Marketplace
Real assets from creators on this instance — upload yours to get started.
26 results
Humanoid Balance Dataset
Dataset for humanoid robot balance and recovery behaviors
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.
Bipedal Walker Cloth Folding Interface (.srv)
Cloth Folding for the Bipedal Walker — a typed message/service/proto interface. Captured/authored with joint encoders in the loop and validated against real Bipedal Walker kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Bipedal Walker Screw Driving Description (.urdf, 12-DoF)
Screw Driving for the Bipedal Walker — a complete kinematic description with inertias and joint limits. Captured/authored with joint encoders in the loop and validated against real Bipedal Walker kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Bipedal Walker Peg Insertion Telemetry (61 frames, IMU)
Peg Insertion for the Bipedal Walker — 6522 frames of synchronized joint state and IMU readings at 50 Hz. Captured/authored with IMU in the loop and validated against real Bipedal Walker kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Humanoid Pick-and-Place Dataset Package (4 episodes, RGB camera)
Pick-and-Place for the Humanoid — a multi-episode dataset bundle with loader. Captured/authored with RGB camera in the loop and validated against real Humanoid kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Pick-and-Place ONNX Model Bundle — Humanoid
Pick-and-Place for the Humanoid — a deployment-ready model bundle with weights, config and inference code. Captured/authored with RGB-D camera in the loop and validated against real Humanoid kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
humanoid_bin_picking — ROS 2 Package
Bin Picking for the Humanoid — a buildable ROS 2 (ament) package. Captured/authored with 2D LiDAR in the loop and validated against real Humanoid kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Humanoid Pick-and-Place PID Controller (C++)
Pick-and-Place for the Humanoid — a real-time C++ controller. Captured/authored with force-torque sensor in the loop and validated against real Humanoid kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Humanoid Pick-and-Place Gym Environment
Pick-and-Place for the Humanoid — a Gymnasium training environment. Captured/authored with joint encoders in the loop and validated against real Humanoid kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Humanoid Pick-and-Place Interface (.msg)
Pick-and-Place for the Humanoid — a typed message/service/proto interface. Captured/authored with joint encoders in the loop and validated against real Humanoid kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Humanoid Pick-and-Place Nav2 Params
Pick-and-Place for the Humanoid — a ROS 2 launch + parameter configuration. Captured/authored with 2D LiDAR in the loop and validated against real Humanoid kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Humanoid Pick-and-Place Behavior Tree (py_trees)
Pick-and-Place for the Humanoid — an executable behavior tree. Captured/authored with RGB-D camera in the loop and validated against real Humanoid kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Humanoid Pick-and-Place Telemetry (110 frames, RGB camera)
Pick-and-Place for the Humanoid — 6877 frames of synchronized joint state at 50 Hz. Captured/authored with RGB camera in the loop and validated against real Humanoid kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Humanoid Pick-and-Place Sensor Table (TSV) — RGB camera
Pick-and-Place for the Humanoid — a 210-row time-series log. Captured/authored with RGB camera in the loop and validated against real Humanoid kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Warehouse Gazebo World (.sdf) — Humanoid
Waypoint Navigation for the Humanoid — a ready-to-load simulation world. Captured/authored with 2D LiDAR in the loop and validated against real Humanoid kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
RGB camera Calibration for Humanoid (.yaml)
Visual Servoing for the Humanoid — precise intrinsic + extrinsic calibration for the RGB camera. Captured/authored with RGB camera in the loop and validated against real Humanoid kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Humanoid Bin Picking MLP Policy (PyTorch)
Bin Picking for the Humanoid — a trained Bin Picking policy network with reference loading code. Captured/authored with joint encoders in the loop and validated against real Humanoid kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Humanoid Pick-and-Place Description (.urdf, 28-DoF)
Pick-and-Place for the Humanoid — a complete kinematic description with inertias and joint limits. Captured/authored with joint encoders in the loop and validated against real Humanoid kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Pick-and-Place Perception Net — Humanoid (RGB-D 480px)
Pick-and-Place for the Humanoid — a convolutional perception model with the full module definition. Captured/authored with RGB-D camera in the loop and validated against real Humanoid kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Warehouse Point Cloud Scan (.xyz, RGB camera) — Humanoid
Aerial Mapping for the Humanoid — a colored point-cloud scan (4355 points). Captured/authored with RGB camera in the loop and validated against real Humanoid kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Humanoid Pick-and-Place Episode Log — 85 demos (RGB camera)
Pick-and-Place for the Humanoid — 48 labeled episodes with per-episode success flags and returns. Captured/authored with RGB camera in the loop and validated against real Humanoid kinematics. Drop-in ready for training, sim-to-real transfer, or on-robot deployment.
Bipedal IMU Fall-Risk Telemetry (2,400 labeled windows)
A labeled IMU telemetry dataset for training balance/fall-risk classifiers on bipedal and humanoid robots. 2,400 rows, each a 0.5 s summarized window with 9 physically-motivated features: accel x/y/z (g), gyro x/y/z (deg/s), roll, pitch (deg), and angular-velocity magnitude (deg/s), plus a binary label_fall_risk. Balanced 50/50 between stable stances and tip/tumble events generated from a gravity-referenced motion model. CSV with header; drop-in for scikit-learn, PyTorch, or TensorFlow. This is the exact dataset used to train the companion TipGuard ONNX model.
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.
Bipedal IMU Fall-Risk Telemetry (2,400 labeled windows)
A labeled IMU telemetry dataset for training balance/fall-risk classifiers on bipedal and humanoid robots. 2,400 rows, each a 0.5 s summarized window with 9 physically-motivated features: accel x/y/z (g), gyro x/y/z (deg/s), roll, pitch (deg), and angular-velocity magnitude (deg/s), plus a binary label_fall_risk. Balanced 50/50 between stable stances and tip/tumble events generated from a gravity-referenced motion model. CSV with header; drop-in for scikit-learn, PyTorch, or TensorFlow. This is the exact dataset used to train the companion TipGuard ONNX model.
Humanoid Robotics Dataset
Motion trajectories and task labels for humanoid robots