in your question the link to this page, the versions of your OS & ROS, and also add appropriate tags. Mapping and Navigation with Turtlebot Descriptwiki.ros.org</div></a></div><a href="https://wiki.ros.org/rtabmap_ros/Tutorials/HandHeldMapping" target="_blank" class="ke-link">https://wiki.ros.org/rtabmap_ros/Tutorials/HandHeldMapping</a><div class="figure-open" contenteditable="false" data-ke-type="opengraph" data-ke-align="alignCenter" data-og-type="website" data-og-title="rtabmap_ros/Tutorials/HandHeldMapping - ROS Wiki" data-og-description="Please ask about problems and questions regarding this tutorial on answers.ros.org. Don't forget to include in your question the link to this page, the versions of your OS & ROS, and also add appropriate tags. RGB-D Handheld Mapping Description: This tutor" data-og-host="wiki.ros.org" data-og-source-url="https://wiki.ros.org/rtabmap_ros/Tutorials/HandHeldMapping" data-og-url="https://wiki.ros.org/rtabmap_ros/Tutorials/HandHeldMapping" data-og-image="https://scrap.kakaocdn.net/dn/Zb0cZ/hyZOGMToP3/e6mikkm9e0ww0PH48T3AHK/img.png?width=1527&height=853&face=0_0_1527_853"><a href="https://wiki.ros.org/rtabmap_ros/Tutorials/HandHeldMapping" target="_blank" data-source-url="https://wiki.ros.org/rtabmap_ros/Tutorials/HandHeldMapping"><div class="og-image"><img class="thumb_img" src="https://scrap.kakaocdn.net/dn/Zb0cZ/hyZOGMToP3/e6mikkm9e0ww0PH48T3AHK/img.png?width=1527&height=853&face=0_0_1527_853" alt="" xxxxonerror="this.src="//img1.kakaocdn.net/thumb/C200x200/?fname=https%3A%2F%2Ft1.daumcdn.net%2Fcafe_image%2Fcafe_meta_image_190529.png""></div><div class="og-text">rtabmap_ros/Tutorials/HandHeldMapping - ROS WikiPlease ask about problems and questions regarding this tutorial on answers.ros.org. Don't forget to include in your question the link to this page, the versions of your OS & ROS, and also add appropriate tags. RGB-D Handheld Mapping Description: This tutorwiki.ros.org</div></a></div>    <hr data-ke-style="style6">3. 방학 때 ros2 심화과정 공부 계획 카페 강의자료의 [ROS2심화] 1. ~ 9까지 진행할 계획 (멀티모달 제외)   <hr data-ke-style="style6">4. 로봇은 2차원에서 움직이는데 3d 맵이 필요한 이유 2D sensor(LiDAR) 혹은 2D map은 세상을 단면으로 봄...<div class="figure-img" data-ke-type="image" data-ke-style="alignLeft" data-ke-mobilestyle="widthOrigin"><img src="https://t1.daumcdn.net/cafeattach/1RgNt/af30c1b62e7af35977f38ffb0d07d754ede3700c_re_1763973787480" class="txc-image" width="600" data-img-src="https://t1.daumcdn.net/cafeattach/1RgNt/af30c1b62e7af35977f38ffb0d07d754ede3700c_re_1763973787480" data-origin-width="845" data-origin-height="500"></div>이런 식으로 바닥에 닿는 부분만 인식해서 맵을 구성하게 됨그럼 센서가 바닥 면적보다 상단 면적이 높은 물체(책상이나 기둥 기반으로 올린 거, 오버행 Overhang)인식을 못하고 그 사이로 지나갈 수도 있음 == 몸통이나 상단 센서가 충돌할 수 있음 3D 센서는 공간의 부피를 인식하기 때문에 이러한 물체에 대해 더 넓게 돌아가는 판단이 가능함  또한 SLAM이 자기 위치를 찾으려면(Localization) 주변의 특징을 기억해야 함긴 복도를 생각하면 2D 맵으로는 어디가 앞이고 뒤인지 구분 못함 (Long Corridor Problem)3D 카메라는 시각적으로 특징 잡을게 많아서 위치 인식에 좋은 성능을 보여줌   <hr data-ke-style="style6">5. slam 분야를 뽑는 업체가 로봇 기업 외에 소프트웨어 전문 기업도 있는지? AR/VR/메타버스 기업: 헤드셋의 위치를 기반으로 주변 환경을 비주얼 슬램으로 구성해야 하기 때문에... 자율주행 소프트웨어 전문 기업도 SLAM 분야를 뽑음<a href="https://stradvision.career.greetinghr.com/ko/guide" target="_blank" class="ke-link">https://stradvision.career.greetinghr.com/ko/guide</a><div class="figure-open" contenteditable="false" data-ke-type="opengraph" data-ke-align="alignCenter" data-og-type="website" data-og-title="스트라드비젼(STRADVISION) 채용" data-og-description="스트라드비젼(STRADVISION)의 채용 홈페이지입니다." data-og-host="stradvision.career.greetinghr.com" data-og-source-url="https://stradvision.career.greetinghr.com/ko/guide" data-og-url="https://stradvision.career.greetinghr.com/ko/guide" data-og-image="https://scrap.kakaocdn.net/dn/cmpIyN/hyZN3XEG8Y/r9Vc1m43gFAnfUF8PDcvjk/img.jpg?width=500&height=500&face=0_0_500_500,https://scrap.kakaocdn.net/dn/dblWdO/hyZODW0pV7/y6xJukqCwuoi8c7uNNi190/img.jpg?width=500&height=500&face=0_0_500_500,https://scrap.kakaocdn.net/dn/LduL2/hyZOqKsOg7/s59YEvOkKxZFnqkKK6wEC1/img.jpg?width=500&height=200&face=0_0_500_200"><a href="https://stradvision.career.greetinghr.com/ko/guide" target="_blank" data-source-url="https://stradvision.career.greetinghr.com/ko/guide"><div class="og-image"><img class="thumb_img" src="https://scrap.kakaocdn.net/dn/cmpIyN/hyZN3XEG8Y/r9Vc1m43gFAnfUF8PDcvjk/img.jpg?width=500&height=500&face=0_0_500_500,https://scrap.kakaocdn.net/dn/dblWdO/hyZODW0pV7/y6xJukqCwuoi8c7uNNi190/img.jpg?width=500&height=500&face=0_0_500_500,https://scrap.kakaocdn.net/dn/LduL2/hyZOqKsOg7/s59YEvOkKxZFnqkKK6wEC1/img.jpg?width=500&height=200&face=0_0_500_200" alt="" xxxxonerror="this.src="//img1.kakaocdn.net/thumb/C200x200/?fname=https%3A%2F%2Ft1.daumcdn.net%2Fcafe_image%2Fcafe_meta_image_190529.png""></div><div class="og-text">스트라드비젼(STRADVISION) 채용스트라드비젼(STRADVISION)의 채용 홈페이지입니다.stradvision.career.greetinghr.com</div></a></div> DeltaX<div class="figure-img" data-ke-type="image" data-ke-style="alignLeft" data-ke-mobilestyle="widthOrigin"><img src="https://t1.daumcdn.net/cafeattach/1RgNt/7497a0e495bdaa0bbbf9957433e35528abed1f0d" class="txc-image" data-img-src="https://t1.daumcdn.net/cafeattach/1RgNt/7497a0e495bdaa0bbbf9957433e35528abed1f0d" data-origin-width="524" data-origin-height="591"></div>  <hr data-ke-style="style6">6. slam의 동작원리, 2d/3d slam 종류 조사 SLAM의 동작원리<ul style="list-style-type: disc;" data-ke-list-type="disc"><li>Localization (위치 추정): 지도가 있어야 내 위치를 알 수 있음</li><li>Mapping (지도 작성): 내 위치를 알아야 지도를 그릴 수 있음</li><li>SLAM: 둘 다 동시에 조금씩 하는 기술</li></ul> 핵심 4단계<ol style="list-style-type: decimal;" data-ke-list-type="decimal"><li>Odometry (추측 항법, Front-end) 센서만 믿고 대충 추측함 (어디까지 이동했는지) 시간이 지날수록 오차가 쌓임 </li><li>Feature Extraction & Matching (특징점 추출) 주변 환경의 랜드마크를 찾아서 비교함 </li><li>Optimization (최적화, Back-end) 센서 값과 관측 값 사이의 오차를 수학적으로 최소화해서 내 위치와 지도를 수정함 (ex, Kalman Filter) </li><li>Loop Closure (루프 탐지) 한 바퀴 돌아서 제자리에 왔다는 걸 깨닫는 순간, 그동한 쌓였던 모든 오차를 보정함</li></ol>   2D SLAM 종류 및 특징 (주로 LiDAR 기반)바닥에 있는 벽만 따는 방식, 요즘 트렌드는 SLAM Toolbox라고 함...<div class="table-wrap"><table data-ke-type="table" data-ke-align="alignLeft" style="width: 100%; height: 144px;" border="1" data-ke-style="style12"><tbody><tr style="height: 18px;"><td style="width: 25%; height: 18px; text-align: center;">이름</td><td style="width: 25%; height: 18px; text-align: center;">특징</td><td style="width: 25%; height: 18px; text-align: center;">장점</td><td style="width: 25%; height: 18px; text-align: center;">단점</td></tr><tr style="height: 54px;"><td style="width: 25%; height: 54px; text-align: center;">Gmapping</td><td style="width: 25%; height: 54px; text-align: center;">필터 기반 (Rao-Blackwellized Paricle Filter)</td><td style="width: 25%; height: 54px; text-align: center;">가볍고 설정이 쉬움</td><td style="width: 25%; height: 54px; text-align: center;">맵이 커지면 메모리 터짐 오래 돌리면 오차 심함</td></tr><tr style="height: 36px;"><td style="width: 25%; height: 36px; text-align: center;">Cartographer</td><td style="width: 25%; height: 36px; text-align: center;">그래프 기반 (Graph SLAM) 구글 제작</td><td style="width: 25%; height: 36px; text-align: center;">정밀도 제일 좋음 오차가 거의 없음</td><td style="width: 25%; height: 36px; text-align: center;">CPU를 많이 잡아먹음 세팅이 매우 복잡함</td></tr><tr style="height: 36px;"><td style="width: 25%; height: 36px; text-align: center;">SLAM Toolbox</td><td style="width: 25%; height: 36px; text-align: center;">Karto 기반 현재 ROS2의 표준</td><td style="width: 25%; height: 36px; text-align: center;">대형 지도도 잘 만듦 지도 저장/로드가 편함</td><td style="width: 25%; height: 36px; text-align: center;">Nav2 기본 탑재라 딱히 단점이 없음 (2D 한정)</td></tr></tbody></table></div>   3D SLAM 종류 및 특징 (Vision & LiDAR)공간 전체를 다루는 방식<div class="table-wrap"><table data-ke-type="table" data-ke-align="alignLeft" style="width: 100%; height: 144px;" border="1" data-ke-style="style12"><tbody><tr style="height: 18px;"><td style="width: 20.8386%; height: 18px;">이름</td><td style="width: 24.2434%; height: 18px;">센서</td><td style="width: 26.6393%; height: 18px;">특징</td><td style="width: 28.2787%; height: 18px;">졸작 적합성</td></tr><tr style="height: 54px;"><td style="width: 20.8386%; height: 54px;">ORB-SLAM(1, 2, 3)</td><td style="width: 24.2434%; height: 54px;">카메라 (Mono/Stereo/RGBD)</td><td style="width: 26.6393%; height: 54px;">특징점(Feature) 기반 카메라만으로 성능이 좋음 지도가 Point로 나옴</td><td style="width: 28.2787%; height: 54px;">좋지만 Nav2용 2D 지도로 변환하려면 추가 작업이 필요함</td></tr><tr style="height: 36px;"><td style="width: 20.8386%; height: 36px;">RTAB-Map</td><td style="width: 24.2434%; height: 36px;">카메라 & 라이다 둘 다 됨</td><td style="width: 26.6393%; height: 36px;">메모리 관리 기술이 있음 오래 돌려도 렉 X Nav2 호환성 좋음</td><td style="width: 28.2787%; height: 36px;">ZED 카메라 + Nav2 최적화</td></tr><tr style="height: 36px;"><td style="width: 20.8386%; height: 36px;">LOAM / LIO-SAM</td><td style="width: 24.2434%; height: 36px;">3D 라이다 (velodyne 등)</td><td style="width: 26.6393%; height: 36px;">3D 라이다가 있으면 이게 좋음</td><td style="width: 28.2787%; height: 36px;">3D 라이다가 없음...</td></tr></tbody></table></div>

카페정보

인공지능로봇연구실

카페 전체 메뉴

▲

카페 게시글

과제게시판 졸업작품 주제 조사 및 공부 계획 (2)

신민서 추천 0 조회 46 25.11.25 16:03 댓글 1

게시글 본문내용

다음검색

저작자 표시 컨텐츠변경 비영리

Sungryul Lee
25.11.26 20:49

첫댓글 1. RTAB-Map를 carla 시뮬레이터에서 응용한 사례가 있는지 조사
2. RTAB-Map를 gazebo 시뮬레이터에서 응용한 사례가 있는지 조사
3. RTAB-Map의 localization 기능 조사 slam후에 맵을 이용하여 위치 추정하는건지
3. slam을 수행하는 AI 모델이 있는지 조사?

검색 옵션 선택상자

댓글내용선택됨 옵션 더 보기

댓글내용

댓글 작성자

최신목록

인공지능로봇연구실

https://cafe.daum.net/SmartRobot

카페 전체 메뉴