ProductsGrasp / Manipulation Model

Grasp / Manipulation Model Products

4 listed

Compare 4 Grasp / Manipulation Model models from NVIDIA, Reward AI and Shanghai Jiao Tong University — sourced specs side by side.

3D/Depth Camera (RGB-D)Angular (Rotary) Gripper Anomaly Detection Model Area Scan Camera (2D)Articulated Robot Ball Screw / Lead Screw Battery Pack Bimanual Manipulation Platform CAD / Geometry Engine Centric (3-Jaw) Gripper Cycloidal / RV Reducer Deburring / Grinding Tool Electric Linear Actuator Electric Motor (Rotary)Encoder Fleet Management Software Force/Torque Sensor Hardware Harmonic / Strain Wave Drive Humanoid Robot Inertial Measurement Unit (IMU)Integrated Joint Actuator Legged Robot (Non-humanoid)LiDAR Scanner Linear Guide / Rail Magnetic Gripper Mobile Ground Robot (AMR/AGV)Motion Planning Library Motor Driver / Servo Drive Multi-Finger/Anthropomorphic Hand Planetary Gearbox Pre-trained Vision Model Programmable Logic Controller (PLC)Proximity/Distance Sensor Robot Controller Robot Operating System / Middleware Robot Programming Environment SLAM / Navigation Software Safety Laser Scanner Safety Light Curtain Screwdriver/Drill EOAT Simulation Software Single-Board Computer / Embedded Soft / Adaptive Gripper System Integration Tactile / Pressure Sensor Tool Changer Two-Finger (Parallel) Gripper Vacuum/Suction Gripper Vision Processing Library

GraspGen

NVIDIA

NVIDIA's diffusion-based 6-DOF grasp generator: give it a segmented object point cloud or mesh, get back ranked gripper poses with confidence scores. Checkpoints for Franka Panda, Robotiq 2F-140 and a 30 mm suction cup. Research use only.

OM-1 (Omnibody Model 1)

Reward AI

General-purpose manipulation policy trained only on human demonstrations captured through a wearable 7-DoF hand — no teleoperation and no on-robot data — and designed to run across arms, humanoids and mobile manipulators.

AnyGrasp

Shanghai Jiao Tong University

General grasp-pose detector from the GraspNet team (SJTU): dense, temporally-smooth 7-DoF grasp poses on unseen objects from a single point cloud — reported ~93% bin-picking success, distributed as a license-gated SDK, free for research.

FoundationGrasp

Southern University of Science and Technology (SUSTech)

Foundation-model-based task-oriented grasping from SUSTech: combines semantic (language) and geometric reasoning to propose task-appropriate 6-DoF grasps that generalise to novel objects and tasks.