a robot can recognize every object in a room and still not know how to open a single drawer knowing there's a cabinet is scene understanding. knowing which handle to grab, which direction to pull, and that it's a drawer not a door is affordance understanding almost no dataset has it in 3D SceneFun3D: 14,800+ functional elements across 710 laser-scanned indoor scenes. every handle, knob, button, and switch labeled with its affordance, motion axis, motion type, and a natural language task description each scene's 3D point cloud with its iPad video recordings in fiftyone. the affordance annotations live in 3D and project into the video frames check it out here huggingface.co/datasets/Voxe…

tilt a lidar 45 degrees and every SLAM assumption tilts with it camera-lidar overlap shrinks, upper beams go sparse, standard odometry drifts. that's exactly how compact mobile mapping rigs are built in the real world. the lidar tilts so it sweeps more vertical structure. but almost no benchmark tests this configuration YUTO MMS from York University: a tilted 32-beam lidar, a 6-lens panoramic camera, and GPS/INS with cm-level ground truth driven through Toronto. every lidar point is RGB-colorized from the nearest panoramic frame, not a synthetic colormap loaded as mcap in fiftyone for your viewing pleasure scrub the timeline and watch the world-frame 3D map build itself progressively alongside the panoramic camera, GPS track, and IMU telemetry checkout the dataset here: huggingface.co/datasets/Voxe… it's running as a live space too, nothing to install: huggingface.co/spaces/harpre… #mcap #skills #computervision #ai #artificialintelligence #machinevision #machinelearning #physicalai

five images of the same pixel: color, depth, heat, ultraviolet, near infrared. MM5 captures RGB, depth, LWIR thermal, UV, and NIR together. pixel labels cover segmentation, instance segmentation, and classification under 8 RGB lighting conditions. an April 2026 update adds unaligned variants. Information Fusion, 2026. github.com/martinbrennernz/M… #PhysicalAI #ComputerVision

the paper behind the four-robot synthetic SLAM set. HERCULES puts 2 drones and 2 Husky UGVs in 4 environments: the Australian outback, a city block, dense forest, and one further site. Unreal Engine 5 with Lumen and Nanite. each robot has RGB, stereo, metric depth, 16-channel LiDAR, an IMU, and 320-class segmentation. about 1.1 TB on Hugging Face. the scenes are synthetic. arxiv.org/abs/2606.22756 #PhysicalAI #Robotics

attenuating the wake shows whether the detector was using it. Curated-Wake, also called HullWake, compares detector confidence before and after wake attenuation on aerial maritime images. it reports worst-group AP and the confidence drop, with wake marks beside hull marks. arxiv.org/abs/2608.26665 #PhysicalAI #ComputerVision

if you have a point cloud, a video, and an imu on three different clocks welcome, this account is for you the pipeline is always the same five steps and i've run it on VRS, rosbags, protobuf, and folders of pngs. everything ends up in MCAP with one timeline, and you can scrub it in fiftyone without installing anything not here to tell you which model to use. here to make sure you've seen your data reply with the format nobody on your team can open

i keep converting datasets to mcap and the pipeline is always the same five steps - read the native format - map streams to foxglove schemas - write messages in global time order -attach calibrations - verify sync. VRS, protobuf, rosbags, folders of pngs: the recipe doesn't change full walkthrough using the hardest case i've done covers authoring MCAP from scratch with the foxglove sdk: images, transforms, annotations, IMU, all written in global time order so playback stays synced. the same pattern works for any non-MCAP source you're sitting on build it yourself: voxel51.com/blog/aria-digita… #mcap #skills #computervision #ai #artificialintelligence #machinevision #machinelearning #physicalai

a robot can cross a hallway without hitting anyone and still make everyone in it uncomfortable collision-free and socially acceptable are different problems, and almost all navigation data only measures the first NavWareSet records the second NavWareSet records both. seven social navigation scenarios (frontal approach, blind corner, following, perpendicular crossing), each run twice under matched conditions: once with socially compliant behavior, once without. same room, same people, same starting positions. the only variable is whether the robot navigates like it knows humans have personal space robot onboard lidar and camera plus an overhead ground truth station tracking every pedestrian in 3D across the full episode loaded as native mcap in fiftyone. scrub the robot's camera, both lidar streams, and the annotated pedestrian trajectories on one synced timeline. filter by scenario and behavior to compare compliant vs non-compliant side by side start here, read the dataset card: huggingface.co/datasets/Voxe… #mcap #skills #computervision #ai #artificialintelligence #machinevision #machinelearning #physicalai

the spray behind a truck on a wet highway is solid to lidar and invisible to radar your camera sees a blur, your lidar sees a wall of false objects, and the disagreement is exactly the signal SemanticSpray++ from Ulm / BMW: 36 vehicle-following episodes on a closed wet airstrip, 50-130 km/h, with per-point semantic labels on both lidar and radar telling you exactly which returns are spray noise and which are the actual vehicle. plus 2D camera boxes and 3D lidar boxes on every frame loaded as native mcap in fiftyone so you can scrub camera, lidar, and radar together and watch the spray noise light up in the point cloud while the boxes track the lead vehicle through it checkout the dataset here: huggingface.co/datasets/Voxe… or get hands on with this hugging face space: huggingface.co/spaces/harpre… #mcap #skills #computervision #ai #artificialintelligence #machinevision #machinelearning #physicalai

seven cameras and a LiDAR on Indian city streets. no boxes in the files. this Minus Zero slice is 8 MCAP files, about 93 GB. cameras: front, front-left, front-right, front-tilted, rear, rear-left, rear-right. LiDAR is stored as autonome.LidarFrame protobuf, with GNSS and pose. video is H.265. recorded October 2025. CC BY-NC 4.0. a 1,469-file collection, about 3.2 TB, is the full set. huggingface.co/datasets/gaga… #PhysicalAI #AutonomousDriving

species labels at this count are rare in a vision set. TreeOfLife-200M holds 233M images across 933K taxa, labeled from kingdom through species. huggingface.co/datasets/imag… #PhysicalAI #BioML

lidar sees a blizzard as ten thousand small objects. radar sees nothing at all most driving datasets are shot on sunny days in california. Boreas is UTIAS's answer: 128-beam lidar, 360 degree radar, and 5MP camera driving the same Toronto route for a full year through sun, rain, and snow. 326,180 3D boxes for cars, pedestrians, and cyclists across 7,111 labeled frames loaded as native mcap in fiftyone so you can scrub camera, lidar, and radar on one synced timeline, and watch the 3D boxes render live on the point cloud and project onto the camera and radar images checkout the dataset here: huggingface.co/datasets/Voxe… or get hands-on with this hugging face space: huggingface.co/spaces/harpre… #mcap #skills #computervision #ai #artificialintelligence #machinevision #machinelearning #physicalai

closed-loop driving success on AlpaSim is up 33 percentage points. LaPla is a VQ-VAE latent-aligned vision-language-action planner. it predicts trajectories on multi-view driving video and reports L2 trajectory error. arxiv.org/abs/2609.04070 #PhysicalAI #AutonomousDriving

evaluating world collection usually runs into the same bottleneck: clean lab setups rarely match messy physical environments. World Collection captures the ground truth: 42 mathematically generated gazebo simulation worlds with programmatic python sdf generation and standardized start poses for navigation benchmarks. github.com/mertgulerx/world-…

the contour is where a segmentation model gets sure and wrong. RABR reads pixel-wise segmentation margin entropy and test-time augmentation variance along boundary contours to isolate overconfident failure regions. arxiv.org/abs/2609.12892 #PhysicalAI #ComputerVision