Ryohei Sasaki @rsasaki0109 Twitter profile

Pinned Tweet

Ryohei Sasaki

@rsasaki0109

1 month

自分が作ったOSSが使われて、ロボットが動いてるの嬉しい〜

Francisco Martín 🇪🇺

@Fmrico

1 month

A new round of experiments is complete. Our Multi-Hipothesys Monte Carlo localization algorithm, fully integrated with #Nav2 , works perfectly at indoors/outdoors non-planar environments. #science #robotics

2

24

165

1

3

63

Last Seen Profiles

@VIDITGUPTA

@im______OBITO

@godhoodcomics

@Nieterwarrior

@apeconcerts

@R43LN

@Strien9

@and_plough

@cyb3rf4iryx

@katieturner0087

@SatuRyynanen

@nukboii

@Kohlerderien

@SpoofyHype

@bgraczak

@MandrakeNS

@bencodental

@maddietagg_

@MariaLuckyxo

@volkphlore

@LNBPFEMENIL

@Coach_EdOrgeron

@hokutoshi_kouko

@MichaelTemps

@kaimeariver

@WCAboyslacrosse

@Larssen00

@VenturaRanciel

@quishs260

@FSAthletics

@danajeanphoenix

@Diavolo_Deaths

@TLyO1dthPibIZXe

@Unit42_Intel

@Blueprint4Biz

@Hi_MINISFORUM

Ryohei Sasaki

@rsasaki0109

11 months

A new method using a Neural Object Field achieves 6-DoF tracking and 3D reconstruction of unknown, rigid objects from RGBD video sequences. It operates effectively even with occlusions, pose changes, and texture-less surfaces. BundleSDF(CVPR 2023)

5

140

915

Ryohei Sasaki

@rsasaki0109

1 year

MPCC Simulation environments in C++ and Matlab of the Model Predictive Contouring Controller (MPCC) for Autonomous Racing developed by the Automatic Control Lab (IfA) at ETH Zurich

4

120

648

Ryohei Sasaki

@rsasaki0109

6 months

mathematical_robotics Optimization for Robotics point_cloud_matching Matching of 3D point clouds using rigid transformation by Lie groups, with optimization performed using Ceres Solver.

5

53

430

Ryohei Sasaki

@rsasaki0109

2 months

VisFusion: Visibility-aware Online 3D Scene Reconstruction from Videos (CVPR 2023)

6

79

424

Ryohei Sasaki

@rsasaki0109

2 months

Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed(CVPR 2024)

0

60

406

Ryohei Sasaki

@rsasaki0109

1 year

"Optimal Motion Generation-tools" is a Python software that simplifies motion planning. It's designed for both single-agent and multi-agent systems, and aims to make research on this topic more accessible. omg-tools

4

68

383

Ryohei Sasaki

@rsasaki0109

4 months

GNSS受信機に関する神資料が公開されてる GNSS 受信機の概要 I アンテナ信号入力から、擬似距離出力まで

1

97

369

Ryohei Sasaki

@rsasaki0109

11 months

NOPE: Novel Object Pose Estimation from a Single Image

2

55

365

Ryohei Sasaki

@rsasaki0109

3 months

viser viser is a library for interactive 3D visualization + Python, inspired by tools like Pangolin, rviz, meshcat, and Gradio. It's designed to support applications in 3D vision and robotics. Point cloud visualization

1

73

335

Ryohei Sasaki

@rsasaki0109

5 years

『システム／制御／情報』のガウス過程特集号「ガウス過程回帰の基礎から応用」が，先月から無料で読めるようになってる！

0

85

326

Ryohei Sasaki

@rsasaki0109

1 year

NeRF-RPN, a new object detection framework, operates directly on NeRF models and leverages multi-scale 3D neural volumetric features in a voxel representation to regress 3D bounding boxes without rendering.[CVPR 2023]

0

48

316

Ryohei Sasaki

@rsasaki0109

3 months

fmm Fast map matching, an open source framework in C++ Map match to OSM road network by drawing

1

56

260

Ryohei Sasaki

@rsasaki0109

1 month

Representing 3D sparse map points and lines for camera relocalization

0

49

285

Ryohei Sasaki

@rsasaki0109

5 months

OccNeRF: Self-Supervised Multi-Camera Occupancy Prediction with Neural Radiance Fields

1

53

266

Ryohei Sasaki

@rsasaki0109

7 months

[CVPR 2023 Highlight]ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields

1

46

266

Ryohei Sasaki

@rsasaki0109

9 months

Traditional LiDAR SLAM yields sparse maps. A new CPU-only system generates and localizes dense mesh maps in real-time using Gaussian process reconstruction, running at 40Hz with enhanced accuracy. SLAMesh

1

39

261

Ryohei Sasaki

@rsasaki0109

5 months

Mip-Splatting: Alias-free 3D Gaussian Splatting > TL;DR: We introduce a 3D smoothing filter and a 2D Mip filter for 3D Gaussian Splatting (3DGS), eliminating multiple artifacts and achieving alias-free renderings.

6

38

262

Ryohei Sasaki

@rsasaki0109

30 days

UniDepth: Universal Monocular Metric Depth Estimation Zero-Shot Visualization YouTube (The Office - Parkour)

1

33

262

Ryohei Sasaki

@rsasaki0109

9 months

ManipulationOnTheMove An Architecture for Reactive Mobile Manipulation On-The-Move(ICRA2023)

1

43

257

Ryohei Sasaki

@rsasaki0109

2 months

CropCraft A Procedural World Generator for Robotics Simulation of Agricultural Tasks > CropCraft is a python script that allows to generate 3D models of crop fields specialized for real-time simulation of robotics application.

0

44

254

Ryohei Sasaki

@rsasaki0109

11 months

The paper presents OccNet, a novel pipeline for 3D occupancy reconstruction that improves driving tasks like detection, segmentation, and planning. Using a general occupancy embedding, it notably reduces collision rates in motion planning.

4

46

249

Ryohei Sasaki

@rsasaki0109

4 months

[AAAI 2024] Official repository for UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation. UCMCTrack ranks first on MOT17 without using any appearance cues. Tracking Vehicles with Moving Camera

0

50

250

Ryohei Sasaki

@rsasaki0109

2 months

(IV 2023) LVT2Calib: Automatic and Unified Extrinsic Calibration Toolbox for Different 3D LiDAR, Visual Camera and Thermal Camera

0

48

250

Ryohei Sasaki

@rsasaki0109

2 months

DepthAnything-ROS DepthAnything-ROS is ROS2 wrapper for Depth-Anything.

0

39

248

Ryohei Sasaki

@rsasaki0109

7 months

mppi_numba A GPU implementation of Model Predictive Path Integral (MPPI) control that uses a probabilistic traversability model for planning risk-aware trajectories.

1

26

242

Ryohei Sasaki

@rsasaki0109

1 month

NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM(3DV 2024 Oral)

2

30

237

Ryohei Sasaki

@rsasaki0109

1 year

主に点群処理/LiDAR SLAMに関する研究をしている産総研小出さんが可視化用ライブラリを公開している iridescence 3D visualization library for rapid prototyping of 3D algorithms

0

55

239

Ryohei Sasaki

@rsasaki0109

2 years

色々なセンサ間キャリブレーションのオープンソースを公開しているOpenCalibというorganizationを見つけた

0

46

234

Ryohei Sasaki

@rsasaki0109

2 months

[CVPR 2024] The official implementation for "SemCity: Semantic Scene Generation with Triplane Diffusion"

1

34

231

Ryohei Sasaki

@rsasaki0109

3 months

SpacetimeGaussians Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis

4

32

228

Ryohei Sasaki

@rsasaki0109

1 year

SegmentAnything3D SAM-3D: A toolbox transfers 2D SAM segments into 3D scene-level point clouds

0

47

226

Ryohei Sasaki

@rsasaki0109

11 months

[ICRA 2023] Adaptive and Explainable Deployment of Navigation Skills via Hierarchical Deep Reinforcement Learning

1

47

223

Ryohei Sasaki

@rsasaki0109

2 months

WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion

0

36

226

Ryohei Sasaki

@rsasaki0109

6 months

Automatic-Parking Python implementation of an automatic parallel parking system in a virtual environment, including path planning, path tracking, and parallel parking

1

31

222

Ryohei Sasaki

@rsasaki0109

10 months

Detector-Free Structure from Motion >TL;DR: We propose a detector-free structure from motion framework that eliminates the requirement of keypoint detection and can recover poses even on challenging texture-poor scene

2

36

220

Ryohei Sasaki

@rsasaki0109

1 year

NeRF-SLAM Real-Time Dense Monocular SLAM with Neural Radiance Fields.

1

41

221

Ryohei Sasaki

@rsasaki0109

1 year

LSD (LiDAR SLAM & Detection) is an open source perception architecture for autonomous vehicle/robotic

4

37

218

Ryohei Sasaki

@rsasaki0109

6 months

UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fields(ICCV2023) Controllable 3D-aware Image Synthesis (top) & Panoptic Prior (bottom)

1

42

213

Ryohei Sasaki

@rsasaki0109

2 months

MorpheuS: Neural Dynamic 360° Surface Reconstruction from Monocular RGB-D Video(CVPR2024)

1

37

217

Ryohei Sasaki

@rsasaki0109

4 months

Direct LiDAR Odometry: Fast Localization with Dense Point Clouds A lightweight and computationally-efficient frontend LiDAR odometry solution with consistent and accurate localization.

0

50

216

Ryohei Sasaki

@rsasaki0109

1 year

The paper outlines a new method for large-scale 3D reconstruction with LiDAR data. It utilizes an octree-based structure and a shallow neural network for data processing, and an incremental mapping system for continual learning.(ICRA' 23)

1

40

211

Ryohei Sasaki

@rsasaki0109

4 months

Camera, LiDAR, and IMU Based Multi-Sensor Fusion SLAM: A Survey

1

34

214

Ryohei Sasaki

@rsasaki0109

7 months

> Neural A* is a novel data-driven search-based planner that consists of a trainable encoder and a differentiable version of A* search algorithm called differentiable A* module. Official implementation of "Path Planning using Neural A* Search"

1

43

217

Ryohei Sasaki

@rsasaki0109

1 year

nvidia-isaac/nvblox A GPU-accelerated TSDF and ESDF library for robots equipped with RGB-D cameras.

0

42

209

Ryohei Sasaki

@rsasaki0109

2 months

point_lio_unilidar Point-LIO for Unitree L1 LiDAR.

2

28

214

Ryohei Sasaki

@rsasaki0109

8 months

dwa_planner ROS implementation of DWA(Dynamic Window Approach) Planner

0

26

209

Ryohei Sasaki

@rsasaki0109

5 months

Recognize Anything The Recognize Anything Model (RAM) can recognize any common category with high accuracy. When combined with localization models (Grounded-SAM), RAM forms a strong and general pipeline for visual semantic analysis.

0

45

208

Ryohei Sasaki

@rsasaki0109

3 months

TinyMPCTh Pytorch Implementation of TinyMPC, a lightweight ADMM-based mpc solver. TinyMPC is division-free and requires no matrix factorization, which makes it robust and efficient.

0

35

207

Ryohei Sasaki

@rsasaki0109

2 months

RoboticsAcademy: Learn Robotics, Artificial Intelligence and Computer Vision

0

40

205

Ryohei Sasaki

@rsasaki0109

5 years

TLでカルマンフィルターが話題なので紹介したいのですが、以下の記事が・測定できない値を推測できる・外乱にも対応できる・モデルが間違っていても、その情報をプロセスノイズに入れて推測できるとKFでできることが書いてあり、余談も示唆に富んでで神記事です。

パラメータ推定（２）カルマンフィルター - Qiita

はじめにパラメータ推定（１）では，線形最小二乗法によるパラメータ推定について述べてみました．今回は拡張カルマンフィルター（EKF：Extended Kalman Filter）と呼ばれる手法による…

qiita.com

1

42

204

Ryohei Sasaki

@rsasaki0109

2 months

Lidar With Velocity: Correcting Moving Objects Point Cloud Distortion From Oscillating Scanning Lidars by Fusion With Camera

0

33

199

Ryohei Sasaki

@rsasaki0109

7 months

Point-SLAM introduces a technique for RGBD using a point-based scene representation. Differing from traditional grid-based methods, this model adjusts anchor point density based on input information density, enhancing efficiency and accuracy(ICCV'23)

1

30

198

Ryohei Sasaki

@rsasaki0109

3 months

beluga A general implementation of Monte Carlo Localization (MCL) algorithms written in C++17, and a ROS package that can be used in ROS 1 and ROS 2.

2

35

195

Ryohei Sasaki

@rsasaki0109

2 months

SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction（CVPR 2024） > SelfOcc empowers 3D autonomous driving world models (e.g., OccWorld) with scalable 3D representations, paving the way for interpretable end-to-end large driving models. Trained…

1

45

195

Ryohei Sasaki

@rsasaki0109

1 year

The Topological Semantic Graph Memory framework enables robots to efficiently navigate unknown environments using landmark-based graph memory collected via an RGB-D camera, outperforming existing methods and demonstrating success in real-world scenarios

0

45

191

Ryohei Sasaki

@rsasaki0109

3 months

sr_livo A LiDAR-inertial-visual odometry and mapping system based on the sweep reconstruction method > SR-LIVO is designed based on the framework of R3Live. > We employ the sweep reconstruction method to align reconstructed sweeps with image timestamps

2

41

193

Ryohei Sasaki

@rsasaki0109

8 months

Fuzzy Metaballs+ use 3D Gaussians for differentiable rendering, integrating optical flow and producing watertight meshes. These techniques ensure speedy, reliable reconstructions on both GPU and CPU.

0

36

192

Ryohei Sasaki

@rsasaki0109

4 months

IMUNet: Efficient Regression Architecture for IMU Navigation and Positioning

0

26

192

Ryohei Sasaki

@rsasaki0109

3 months

NF-Atlas: Multi-Volume Neural Feature Fields for Large Scale LiDAR Mapping

1

34

191

Ryohei Sasaki

@rsasaki0109

6 months

google-research/ibc Implicit Behavioral Cloning Implicit BC policy on a precise, 1-millimeter-tolerance slide-then-insert task: push a block across a table, then slide it into a slot.

3

34

184

Ryohei Sasaki

@rsasaki0109

3 months

RAP-SAM:Towards Real-Time All-Purpose Segment Anything

1

44

186

Ryohei Sasaki

@rsasaki0109

6 months

curobo CUDA Accelerated Robot Library > CuRobo is a CUDA accelerated library containing a suite of robotics algorithms that run significantly faster than existing implementations leveraging parallel compute.

1

33

183

Ryohei Sasaki

@rsasaki0109

2 months

LiDeNeRF: Neural Radiance Field Reconstruction with Depth Prior Provided by LiDAR Point Cloud

0

35

182

Ryohei Sasaki

@rsasaki0109

3 months

Calib-Anything: Zero-training LiDAR-Camera Extrinsic Calibration Method Using Segment Anything

2

25

182

Ryohei Sasaki

@rsasaki0109

2 months

Single-Shot Global Localization via Graph-Theoretic Correspondence Matching

1

29

182

Ryohei Sasaki

@rsasaki0109

2 years

PFNの方のSLAM開発における評価/チューニング/テストに関する資料 SLAM開発における課題と対策の一例の紹介

SLAM開発における課題と対策の一例の紹介

SLAM開発における課題と対策の一例の紹介 - Download as a PDF or view online for free

www.slideshare.net

0

26

181

Ryohei Sasaki

@rsasaki0109

6 months

lightNet-TRT > LightNet-TRT is a high-efficiency and real-time implementation of convolutional neural networks (CNNs) using Edge AI.

0

30

179

Ryohei Sasaki

@rsasaki0109

1 month

Loopy-SLAM: Dense Neural SLAM with Loop Closures (CVPR2024)

2

31

182

Ryohei Sasaki

@rsasaki0109

5 months

DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images

1

36

180

Ryohei Sasaki

@rsasaki0109

3 months

OASim: an Open and Adaptive Simulator based on Neural Rendering for Autonomous Driving

0

32

179

Ryohei Sasaki

@rsasaki0109

3 months

A demo of bundle adjustment has been added to "MathematicalRobotics", a python sample code library that utilizes Lie algebra in robotics algorithms👀

2

31

178

Ryohei Sasaki

@rsasaki0109

11 months

The software by zhm-real is a collection of key algorithms for autonomous vehicle planning and tracking, featuring Hybrid A* Planner, Frenet Optimal Trajectory, and multiple controllers. Hybrid A* Planner

1

32

177

Ryohei Sasaki

@rsasaki0109

2 years

強強な後輩が作った自己位置推定ソフトウェアが公開されました🥳 hawkeye Hawkeye - Localization with LiDAR, GNSS/INS and ortho image map Youtube

Hawkeye - LiDAR Localization using Intensity Map (with Ground...

null

www.youtube.com

0

30

177

Ryohei Sasaki

@rsasaki0109

4 months

FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators

1

21

178

Ryohei Sasaki

@rsasaki0109

6 months

pytorch-labs/segment-anything-fast A batched offline inference oriented version of segment-anything

GitHub - pytorch-labs/segment-anything-fast: A batched offline inference oriented version of...

A batched offline inference oriented version of segment-anything - pytorch-labs/segment-anything-fast

github.com

0

25

176

Ryohei Sasaki

@rsasaki0109

2 months

Khronos Spatio-Temporal Metric-Semantic SLAM > Khronos is a unified approach that can reason about short-term dynamics and long-term changes when performing online metric-semantic simultaneous mapping and localization (SLAM) in dynamic environments

1

36

174

Ryohei Sasaki

@rsasaki0109

5 months

100 SLAM-related technical interview questions

100 questions on SLAM, from theory to system design and live coding interview.

www.cv-learn.com

4

27

173

Ryohei Sasaki

@rsasaki0109

4 months

LMDrive Closed-Loop End-to-End Driving with LLM An end-to-end, closed-loop, language-based autonomous driving framework, which interacts with the dynamic environment via multi-modal multi-view sensor data and natural language instructions

5

35

175

Ryohei Sasaki

@rsasaki0109

4 months

torch-bakedsdf An unofficial pytorch implementation of Meshing Neural SDFs for Real-Time View Synthesis.

1

25

173

Ryohei Sasaki

@rsasaki0109

5 months

PatchFusion An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation

1

34

174

Ryohei Sasaki

@rsasaki0109

7 months

GraphBasedLocalTrajectoryPlanner for autonomous race vehicles employs a multilayer graph framework, providing optimal, feasible actions, and has demonstrated success in real-world applications at speeds above 200kph during Roborace Season Alpha.

0

37

174

Ryohei Sasaki

@rsasaki0109

7 months

python_simple_mppi Python implementation of MPPI(Model Predictive Path-Integral) controller to understand the basic idea. Mandatory dependencies are numpy and matplotlib only.

1

24

171

Ryohei Sasaki

@rsasaki0109

4 months

TextSLAM: Visual SLAM with Semantic Planar Text Features. (ICRA2020 & TPAMI2023)

0

31

172

Ryohei Sasaki

@rsasaki0109

5 months

cuda-efficient-features A CUDA implementation of keypoint detection and descriptor extraction

2

29

171

Ryohei Sasaki

@rsasaki0109

5 months

Awesome-Robotics-Foundation-Models

2

39

168

Ryohei Sasaki

@rsasaki0109

5 months

SLAMBOX is designed for use metod SLAM in education, experiments, research and development by Node-based user interface. This is a box with tools that you can quickly and conveniently experiment with separate SLAM nodes

2

29

170

Ryohei Sasaki

@rsasaki0109

5 months

Awesome-3D-LiDAR-Datasets This reposiotry is the collection for public 3D LiDAR datasets

1

33

170

Ryohei Sasaki

@rsasaki0109

3 months

DMSTrack Probabilistic 3D Multi-Object Cooperative Tracking for Autonomous Driving via Differentiable Multi-Sensor Kalman Filter(ICRA2024)

1

26

167

Ryohei Sasaki

@rsasaki0109

2 months

ORB-SLAM3-python Python binding for ORB-SLAM3.

GitHub - xingruiyang/ORB-SLAM3-python: Python binding for ORB-SLAM3.

Python binding for ORB-SLAM3. Contribute to xingruiyang/ORB-SLAM3-python development by creating an account on GitHub.

github.com

1

27

167

Ryohei Sasaki

@rsasaki0109

6 months

[RA-L 2023] Official Code Release for LONER: LiDAR Only Neural Representations for Real-Time SLAM

0

41

168

Ryohei Sasaki

@rsasaki0109

6 months

TinyMPC Model-predictive control on resource-constrained microcontrollers Efficient/Robust/Free(Apache 2.0)/Embeddable/Multi-interface(C/C++, Matlab, Python, Julia)/Dependency-minimal(Only Eigen)

GitHub - TinyMPC/TinyMPC: Model-predictive control for microcontrollers

Model-predictive control for microcontrollers. Contribute to TinyMPC/TinyMPC development by creating an account on GitHub.

github.com

1

20

167

Ryohei Sasaki

@rsasaki0109

6 months

libRSF is a robust C++ library for sensor fusion with sliding window filtering, predefined cost functions, and robust error models, leveraging Ceres Solver libRSF A robust sensor fusion library for online localization.

1

34

164

Ryohei Sasaki

@rsasaki0109

4 months

👀 autowarefoundation/autoware.universe Pull Request feat(localization): add nerf_based_localizer #ROS2

2

39

165

Ryohei Sasaki

@rsasaki0109

2 months

Consistent4D: Consistent 360° Dynamic Object Generation from Monocular Video

0

28

166

Ryohei Sasaki

@rsasaki0109

2 months

RoadNet [ICCV2023 Oral] RoadNetworkTRansformer & [AAAI 2024] LaneGraph2Seq Road Network and Lane Topology Extraction

0

31

164

Ryohei Sasaki

@rsasaki0109

5 months

PrimA6D++ PrimA6D++ estimates three rotation axis primitive images and their associated uncertainties.

0

24

162

Ryohei Sasaki

@rsasaki0109

4 months

R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras [ICCV 2023]

0

23

163

Ryohei Sasaki

@rsasaki0109

2 months

[ICLR'24] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching

0

30

164

Ryohei Sasaki

@rsasaki0109

1 year

RGB-D画像のマッチング精度を向上させるための画像特徴抽出と融合手法を提案。 SIFT、SURF、ORB特徴量とPFH、FPFH特徴量を組み合わせた特徴量を使用し、誤マッチングを減少させている。 GlueStick: Robust Image Matching by Sticking Points and Lines Together

1

20

161

Ryohei Sasaki

@rsasaki0109

2 months

monoforce Robot-terrain interaction prediction from only RGB images as input.

0

25

161