Marketplace
Real assets from creators on this instance — upload yours to get started.
107 results
Warehouse Navigation Dataset
Dataset for training autonomous robots in warehouse navigation
Autonomous Vehicle Traffic Data
Labeled traffic intersection data for autonomous vehicles
Robotic Arm Grasping
Neural network for robotic arms to pick and grasp objects
Humanoid Balance Dataset
Dataset for humanoid robot balance and recovery behaviors
Push & pull the chair — field capture
Real-world robot-training clip captured with Node GO. Task: Pull the chair out from the table, pause, then push it back in. Action class: push-pull · QC score: 79%
Robot Arm Package Sorting
Reinforcement learning environment for robot arm package sorting
Push & pull the chair — field capture
Real-world robot-training clip captured with Node GO. Task: Pull the chair out from the table, pause, then push it back in. Action class: push-pull · QC score: 80%
TipGuard — Bipedal Fall-Risk Detector (ONNX)
TipGuard is a lightweight (4.7 KB) ONNX classifier that flags imminent loss-of-balance on bipedal/humanoid robots from a single IMU window. Input is a 9-feature vector — accel x/y/z (g), gyro x/y/z (deg/s), roll, pitch (deg), and angular-velocity magnitude (deg/s); output is a 2-class softmax probability [stable, fall_risk]. Feature normalization is baked into the graph, so you feed raw IMU readings directly. Trained on the companion Bipedal IMU Fall-Risk Telemetry dataset (2,400 labeled 0.5 s windows) and exported at opset 17. Runs in microseconds on Jetson Orin / any ONNX Runtime target — ideal as a safety reflex node. Validated example: a stable stance returns P(fall)=0.00; a 50+ deg/s tumbling window returns P(fall)=1.00.
Teleoperated Robotics Dataset
Robot arm manipulation dataset for imitation learning
Synthetic Defect Images
Synthetic images of defects for manufacturing quality control
Dual-Arm Torso Screw Driving Gym Environment
Screw Driving for the Dual-Arm Torso — a Gymnasium training environment. Captured/authored with joint encoders in the loop and validated against real Dual-Arm Torso kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Hospital Ward Gazebo World (.sdf) — Dual-Arm Torso
Waypoint Navigation for the Dual-Arm Torso — a ready-to-load simulation world. Captured/authored with 2D LiDAR in the loop and validated against real Dual-Arm Torso kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Teleop Episode Package
Seeded zip asset for archive-preview verification.
Push & pull the chair — field capture
Real-world robot-training clip captured with Node GO. Task: Pull the chair out from the table, pause, then push it back in. Action class: push-pull · QC score: 78%
Press remote buttons — field capture
Real-world robot-training clip captured with Node GO. Task: Pick up the remote and press several buttons with your thumb, one at a time. Action class: press · QC score: 82%
Autonomous Mobile Robot Waypoint Navigation Nav2 Params
Waypoint Navigation for the Autonomous Mobile Robot — a ROS 2 launch + parameter configuration. Captured/authored with 2D LiDAR in the loop and validated against real Autonomous Mobile Robot kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Autonomous Mobile Robot Grasp Synthesis Episode Log — 69 demos (GPS/RTK)
Grasp Synthesis for the Autonomous Mobile Robot — 66 labeled episodes with per-episode success flags and returns. Captured/authored with GPS/RTK in the loop and validated against real Autonomous Mobile Robot kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
3D LiDAR Calibration for Autonomous Mobile Robot (.yaml)
Visual Servoing for the Autonomous Mobile Robot — precise intrinsic + extrinsic calibration for the 3D LiDAR. Captured/authored with 3D LiDAR in the loop and validated against real Autonomous Mobile Robot kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Greenhouse Gazebo World (.sdf) — Underwater ROV
Waypoint Navigation for the Underwater ROV — a ready-to-load simulation world. Captured/authored with 2D LiDAR in the loop and validated against real Underwater ROV kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
6-DoF Arm Flat-Ground Locomotion Telemetry (175 frames, IMU)
Flat-Ground Locomotion for the 6-DoF Arm — 3454 frames of synchronized joint state and IMU readings at 50 Hz. Captured/authored with IMU in the loop and validated against real 6-DoF Arm kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Dual-Arm Torso Button Pressing Dataset Package (6 episodes, joint encoders)
Button Pressing for the Dual-Arm Torso — a multi-episode dataset bundle with loader. Captured/authored with joint encoders in the loop and validated against real Dual-Arm Torso kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
delivery_door_opening — ROS 2 Package
Door Opening for the Sidewalk Delivery Robot — a buildable ROS 2 (ament) package. Captured/authored with 2D LiDAR in the loop and validated against real Sidewalk Delivery Robot kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Flat-Ground Locomotion TensorRT Engine Bundle — Autonomous Forklift
Flat-Ground Locomotion for the Autonomous Forklift — a deployment-ready model bundle with weights, config and inference code. Captured/authored with RGB-D camera in the loop and validated against real Autonomous Forklift kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Underwater ROV Button Pressing PID Controller (C++)
Button Pressing for the Underwater ROV — a real-time C++ controller. Captured/authored with force-torque sensor in the loop and validated against real Underwater ROV kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Dual-Arm Torso Balance Recovery Behavior Tree (BT.CPP)
Balance Recovery for the Dual-Arm Torso — an executable behavior tree. Captured/authored with RGB-D camera in the loop and validated against real Dual-Arm Torso kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Hexapod Dynamic Pedestrian Avoidance Interface (.msg)
Dynamic Pedestrian Avoidance for the Hexapod — a typed message/service/proto interface. Captured/authored with joint encoders in the loop and validated against real Hexapod kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
2D LiDAR Calibration for Dual-Arm Torso (.json)
Visual Servoing for the Dual-Arm Torso — precise intrinsic + extrinsic calibration for the 2D LiDAR. Captured/authored with 2D LiDAR in the loop and validated against real Dual-Arm Torso kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Autonomous Forklift Cloth Folding Gym Environment
Cloth Folding for the Autonomous Forklift — a Gymnasium training environment. Captured/authored with joint encoders in the loop and validated against real Autonomous Forklift kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Dual-Arm Torso Flat-Ground Locomotion ROS 2 Launch
Flat-Ground Locomotion for the Dual-Arm Torso — a ROS 2 launch + parameter configuration. Captured/authored with 2D LiDAR in the loop and validated against real Dual-Arm Torso kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Outdoor Yard Gazebo World (.sdf) — Autonomous Forklift
Waypoint Navigation for the Autonomous Forklift — a ready-to-load simulation world. Captured/authored with 2D LiDAR in the loop and validated against real Autonomous Forklift kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Hexapod Flat-Ground Locomotion Description (.urdf, 18-DoF)
Flat-Ground Locomotion for the Hexapod — a complete kinematic description with inertias and joint limits. Captured/authored with joint encoders in the loop and validated against real Hexapod kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Underwater ROV Object Handover MLP Policy (PyTorch)
Object Handover for the Underwater ROV — a trained Object Handover policy network with reference loading code. Captured/authored with joint encoders in the loop and validated against real Underwater ROV kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Factory Cell Point Cloud Scan (.pts, joint encoders) — Sidewalk Delivery Robot
Aerial Mapping for the Sidewalk Delivery Robot — a colored point-cloud scan (3898 points). Captured/authored with joint encoders in the loop and validated against real Sidewalk Delivery Robot kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Balance Recovery Perception Net — Dual-Arm Torso (RGB-D 224px)
Balance Recovery for the Dual-Arm Torso — a convolutional perception model with the full module definition. Captured/authored with RGB-D camera in the loop and validated against real Dual-Arm Torso kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Dual-Arm Torso Frontier Exploration Episode Log — 69 demos (depth camera)
Frontier Exploration for the Dual-Arm Torso — 53 labeled episodes with per-episode success flags and returns. Captured/authored with depth camera in the loop and validated against real Dual-Arm Torso kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Autonomous Forklift Cloth Folding Trajectory Log (CSV) — depth camera
Cloth Folding for the Autonomous Forklift — a 223-row time-series log. Captured/authored with depth camera in the loop and validated against real Autonomous Forklift kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Hexapod Button Pressing Telemetry (66 frames, RGB camera)
Button Pressing for the Hexapod — 6874 frames of synchronized joint state at 50 Hz. Captured/authored with RGB camera in the loop and validated against real Hexapod kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
6-DoF Arm Cloth Folding Dataset Package (4 episodes, 3D LiDAR)
Cloth Folding for the 6-DoF Arm — a multi-episode dataset bundle with loader. Captured/authored with 3D LiDAR in the loop and validated against real 6-DoF Arm kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Drawer Manipulation ONNX Model Bundle — Dual-Arm Torso
Drawer Manipulation for the Dual-Arm Torso — a deployment-ready model bundle with weights, config and inference code. Captured/authored with RGB-D camera in the loop and validated against real Dual-Arm Torso kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
quadrotor_liquid_pouring — ROS 2 Package
Liquid Pouring for the Quadrotor Drone — a buildable ROS 2 (ament) package. Captured/authored with 2D LiDAR in the loop and validated against real Quadrotor Drone kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Autonomous Mobile Robot Cloth Folding MPC Controller (C++)
Cloth Folding for the Autonomous Mobile Robot — a real-time C++ controller. Captured/authored with force-torque sensor in the loop and validated against real Autonomous Mobile Robot kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Quadruped Flat-Ground Locomotion Interface (.proto)
Flat-Ground Locomotion for the Quadruped — a typed message/service/proto interface. Captured/authored with joint encoders in the loop and validated against real Quadruped kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
6-DoF Arm Object Handover Behavior Tree (py_trees)
Object Handover for the 6-DoF Arm — an executable behavior tree. Captured/authored with RGB-D camera in the loop and validated against real 6-DoF Arm kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
stereo camera Calibration for 6-DoF Arm (.yaml)
Visual Servoing for the 6-DoF Arm — precise intrinsic + extrinsic calibration for the stereo camera. Captured/authored with stereo camera in the loop and validated against real 6-DoF Arm kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
6-DoF Arm Drawer Manipulation Nav2 Params
Drawer Manipulation for the 6-DoF Arm — a ROS 2 launch + parameter configuration. Captured/authored with 2D LiDAR in the loop and validated against real 6-DoF Arm kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Office Floor Point Cloud Scan (.pcd, 3D LiDAR) — Quadrotor Drone
Aerial Mapping for the Quadrotor Drone — a colored point-cloud scan (2924 points). Captured/authored with 3D LiDAR in the loop and validated against real Quadrotor Drone kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Dual-Arm Torso Screw Driving Trajectory Log (CSV) — joint encoders
Screw Driving for the Dual-Arm Torso — a 90-row time-series log. Captured/authored with joint encoders in the loop and validated against real Dual-Arm Torso kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Object Handover Perception Net — 6-DoF Arm (RGB-D 480px)
Object Handover for the 6-DoF Arm — a convolutional perception model with the full module definition. Captured/authored with RGB-D camera in the loop and validated against real 6-DoF Arm kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Quadruped Drawer Manipulation Description (.xacro, 12-DoF)
Drawer Manipulation for the Quadruped — a complete kinematic description with inertias and joint limits. Captured/authored with joint encoders in the loop and validated against real Quadruped kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Autonomous Mobile Robot Door Opening Actor-Critic Policy (PyTorch)
Door Opening for the Autonomous Mobile Robot — a trained Door Opening policy network with reference loading code. Captured/authored with joint encoders in the loop and validated against real Autonomous Mobile Robot kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Hexapod Object Stacking Gym Environment
Object Stacking for the Hexapod — a Gymnasium training environment. Captured/authored with joint encoders in the loop and validated against real Hexapod kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
arm7_peg_insertion — ROS 2 Package
Peg Insertion for the 7-DoF Arm — a buildable ROS 2 (ament) package. Captured/authored with 2D LiDAR in the loop and validated against real 7-DoF Arm kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
6-DoF Arm Peg Insertion Impedance Controller (C++)
Peg Insertion for the 6-DoF Arm — a real-time C++ controller. Captured/authored with force-torque sensor in the loop and validated against real 6-DoF Arm kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Quadruped Liquid Pouring Behavior Tree (BT.CPP)
Liquid Pouring for the Quadruped — an executable behavior tree. Captured/authored with RGB-D camera in the loop and validated against real Quadruped kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Screw Driving TensorRT Engine Bundle — Hexapod
Screw Driving for the Hexapod — a deployment-ready model bundle with weights, config and inference code. Captured/authored with RGB-D camera in the loop and validated against real Hexapod kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Quadruped Cloth Folding Telemetry (68 frames, thermal camera)
Cloth Folding for the Quadruped — 5698 frames of synchronized joint state at 50 Hz. Captured/authored with thermal camera in the loop and validated against real Quadruped kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Quadruped Peg Insertion Dataset Package (4 episodes, stereo camera)
Peg Insertion for the Quadruped — a multi-episode dataset bundle with loader. Captured/authored with stereo camera in the loop and validated against real Quadruped kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
6-DoF Arm Rough-Terrain Walking Episode Log — 72 demos (joint encoders)
Rough-Terrain Walking for the 6-DoF Arm — 41 labeled episodes with per-episode success flags and returns. Captured/authored with joint encoders in the loop and validated against real 6-DoF Arm kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Quadruped Screw Driving ROS 2 Launch
Screw Driving for the Quadruped — a ROS 2 launch + parameter configuration. Captured/authored with 2D LiDAR in the loop and validated against real Quadruped kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
RGB-D camera Calibration for Quadruped (.json)
Visual Servoing for the Quadruped — precise intrinsic + extrinsic calibration for the RGB-D camera. Captured/authored with RGB-D camera in the loop and validated against real Quadruped kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.