What's in This Configuration

The R1-A7 Smart F pushes desktop manipulation into high-DOF territory. You get the full upper-body dual-arm humanoid with 7-DOF arms, waist rotation, binocular vision, voice interaction, and open SDK — now paired with LinkerBot O6 six-DOF dexterous hands that deliver unprecedented mechanical complexity in a compact form factor. Each hand features 6 active DOF plus 5 passive joints (11 joints total) driven by worm-gear transmission with high-torque servo modules, achieving 130 N max grip force and ±0.2 mm repeat accuracy at just 370 g per hand. Wrist-mounted RGB cameras provide close-up visual feedback. The built-in Orin Nano 40 TOPS compute module powers real-time perception and AI inference locally. At just ~13 kg, the R1-A7 Smart F is the most mechanically sophisticated desktop humanoid in the lineup.

Dual 7-DOF Arms. Redundant Kinematics. Human-Like Dexterity.

The R1-A7 Smart F is engineered around two 7-DOF high-performance arms, each driven by low-inertia inner-rotor PMSM motors with crossed-roller and double-row ball bearings. With 555 mm reach and a ~2 kg payload per arm, it handles precise assembly, pick-and-place, and manipulation research with human-like fluidity. The extra two degrees of freedom per arm (compared to 5-DOF platforms) provide kinematic redundancy — the arm can maintain end-effector pose while reconfiguring its elbow to avoid obstacles, reach around corners, or optimize for natural motion. Dual encoders on every joint deliver closed-loop precision down to ±0.1 mm.

LinkerBot O6 — Six-DOF Dexterity for High-DOF Manipulation

The LinkerBot O6 is a mechanically sophisticated six-DOF dexterous hand designed for research that demands maximum joint complexity. Each hand packs 6 active degrees of freedom plus 5 passive joints into an 11-joint architecture — more than any other hand in the R1-A7 lineup. The worm-gear transmission with high-torque servo modules delivers 130 N max five-finger grip force, 28 N at the thumb tip, and 33 N at the four-finger tips, with ±0.2 mm repeat accuracy — all at just 370 g per hand. This exceptional power-to-weight ratio makes the O6 ideal for high-DOF manipulation research where every joint matters: in-hand reorientation, multi-finger coordination, precision assembly, and dexterous tool use. The five-finger configuration with 6 active DOF enables complex finger gaits, independent fingertip control, and adaptive grasping strategies that go far beyond simpler end effectors.

High-DOF Grasping — Precision and Power in Every Joint

With the LinkerBot O6 hands, the R1-A7 Smart F unlocks high-DOF grasping capabilities that rival research-grade robotic hands at a fraction of the cost and weight. The 6 active DOF per hand enable independent control of finger adduction, flexion, and opposition — the same degrees of freedom that give human hands their versatility. Combined with 7-DOF arms, the robot achieves 20 controllable degrees of freedom per arm-hand chain, enabling whole-arm manipulation strategies where the arm and hand work together to reposition, reorient, and manipulate objects with unprecedented dexterity. The 130 N max grip force handles heavy or resistive objects, while the ±0.2 mm repeat accuracy ensures precision for delicate assembly tasks. This makes the Smart F the ideal platform for research in in-hand manipulation, visual dexterous grasping, and embodied AI where high-DOF control is essential.

Wrist-Mounted RGB Cameras — See From the Gripper

Integrated RGB cameras on each wrist provide a gripper's-eye view of the workspace. These close-up feeds are invaluable for visual servoing, grasp verification, and fine manipulation tasks where the head-mounted stereo pair lacks resolution or the right viewing angle. With 6-DOF hands, wrist cameras become essential — they capture detailed finger configurations, joint angles, and contact geometry, enabling precise visual feedback for high-DOF control algorithms. The cameras support visual dexterous grasping research by providing ground-truth data for finger pose estimation and grasp quality assessment.

Vision-Wrist Fusion — Two-Scale Perception for High-DOF Manipulation

The R1-A7 Smart F fuses stereo vision from the head with close-up RGB feeds from the wrist cameras into a unified perception stack optimized for high-DOF manipulation. The binocular camera provides global scene understanding, object detection, and coarse grasp planning across the full workspace. The wrist cameras deliver high-resolution local views of the 11-joint hand-object interaction, capturing finger positions, joint configurations, and grasp geometry in detail. Together, these two visual scales create a complete manipulation perception pipeline: the head camera finds the object and proposes a grasp strategy, the wrist camera guides the 6-DOF fingers into position, and the Orin Nano 40 TOPS processes both streams in real time to execute precise high-DOF grasps. This dual-scale visual architecture is essential for research in visual dexterous manipulation, high-DOF grasp pose estimation, and embodied AI with complex end effectors.

Waist Rotation — Expand Your Workspace

The 1-DOF waist joint provides ±150° of rotation, dramatically expanding the robot's reachable workspace without moving the base. In a seated or standing deployment, the waist allows the robot to turn and manipulate objects on either side, hand objects from one hand to the other across the body, and orient toward humans or workstations. Combined with 7-DOF arms and 6-DOF dexterous hands, the R1-A7 Smart F achieves an extraordinary 24 controllable degrees of freedom across each arm-waist-hand chain — enabling whole-body manipulation strategies that leverage every joint for dexterous, fluid motion.

Orin Nano 40 TOPS — AI Onboard, No Latency

The R1-A7 Smart F ships with a built-in NVIDIA Jetson Orin Nano delivering 40 TOPS of AI compute. This means visual perception, high-DOF grasp pose estimation, finger keypoint detection, and reinforcement learning policies all run in real time locally. Object detection models process head camera frames, hand pose estimators track 11 joints per hand from wrist camera feeds, and multi-joint control policies execute with sub-millisecond latency — all without external GPU servers or cloud dependency. Just plug in power and start training high-DOF manipulation policies.

Binocular Vision & AI Perception

A binocular camera head delivers a 146° × 124° field of view with a 60 mm stereo baseline. RGB streams at 1280×720@30 Hz and depth at 544×448@10 Hz give the R1-A7 true spatial awareness. Paired with an 8-core high-performance CPU + 10 TOPS NPU in the head module, plus the Orin Nano 40 TOPS body compute, it runs visual perception, object detection, and gesture recognition locally — no cloud required.

Voice Collaboration & Natural Interaction

Four-array beamforming microphones and dual 3 W speakers enable clear voice capture and synthesis in noisy labs or classrooms. The open audio framework supports custom wake words, multilingual TTS, and integration with LLMs for conversational command-and-control.

Compact. Lightweight. Desktop-Ready.

At just 835 × 357 × 190 mm and approximately 13 kg, the R1-A7 Smart F fits on a standard lab bench or classroom desk. Despite housing the most mechanically complex hands in the lineup, the compact footprint leaves room for objects, tools, and sensors around the robot. Power via the included external supply — an optional upper-body Li-ion battery is available for ~1.5 hours of untethered operation.

Full-Stack Open Development

Unitree provides a mature, Linux-based robot development framework with open APIs for the underlying system, robotic arms, audio, lighting, and visual control. ROS 2 native support, dual encoders on every arm joint, and hollow internal wiring make the R1-A7 Smart F a clean slate for reinforcement learning, teleoperation research, high-DOF control algorithms, and embodied AI. The built-in Orin Nano 40 TOPS handles model training and inference for visual perception and high-DOF grasp planning without external hardware. The open SDK includes full control over all 6 active DOF per hand plus passive joint state monitoring, enabling research-grade control of complex multi-joint end effectors.

Upgrade Path — Grow With Your Research

Start with Smart F and expand as your projects evolve. The R1-A7 platform is fully modular:

• End Effectors — Upgrade from LinkerBot O6 to LinkerBot O6 Tactile (adds force-sensitive fingertips and palm arrays), BrainCo Revo 2 Basic or Tactile 5-finger hands, Dex3-1 or Dex3-1 Tactile 3-finger hands, or tendon-driven hands.
• Tactile — Add the LinkerBot O6 Tactile upgrade to bring force sensing to your high-DOF hands for multi-modal manipulation research.
• Large VLM — Deploy vision-language models for natural-language manipulation commands, visual question answering, and semantic scene understanding.
• Compute Module — Swap the Orin Nano for the Orin NX 100 TOPS module to unlock 2.5× AI performance, 16 GB RAM, and dual DLA cores for simultaneous head camera, wrist camera, and high-DOF hand processing.
• Upper-Body Battery — Add the Li-ion battery pack for ~1.5 hours of cord-free operation.

Designed For

Technical Specifications

Model	Unitree R1-A7 Smart F (Upper Body)
Dimensions (Compact)	835 × 357 × 190 mm (H × W × D)
Dimensions (Extended)	1320 × 450 × 200 mm (H × W × D)
Weight (with Battery)	~13 kg
Total DOF	17 (Arm 7×2, Waist 1, Head 2)
Arm Reach	555 mm (forearm + upper arm)
Joint Bearings	Crossed-roller + double-row ball bearings
Joint Motors	Low-inertia, high-speed, inner-rotor permanent magnet synchronous motors
Max Arm Payload	~2 kg (posture-dependent)
End-Effector Precision	±0.1 mm
End Effectors	LinkerBot O6 six-DOF dexterous hands (both arms, pre-installed)
Hand DOF	6 active DOF + 5 passive joints (11 joints total) per hand
Hand Actuation	Worm-gear transmission with high-torque servo modules
Hand Weight	~370 g per hand
Hand Grip Force	130 N max five-finger; 28 N thumb tip; 33 N four-finger tip
Hand Repeat Accuracy	±0.2 mm
Wrist Cameras	RGB integrated (pre-installed, both wrists)
Tactile Sensing	Not included (optional upgrade: LinkerBot O6 Tactile)
Waist Joint	1-DOF, Yaw: ±150°
Head Joint	2-DOF, Yaw: ±115°, Pitch: ±36°
Vision	Binocular camera — RGB 1280×720@30 Hz, Depth 544×448@10 Hz, FOV 146°×124°
Head Compute	8-core high-performance CPU + 10 TOPS NPU
Body Compute	8-core high-performance CPU
Onboard AI Compute	NVIDIA Jetson Orin Nano 40 TOPS, 6-core CPU, 8 GB LPDDR5 (built-in)
Audio	4-array microphone + dual 3 W speakers
Connectivity	Wi-Fi 6, Bluetooth 5.2, OTA updates
Power