What's in This Configuration

The R1-A7 Smart C adds tactile sensing to the dexterous manipulation stack. 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 Dex3-1 Tactile three-finger dexterous hands that can feel what they grasp. Force-sensitive fingertips and palm arrays provide real-time contact feedback, while wrist-mounted RGB cameras deliver close-up visual confirmation. The built-in Orin Nano 40 TOPS compute module handles both vision and tactile inference locally. At just ~13 kg, the R1-A7 Smart C brings multi-modal sensing to desktop humanoid research.

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

The R1-A7 Smart C 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.

Dex3-1 Tactile — Three-Finger Dexterity That Feels

The Dex3-1 Tactile takes the adaptive three-finger design of the Dex3-1 and adds a full tactile sensing layer. Force-sensitive arrays cover the fingertips and palm of each hand, measuring contact forces in real time during grasping, sliding, and manipulation. This transforms the robot from a visual-only grasper into a multi-modal manipulator that can detect slip, estimate object compliance, and modulate grip force dynamically — just like a human hand. The three-finger configuration strikes an optimal balance between dexterity and control complexity, making it ideal for research in tactile sensorimotor learning, force-controlled assembly, and physical human-robot interaction.

Tactile Grasping — Force-Aware Dexterity at Your Desktop

With the Dex3-1 Tactile hands, the R1-A7 Smart C can perform force-aware grasping that goes far beyond visual pose estimation. The tactile arrays detect initial contact, monitor grip stability, and trigger corrective actions when slip is detected — enabling robust manipulation of fragile, deformable, or irregularly shaped objects that would challenge vision-only systems. This capability is essential for research in in-hand manipulation, compliant control, and tactile exploration of unknown objects. The compact desktop form factor means you can run these experiments on a standard lab bench without needing a full mobile platform or external sensing infrastructure.

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. Combined with the tactile sensors, wrist cameras enable visual-tactile fusion — the robot can see an object approach, feel it make contact, and confirm the grasp quality using both modalities simultaneously.

Tactile-Vision Fusion — Two-Modal Perception for Manipulation

The R1-A7 Smart C fuses stereo vision from the head with tactile sensing from the hands into a unified perception stack. The binocular camera provides global scene understanding, object detection, and coarse grasp planning. The tactile arrays deliver local contact information, slip detection, and grip force modulation. Together, these two modalities create a closed feedback loop: vision proposes, tactile verifies, and the Orin Nano 40 TOPS processes both streams in real time to refine grasp strategies on the fly. This dual-modal architecture is the foundation for next-generation embodied AI research that mimics human sensorimotor coordination.

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 tactile sensing, the R1-A7 Smart C achieves human-like reach envelopes with force-aware manipulation across a full semicircle of desktop space — ideal for collaborative tasks, bimanual assembly workflows, and human-robot interaction studies.

Orin Nano 40 TOPS — AI Onboard, No Latency

The R1-A7 Smart C ships with a built-in NVIDIA Jetson Orin Nano delivering 40 TOPS of AI compute. This means visual perception, tactile feature extraction, and sensor fusion all run in real time locally. Object detection models process head camera frames, tactile CNNs classify contact patterns, and reinforcement learning policies execute with sub-millisecond latency — all without external GPU servers or cloud dependency. Just plug in power and start training multi-modal 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 C fits on a standard lab bench or classroom desk. 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 + Tactile API

Unitree provides a mature, Linux-based robot development framework with open APIs for the underlying system, robotic arms, audio, lighting, visual control, and tactile sensing. ROS 2 native support, dual encoders on every arm joint, and hollow internal wiring make the R1-A7 Smart C a clean slate for reinforcement learning, teleoperation research, tactile sensorimotor learning, and embodied AI. The built-in Orin Nano 40 TOPS handles model training and inference for both vision and tactile modalities without external hardware. Tactile sensor data streams at high frequency via the open API, ready for your custom force controllers and learning algorithms.

Upgrade Path — Grow With Your Research

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

• End Effectors — Upgrade from Dex3-1 Tactile to BrainCo Revo 2 5-finger dexterous hand (Basic or Tactile), LinkerBot Hand O6 (6-DOF, tactile and non-tactile versions), or tendon-driven hands.
• 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 vision and tactile inference.
• 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 C (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	Dex3-1 Tactile three-finger dexterous hands (both arms, pre-installed)
Wrist Cameras	RGB integrated (pre-installed, both wrists)
Tactile Sensing	Force-sensitive fingertips and palm arrays (pre-installed)
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	External DC PSU included (optional Li-ion battery, ~1.5 h)
Cabling	Hollow + internal wiring
Joint Encoders	Dual + single encoders per joint
Cooling	Localized air cooling
SDK & Interfaces	Linux-based framework, ROS 2, open APIs for arm/audio/vision/tactile/lighting
Controllers	Standard dual-hand controllers included
Warranty	12 months on the entire unit

What's in the Box

• Unitree R1-A7 Smart C Humanoid Robot (upper body)
• Dex3-1 Tactile three-finger dexterous hands (pre-installed, both arms)
• Tactile sensor arrays (pre-installed in fingertips and palms)
• Wrist RGB cameras (pre-installed, both wrists)
• NVIDIA Jetson Orin Nano 40 TOPS compute module (pre-installed)
• External power supply & AC cable
• Optional: upper-body lithium-ion battery pack
• Binocular vision head module (pre-installed)
• 4-array microphone + dual speaker module (pre-installed)
• Standard dual-hand remote controllers
• Quick-start guide & safety manual
• Secondary development documentation access