#SLAM (53)

LT-Mem: Volatility-Aware Spatio-Temporal Memory for Lifelong Scene Understanding

DGIST team, accepted to IROS 2026. Robots operating long-term revisit evolving environments; existing systems either overwrite history to keep an up-to-date map or store semantic snapshots without cross-session object identity — the authors call this temporal amnesia: unable to answer "Where has the green chair been across all sessions?" LT-Mem is a three-layer solution: (1) Perception: MASt3R-SLAM multi-session alignment (Sim(3) anchors + inter-session loop closures + joint g2o optimization) plus SAM3 instance segmentation extracting per-object centroid/volume/visual embedding; (2) Reasoning: five evidence scores (E1 spatial proximity, E2 temporal continuity, E3 feature similarity as the primary signal w=0.45, E4 motion consistency, E5 occlusion handling) drive deterministic cross-session re-identification, with a constrained LLM judge only for ambiguous cases (MATCH/NEW-TRACK/HOLD); a structural integrity check triggers a session-wide HOLD on alignment failure; a volatility score V accumulates evidence in a Bayesian manner (Eq.2, one-time LLM prior), selecting among OVERWRITE/HOLD/MULTI-HYPOTHESIS updates; (3) Tri-Memory: Live stores current states, Delta logs timestamped events (APPEAR/DISAPPEAR/MOVE/RE-APPEAR/NONE), Meta accumulates volatility statistics feeding back into the update policy. The paper releases LT-VQA (two indoor envs, 10 objects × 10 sessions each, plus an outdoor parking lot over 10 sessions; 61 state-change events and 80 QA pairs). Results: Event F1 0.910 / QA-Event 0.820 / QA-Freq 0.600, beating Geometric/Text-Batch/VLM-Batch/STAR baselines across the board, with 438K tokens — 1/16 of VLM-Batch (7,114K) and 1/100 of STAR (45,859K); swapping in Qwen2.5-3B still reaches 0.885, showing the gains come from the structured memory architecture rather than LLM capacity. Ablations: removing re-identification collapses F1 to 0.140; removing volatility-awareness drops it to 0.615. Scene-level statistics on the parking lot even answer "when should I go to find a parking spot" (8:00 AM, 0 cars vs 1:03 PM, 34 cars).

Yumin Lee, Hyoseok Ju, Giseop Kim · 415 views · Aug 19, 2026

SLAMLong-Term-AutonomyScene UnderstandingAug 19, 2026

ROS Tutorial 15 Deep Read: robot_localization — from wheel odometry & IMU to robot state estimation

A deep read of chapter 15 of wdfk-prog's ROS tutorial series: why you need robot_localization even when the driver already publishes /odom. Covers EKF vs UKF predict-correct over 15 states (31 sigma points), the real roles of P/Q/R covariances, the data-provenance thinking behind 15-bit _config switches, the semantic gap between differential (velocity) and relative (pose), TF ownership refactoring (/odom→/odom/raw, EKF takes over odom→base_link), world_frame and sensor_timeout time semantics, and the contract-first mindset: every observation must answer who measured it, in which frame, at which time, and how trustworthy it is.

BLOG

ROSrobot_localizationEKFUKFTF

1:06

AMB3R-SLAM: kilometer-scale real-time SLAM on a single consumer GPU, no bundle adjustment needed

@rsasaki0109 · 525 views · 2026-09-30

SLAMPerceptionDynamic Scene

1:22

Matic: Build Home Robots Eyes First, Hands Later

@mehul · 588 views · 2026-09-29

Home RobotService robotsSLAM

GaussLite: Online Task-Conditioned 3D Gaussian Splatting for Real-Time Robotic Mapping

MIT presents GaussLite, the first 3DGS mapping system that takes a natural-language task and allocates representation capacity online by task relevance: a one-shot LLM parser extracts target and anchor objects, Grounding DINO + FastSAM ground them per frame into relevance masks that steer seeding density, gradient flow and initial scale. At matched Gaussian budget and real-time 4 Hz mapping, ROI PSNR improves by +2.72 dB on Replica and +2.23 dB on real campus scenes; multi-agent maps fuse via per-voxel voting on active-optimization counts, beating concatenation by +3.42 dB while sharing only 7.08% of the map.

Thomas, Annika, Peterson, Mason, How, Jonathan P. · 608 views · Jun 29, 2026

3D Gaussian SplattingSLAMRobotic MappingJun 29, 2026

FreeOcc: Training-Free Embodied Open-Vocabulary Occupancy Prediction

Existing occupancy prediction relies on large-scale voxel annotations and generalizes poorly across environments, collapsing to near-zero per-class scores on unseen scenes. FreeOcc is the first training-free framework for open-vocabulary occupancy prediction: a SLAM backbone supplies poses and sparse geometry, geometrically anchored Gaussian updates build a dense 3DGS map (ray-aligned anisotropic initialization with s_parallel = gamma * s_perp and Gaussian centers fixed to SLAM points), an off-the-shelf vision-language model attaches open-vocabulary semantics to Gaussian primitives, and a probabilistic Gaussian-to-occupancy projection yields a voxel field queryable online, with no learnable parameter serving the occupancy task. On EmbodiedOcc-ScanNet it reaches 31.29/13.86 monocular and 34.40/15.84 RGB-D IoU/mIoU, more than double the self-supervised baselines; geometric IoU improves 76.1% over the next-best DROID-Splat. The paper also introduces ReplicaOcc, where learned baselines collapse to 0.00-0.01 while FreeOcc transfers zero-shot to 55.65/20.90 and runs online at 25 FPS on a live RealSense D435i stream.

Jiang, Zeyu, Zhou, Changqing, Zuo, Xingxing · 794 views · Apr 30, 2026

3D Gaussian SplattingOccupancy PredictionSLAMApr 30, 2026

1:14

Grounded API: Robot Perception and SLAM

@GroundedSI · 766 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 (Horizon Robotics, IROS 2025) targets three stacked failure modes of quadruped localization: motion blur and IMU distortion from fast locomotion, and feature scarcity in texture-less scenes. Three interlocking contributions: dual-stream optical-flow tracking aided by prior map points and poses (a 3D-to-2D reprojection stream plus a 2D-to-2D fallback stream); a pose-initialization priority chain degrading from leg odometry to IMU, PnP, GICP, and finally a constant-velocity model; and a tightly-coupled optimization framework placing depth-to-map point-to-plane and GICP relative-pose residuals alongside visual reprojection and IMU pre-integration in one factor graph. On four real Go2 sequences (office, texture-less corridor, underground parking, open plaza) it is the only method that succeeds on Seq2-4, with 88% improvement over VINS-RGBD on Seq1. ScanNet mean ATE 0.0779 m (~70% better than ORB-SLAM3), TUM 0.0129 m; global plane-feature maps are still built in the structure-less texture-less TUM extremes. Code and data are open source (HorizonRobotics/GeoFlowSlam).

Xiao, Tingyang, Zhou, Xiaolin, Liu, Liu · 559 views · Mar 18, 2025

SLAMLocalizationQuadruped robotsMar 18, 2025

3:30

microSLAM: Monocular SLAM for Interactive 3D Environments

@ZenoInMotion · 709 views · 2026-09-10

SLAMMonocular Vision3D reconstruction

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 Lee · 559 views · Aug 3, 2026

SLAM3D VisionLocalizationAug 3, 2026

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

Inspection

HEYN H1

InspectionWheeled

0:15

ABot-Recon Streaming 3D Reconstruction

@IndieDevHailey · 607 views · 2026-08-29

SLAMAMapABot-Recon

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 Liu · 622 views · Jul 2, 2026

Dynamic EnvironmentSLAM3D Gaussian SplattingJul 2, 2026

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

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

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

0:36

Inside SuperMap: Persistent 3D Object Identities

@robotsdigest · 658 views · 2026-08-16

SLAMSuperMapSuperOdometry

3:52

SuperMap Turns SLAM into Persistent 4D Spatial Memory

@robotsdigest · 626 views · 2026-08-16

SLAMSuperMapSpatial memory

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

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

As an Amazon Associate, we earn from qualifying purchases.

#SLAM (53)

LT-Mem: Volatility-Aware Spatio-Temporal Memory for Lifelong Scene Understanding

ROS Tutorial 15 Deep Read: robot_localization — from wheel odometry & IMU to robot state estimation

AMB3R-SLAM: kilometer-scale real-time SLAM on a single consumer GPU, no bundle adjustment needed

Matic: Build Home Robots Eyes First, Hands Later

GaussLite: Online Task-Conditioned 3D Gaussian Splatting for Real-Time Robotic Mapping

FreeOcc: Training-Free Embodied Open-Vocabulary Occupancy Prediction

Grounded API: Robot Perception and SLAM

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

microSLAM: Monocular SLAM for Interactive 3D Environments

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

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

Build Your Own Mini Pupper Open-Source Quadruped

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

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

HEYN H1

ABot-Recon Streaming 3D Reconstruction

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

ADI ADIS16501 Precision MEMS IMU

ADI ADIS16505 Precision Miniature MEMS IMU

ADI ADIS16470 Wide Dynamic Range Miniature MEMS IMU

Inside SuperMap: Persistent 3D Object Identities

SuperMap Turns SLAM into Persistent 4D Spatial Memory

Slamtec RPLIDAR A2 2D LiDAR

Slamtec RPLIDAR S3 2D TOF LiDAR