Skip to content
Agientry
← Tags

#SLAM (47)

WaterfallPagination
Grounded API: Robot Perception and SLAM
1:14

Grounded API: Robot Perception and SLAM

@GroundedSI · 110 views · 2026-09-16
Robot perceptionSLAMHand Tracking
GeoFlow-SLAM: A Robust Tightly-Coupled RGBD-Inertial and Legged Odometry Fusion SLAM for Dynamic Legged Robotics

GeoFlow-SLAM: A Robust Tightly-Coupled RGBD-Inertial and Legged Odometry Fusion SLAM for Dynamic Legged Robotics

GeoFlow-SLAM targets the feature-matching, initialization, and texture-robustness failures that arise when legged robots move aggressively at high frequency. It tightly couples dual-stream optical flow, legged odometry, PnP, GICP, and depth-to-map geometric constraints in one optimization framework. Experiments on Unitree Go2 and G1 robots plus OpenLORIS, ScanNet, and TUM datasets show state-of-the-art robustness and accuracy.

Xiao, Tingyang, Zhou, Xiaolin, Liu, LiuMar 18, 2025
SLAMLegged RoboticsRGBD-InertialMar 18, 2025
microSLAM: Monocular SLAM for Interactive 3D Environments
3:30

microSLAM: Monocular SLAM for Interactive 3D Environments

@ZenoInMotion · 175 views · 2026-09-10
SLAMMonocular Vision3D reconstruction
UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization

UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization

Recent geometric foundation models enable feed-forward inference for SLAM, but their predictions are strongly dependent on the input view set, which leads to geometric inconsistencies and trajectory drift when results are chained over long sequences. Online deployment further exposes a trade-off between the low latency of two-view tracking and the constraint richness of multi-view inference. We introduce UniSim-SLAM, an integrated system that runs lightweight two-view keyframe tracking in the frontend and performs periodic multi-view submap refinement in the backend. To combine predictions defined in heterogeneous local coordinates with inconsistent scales, we formulate a unified multi-level factor graph on Sim(3) that jointly optimizes global keyframe poses and submap poses. The graph integrates temporal view-to-view odometry edges, view-to-submap bridge edges with depth-statistics scale anchoring, and submap-to-submap tie and scale constraints to enforce consistent similarity relations across submaps. Experiments on TUM RGB-D and 7-Scenes show that UniSim-SLAM achieves state-of-the-art accuracy in the uncalibrated setting, reducing trajectory error by 38.5% on TUM RGB-D and 45.9% on 7-Scenes compared to prior best results. Project page: https://vision3d-lab.github.io/unisim-slam/

Inha Lee, Dongjae Jeong, Junhee LeeAug 3, 2026
SLAM3D VisionLocalizationAug 3, 2026
VidMap at ECCV 2026: Video-Based Structure-from-Motion

VidMap at ECCV 2026: Video-Based Structure-from-Motion

@pesarlin · 218 views · 2026-09-07
Structure-from-Motion3D reconstructionCamera Pose Estimation
Build Your Own Mini Pupper Open-Source Quadruped
0:10

Build Your Own Mini Pupper Open-Source Quadruped

@Alacritic_Super · 175 views · 2026-09-04
Mini PupperOpen-source quadrupedROS
Axioma: Open-Source ROS 2 Robot for Mapping and Autonomous Navigation
0:47

Axioma: Open-Source ROS 2 Robot for Mapping and Autonomous Navigation

@Alacritic_Super · 809 views · 2026-09-03
ROS2SLAMNav2
glass-LIO: A LiDAR-Inertial Odometry Written to Be Read — 10 Write-ups, a 200-Line Solver, and Fully Documented Bugs

glass-LIO: A LiDAR-Inertial Odometry Written to Be Read — 10 Write-ups, a 200-Line Solver, and Fully Documented Bugs

glass-LIO is an open-source scan-to-map LiDAR-inertial odometry for the Livox MID-360, described by its author as “written to be read”: each of its six pipeline stages has a deep-dive write-up, the manifold Gauss-Newton solver is under 200 lines of Eigen with no Ceres/GTSAM, and every bug that produces plausible output is documented — including the full failure post-mortem of tight coupling diverging on real data. It runs real time at 10 Hz on the test bag with zero dropped scans and steady RMSE around 0.13 m.

BLOG

SLAMLiDAR-Inertial OdometryLivox MID-360Lie AlgebraOpen Source Tutorial
HEYN H1Inspection

HEYN H1

InspectionWheeled
ABot-Recon Streaming 3D Reconstruction
0:15

ABot-Recon Streaming 3D Reconstruction

@IndieDevHailey · 208 views · 2026-08-29
SLAMAMapABot-Recon
DL-SLAM: Enabling High-Fidelity Gaussian Splatting SLAM in Dynamic Environments based on Dual-Level Probability

DL-SLAM: Enabling High-Fidelity Gaussian Splatting SLAM in Dynamic Environments based on Dual-Level Probability

Recent advances in 3D Gaussian Splatting (3DGS) have enabled significant progress in dense dynamic Simultaneous Localization And Mapping (SLAM). Prevailing methods typically discard predefined dynamic objects, ignoring that transiently static objects offer valuable geometric constraints for pose estimation. A recent work attempts to leverage this potential by employing per-pixel uncertainty maps to quantify the magnitude of motion. While this approach enables transiently static objects to enhance pose estimation, it erroneously integrates these objects into the static map, resulting in persistent artifacts. Moreover, its reliance on purely geometric information leads to ambiguous object boundaries in the uncertainty maps. To overcome these limitations, we present DL-SLAM, a monocular Gaussian Splatting SLAM system built upon a novel dual-level probabilistic framework. Our method computes dynamic probability maps by combining semantic and geometric information. These pixel-level probabilities are lifted to 3D and aggregated to derive an object-level dynamic probability for each instance. Object-level probability enables the categorical pruning of dynamic Gaussians, resulting in an artifact-free static map. The static map, in turn, provides a geometrically consistent guidance to refine the pixel-wise probabilities, enhancing their reliability. Experimental results demonstrate that DL-SLAM outperforms existing approaches, improving tracking accuracy by up to 13% while generating high-fidelity semantic maps.

Ziheng Xu, Qingfeng Li, Xuefeng LiuJul 2, 2026
Dynamic EnvironmentSLAM3D Gaussian SplattingJul 2, 2026
ADI ADIS16501 Precision MEMS IMU

ADI ADIS16501 Precision MEMS IMU

Analog Devices (USA) ADIS16501 is a precision miniature MEMS IMU: triaxial digital gyroscope with ±500 °/s range, 2.7 °/h in-run bias stability, 0.15 °/√hr angular random walk (x/y, 1σ) and ±0.25° axis-to-axis misalignment; triaxial digital accelerometer with ±14 g range and 12.7 µg in-run bias stability (x/y). Each sensor is factory calibrated for sensitivity, bias, alignment, linear acceleration (gyro bias) and point of percussion; the SPI interface and register structure simplify integration with automatic/manual bias correction. It survives 1500 g mechanical shock, operates from −40 to +105 °C in a 100-ball BGA module, and ships with official Linux driver, ROS2 driver and PyADI-IIO support — a mainstream choice for humanoid robots, robot dogs and industrial mobile platforms.

COMPONENT

IMUMEMSADIPrecision gradeHumanoid
ADI ADIS16505 Precision Miniature MEMS IMU

ADI ADIS16505 Precision Miniature MEMS IMU

Analog Devices (USA) ADIS16505 is the iSensor precision miniature MEMS IMU, offered with ±125/±500/±2000 °/s gyro range models (ADIS16505-1/2/3). The ADIS16505-1 achieves 2.3 °/h in-run bias stability, 0.13 °/√hr angular random walk (x/y axes, 1σ) and ±0.25° axis-to-axis misalignment; the triaxial digital accelerometer spans ±78.4 m/s² (±8 g). All axes are factory calibrated for sensitivity, bias and alignment over −40 to +85 °C; SPI interface with automatic/manual bias correction, −40 to +105 °C operation in an ~15 × 15 × 5 mm 100-ball BGA package. A common core sensor for high-accuracy attitude estimation, SLAM and control on humanoid robots, robot dogs and autonomous platforms.

COMPONENT

IMUMEMSADIPrecision gradeHumanoid
ADI ADIS16470 Wide Dynamic Range Miniature MEMS IMU

ADI ADIS16470 Wide Dynamic Range Miniature MEMS IMU

Analog Devices (USA) ADIS16470 is the iSensor wide-dynamic-range miniature MEMS IMU, integrating triaxial digital gyroscope and accelerometer with signal conditioning in an ~11 × 15 × 11 mm 44-ball BGA module. Gyro full range ±2000 °/s with 8 °/h in-run bias stability and 0.008 °/s/√Hz rate noise density; accelerometer ±40 g range. Every axis is factory calibrated for sensitivity, bias and alignment (calibration range −10 to +75 °C); SPI interface with automatic/manual bias correction, −25 to +85 °C operation. With its high dynamics and low drift, the ADIS16470 is widely used for SLAM, attitude estimation and stabilization on humanoid robots, robot dogs, drones and mobile platforms.

COMPONENT

IMUMEMSADITactical gradeHumanoid
Inside SuperMap: Persistent 3D Object Identities
0:36

Inside SuperMap: Persistent 3D Object Identities

@robotsdigest · 196 views · 2026-08-16
SLAMSuperMapSuperOdometry
SuperMap Turns SLAM into Persistent 4D Spatial Memory
3:52

SuperMap Turns SLAM into Persistent 4D Spatial Memory

@robotsdigest · 179 views · 2026-08-16
SLAMSuperMapSpatial memory
Slamtec RPLIDAR A2 2D LiDAR

Slamtec RPLIDAR A2 2D LiDAR

RPLIDAR A2 is Slamtec's classic 2D LiDAR: 0.2-16 m, 16 kHz sampling, 0.225° resolution, 360° at 10 Hz, the go-to sensor for robot navigation, SLAM and research.

COMPONENT

LiDAR2DSLAMeducation and researchNavigation
Slamtec RPLIDAR S3 2D TOF LiDAR

Slamtec RPLIDAR S3 2D TOF LiDAR

RPLIDAR S3 offers 40 m range, 32 kHz sampling and 360° scanning in a 55.6 mm body with high resolution and low noise for AGVs and outdoor mapping.

COMPONENT

LiDAR2DTOFAGVSLAM
Slamtec RPLIDAR S2 2D TOF LiDAR

Slamtec RPLIDAR S2 2D TOF LiDAR

RPLIDAR S2 is Slamtec's 2D TOF LiDAR for commercial robots: 30 m range at 90% reflectivity, 32 kHz sampling, 0.1125° angular resolution, 360° FOV at 10 Hz, stable on mirrors and glass.

COMPONENT

LiDAR2DTOFSLAMService robots
Ouster OS0 Ultra-Wide View High-Resolution Imaging Lidar

Ouster OS0 Ultra-Wide View High-Resolution Imaging Lidar

The Ouster OS0 is the Rev8 ultra-wide short-range imaging lidar: 90 deg vertical FOV (+45 to -45) and 360 deg horizontal, 32/64/128 channels, 512-4096 horizontal columns (0.088 deg angular resolution at 4096) and 5-40 Hz configurable rotation. In 1024 @ 10 Hz mode it reaches 75 m on 80% Lambertian targets and 35 m on 10% targets, both at >90% detection probability under 100 klx sunlight, with 500 m max representable range and a minimum range configurable down to 0 m (0.5 m default, 0.3 m optional). Range accuracy is +/-1.25 cm (Lambertian) / +/-2.5 cm (retroreflective) - 2x better precision and accuracy than Rev7 - at 0.1 cm range resolution, with up to 2 returns and 10,485,760 points per second; the 865 nm laser is Class 1 eye-safe. Native RGB-D color point cloud (116 dB dynamic range) carries RGB, range, signal, reflectivity, NIR, channel, azimuth and timestamp per point, with a synchronous IMU at 640/1280/2560 Hz. Data leaves over gigabit Ethernet UDP with PTP/gPTP/NMEA/PPS time sync (<1 ms error) and <10 ms latency. It runs from 12/24 VDC (9-58 V) at 10-20 W, measures 87 mm diameter x 58.35 mm and weighs 500 g (580 g with halo cap); IP68/IP69K, -40 to +85 C (Rev7 was +60 C), 100 g shock, 10 Grms vibration and MTTF over 250,000 h. Engineered for functional safety (ASIL-B, SIL-2, PLd) with an on-sensor 3D Zone Monitor and designed for cybersecurity to ISO 21434 / UNECE WP.29 / IEC 62443 / ISO 27001. Built for AMRs, AGVs, inspection robots, heavy machinery, drones and mapping solutions that need close-range blind-spot perception and high-accuracy 3D modeling.

COMPONENT

LiDAROusterRGB-DUltra-Wide AngleShort Distance
Velodyne Puck Hi-Res High-Resolution 3D LiDAR

Velodyne Puck Hi-Res High-Resolution 3D LiDAR

Velodyne Puck Hi-Res is the high-resolution Puck: 16 channels, 360x20 deg FOV (+10 to -10), 1.33 deg vertical resolution, 100 m range at +/-3 cm, 0.1-0.4 deg azimuth, 5-20 Hz; 905 nm Class 1 eye-safe, 8 W, ~750 g, 0 to +60 C. Denser point clouds for inspection, surveying and fine-grained mapping.

COMPONENT

LiDARHigh-Resolution16-beam360°Inspection
Velodyne Puck LITE Lightweight 3D LiDAR

Velodyne Puck LITE Lightweight 3D LiDAR

Velodyne Puck LITE is the lightweight Puck: 16 channels, 360x30 deg FOV, 100 m range at +/-3 cm, 2.0 deg vertical resolution, 0.1-0.4 deg azimuth, 5-20 Hz, ~600k pts/s; 903 nm Class 1 eye-safe, 8 W, only ~590 g, -10 to +60 C. Ideal for payload-sensitive platforms like UAVs and inspection robots.

COMPONENT

LiDARLightweight16-beam360°Drones
Velodyne Ultra Puck VLP-32C 3D LiDAR Sensor

Velodyne Ultra Puck VLP-32C 3D LiDAR Sensor

Velodyne Ultra Puck VLP-32C is the 32-channel 3D LiDAR workhorse: 360x40 deg FOV (-25 to +15), 200 m range at +/-3 cm, 0.33 deg vertical resolution, 0.1-0.4 deg azimuth, 5-20 Hz, up to 1.2M pts/s dual return; 905 nm Class 1 eye-safe, 10 W, ~925 g in a 103x86.9 mm housing, -20 to +60 C. A mainstream pick for inspection robots, UGVs and autonomous driving perception.

COMPONENT

LiDAR32 Lines360°InspectionAGV
RoboSense Fairy 96-Beam Ultra-Compact LiDAR

RoboSense Fairy 96-Beam Ultra-Compact LiDAR

RoboSense Fairy is an ultra-compact LiDAR for robots and inspection devices: 96/48-beam options, 360x32 deg FOV, 150 m range, 0.5 cm (1 sigma) precision, ~1.37M pts/s on the 96-beam version; under 350 g in a 75x70 mm cylinder. Built for UAVs, inspection robots and AGV perception and SLAM.

COMPONENT

LiDAR96 LinesUltra-compactDronesInspection