About
Description
Unitree Robotics — Smart Series
Unitree R1-A7 Smart D
Upper-Body Dual-Arm Humanoid Robot with BrainCo Revo 2 Basic Five-Finger Anthropomorphic Dexterous Hands, Wrist RGB Cameras & Onboard Orin Nano 40 TOPS. 17 DOF, 7-DOF precision arms, 555 mm reach, human-like grasping & full-stack open SDK. The anthropomorphic entry to advanced humanoid manipulation research.
17
Total DOF
7+7
Arm DOF
555
mm Reach
~2
kg Payload
13
kg Weight
What's in This Configuration
The R1-A7 Smart D brings true anthropomorphic dexterity to the desktop. 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 BrainCo Revo 2 Basic five-finger anthropomorphic dexterous hands that mirror human hand morphology. Each hand features five independently actuated fingers with human-like joint architecture, enabling natural grasping of everyday objects, tools, and components. Wrist-mounted RGB cameras provide close-up visual feedback for grasp verification and hand-eye coordination. 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 D is the most human-like desktop manipulator in the R1-A7 lineup.
✓ R1-A7 Upper-Body Humanoid
Dual 7-DOF arms, 1-DOF waist (±150°), 2-DOF head. 835×357×190 mm compact footprint, ~13 kg. Crossed-roller bearings, low-inertia inner-rotor motors, hollow internal cabling.
✓ BrainCo Revo 2 Basic Five-Finger Hands
Anthropomorphic dexterous hands with five independently actuated fingers on both arms. Human-like joint architecture for natural grasping of everyday objects and tools.
✓ Wrist RGB Cameras
RGB cameras integrated into each wrist module for close-up visual feedback, grasp verification, and hand-eye coordination.
✓ Orin Nano 40 TOPS
Onboard NVIDIA Jetson Orin Nano delivering 40 TOPS for real-time perception, grasp planning, and AI model inference.
✓ Binocular Vision Head
RGB 1280×720@30 Hz + Depth 544×448@10 Hz. 146°×124° FOV, 60 mm baseline. 8-core CPU + 10 TOPS NPU on-board.
✓ Full-Stack Open SDK
Linux framework, ROS 2 native, open APIs for arms, audio, vision, lighting. Dual encoders per joint.
Dual 7-DOF Arms. Redundant Kinematics. Human-Like Dexterity.
The R1-A7 Smart D 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.
BrainCo Revo 2 Basic — Five-Finger Anthropomorphic Dexterity
The BrainCo Revo 2 Basic is a research-grade five-finger anthropomorphic dexterous hand designed to replicate human hand morphology and motion. Each hand features five independently actuated fingers with multiple joints per finger, enabling a wide repertoire of grasp types — from precision pinches to power grips, from tripod grasps to lateral holds. The human-like joint architecture means the robot can manipulate the same objects humans use every day: pens, cups, tools, phones, and components. Unlike simpler grippers, the Revo 2 Basic can perform in-hand manipulation — reorienting objects without releasing them, sliding fingers along surfaces, and adjusting grip configurations on the fly. This makes it the ideal end effector for research in anthropomorphic robotics, human-robot interaction, and embodied AI that aims to bridge the gap between machine and human manipulation capabilities.
Anthropomorphic Grasping — Human-Like Dexterity at Your Desktop
With the BrainCo Revo 2 Basic hands, the R1-A7 Smart D can perform anthropomorphic grasping that mirrors human hand behavior. The five-finger configuration supports the full taxonomy of human grasps — power grips for large objects, precision grips for small items, tripod grasps for spherical objects, and lateral pinches for flat components. Each finger moves independently, allowing the hand to conform to irregular object geometries and maintain stable contact across multiple points. This level of dexterity is essential for research in human-robot handover, tool use, domestic manipulation, and embodied AI where the robot must interact with human-designed environments and objects. The compact desktop form factor puts this anthropomorphic capability within reach of any research lab or university classroom.
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 five-finger hands, wrist cameras become even more critical — they capture finger configurations, contact points, and object pose relative to the palm, enabling detailed analysis of grasp quality and hand posture. Combined with the anthropomorphic hand design, wrist cameras support visual imitation learning from human hand videos and grasp pose estimation for complex multi-finger configurations.
Vision-Wrist Fusion — Two-Scale Perception for Anthropomorphic Manipulation
The R1-A7 Smart D fuses stereo vision from the head with close-up RGB feeds from the wrist cameras into a unified perception stack. 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 hand-object interaction, capturing finger positions, contact geometry, and grasp stability in detail. Together, these two visual scales create a complete manipulation perception pipeline: the head camera finds the object, the wrist camera guides the fingers, and the Orin Nano 40 TOPS processes both streams in real time to execute precise anthropomorphic grasps. This dual-scale visual architecture is essential for research in visual dexterous manipulation, grasp pose estimation, and imitation learning from human demonstrations.
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 five-finger anthropomorphic hands, the R1-A7 Smart D achieves human-like reach envelopes with natural grasping 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 D ships with a built-in NVIDIA Jetson Orin Nano delivering 40 TOPS of AI compute. This means visual perception, grasp pose estimation, and hand tracking all run in real time locally. Object detection models process head camera frames, finger keypoint detectors analyze wrist camera feeds, and reinforcement learning policies execute with sub-millisecond latency — all without external GPU servers or cloud dependency. Just plug in power and start training anthropomorphic 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 D 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
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 D a clean slate for reinforcement learning, teleoperation research, imitation learning from human hand videos, and embodied AI. The built-in Orin Nano 40 TOPS handles model training and inference for visual perception and grasp planning without external hardware. The open SDK includes full control over all five fingers per hand, enabling custom grasp controllers and anthropomorphic motion primitives.
Upgrade Path — Grow With Your Research
Start with Smart D and expand as your projects evolve. The R1-A7 platform is fully modular:
- End Effectors — Upgrade from BrainCo Revo 2 Basic to BrainCo Revo 2 Tactile (adds force-sensitive fingertips and palm arrays), Dex3-1 or Dex3-1 Tactile 3-finger hands, LinkerBot Hand O6 (6-DOF, tactile and non-tactile versions), or tendon-driven hands.
- Tactile — Add the BrainCo Revo 2 Tactile upgrade to bring force sensing to your anthropomorphic 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 and wrist camera processing.
- Upper-Body Battery — Add the Li-ion battery pack for ~1.5 hours of cord-free operation.
Designed For
Anthropomorphic Manipulation
Research human-like grasping, in-hand manipulation, tool use, and dexterous object handling with five-finger anthropomorphic hands on a compact desktop platform.
Human-Robot Interaction
Natural handovers, collaborative tasks, and social robotics research where human-like hand morphology improves trust, predictability, and interaction quality.
University Labs
Teaching anthropomorphic robotics, grasp taxonomy, dexterous control, and embodied AI on an open platform with human-like end effectors and full SDK access.
Embodied AI & Imitation Learning
Train policies from human hand videos, learn dexterous behaviors through demonstration, and study transfer learning between human and robot manipulation.
Technical Specifications
Description
Unitree Robotics — Smart Series
Unitree R1-A7 Smart D
Upper-Body Dual-Arm Humanoid Robot with BrainCo Revo 2 Basic Five-Finger Anthropomorphic Dexterous Hands, Wrist RGB Cameras & Onboard Orin Nano 40 TOPS. 17 DOF, 7-DOF precision arms, 555 mm reach, human-like grasping & full-stack open SDK. The anthropomorphic entry to advanced humanoid manipulation research.
17
Total DOF
7+7
Arm DOF
555
mm Reach
~2
kg Payload
13
kg Weight
What's in This Configuration
The R1-A7 Smart D brings true anthropomorphic dexterity to the desktop. 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 BrainCo Revo 2 Basic five-finger anthropomorphic dexterous hands that mirror human hand morphology. Each hand features five independently actuated fingers with human-like joint architecture, enabling natural grasping of everyday objects, tools, and components. Wrist-mounted RGB cameras provide close-up visual feedback for grasp verification and hand-eye coordination. 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 D is the most human-like desktop manipulator in the R1-A7 lineup.
✓ R1-A7 Upper-Body Humanoid
Dual 7-DOF arms, 1-DOF waist (±150°), 2-DOF head. 835×357×190 mm compact footprint, ~13 kg. Crossed-roller bearings, low-inertia inner-rotor motors, hollow internal cabling.
✓ BrainCo Revo 2 Basic Five-Finger Hands
Anthropomorphic dexterous hands with five independently actuated fingers on both arms. Human-like joint architecture for natural grasping of everyday objects and tools.
✓ Wrist RGB Cameras
RGB cameras integrated into each wrist module for close-up visual feedback, grasp verification, and hand-eye coordination.
✓ Orin Nano 40 TOPS
Onboard NVIDIA Jetson Orin Nano delivering 40 TOPS for real-time perception, grasp planning, and AI model inference.
✓ Binocular Vision Head
RGB 1280×720@30 Hz + Depth 544×448@10 Hz. 146°×124° FOV, 60 mm baseline. 8-core CPU + 10 TOPS NPU on-board.
✓ Full-Stack Open SDK
Linux framework, ROS 2 native, open APIs for arms, audio, vision, lighting. Dual encoders per joint.
Dual 7-DOF Arms. Redundant Kinematics. Human-Like Dexterity.
The R1-A7 Smart D 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.
BrainCo Revo 2 Basic — Five-Finger Anthropomorphic Dexterity
The BrainCo Revo 2 Basic is a research-grade five-finger anthropomorphic dexterous hand designed to replicate human hand morphology and motion. Each hand features five independently actuated fingers with multiple joints per finger, enabling a wide repertoire of grasp types — from precision pinches to power grips, from tripod grasps to lateral holds. The human-like joint architecture means the robot can manipulate the same objects humans use every day: pens, cups, tools, phones, and components. Unlike simpler grippers, the Revo 2 Basic can perform in-hand manipulation — reorienting objects without releasing them, sliding fingers along surfaces, and adjusting grip configurations on the fly. This makes it the ideal end effector for research in anthropomorphic robotics, human-robot interaction, and embodied AI that aims to bridge the gap between machine and human manipulation capabilities.
Anthropomorphic Grasping — Human-Like Dexterity at Your Desktop
With the BrainCo Revo 2 Basic hands, the R1-A7 Smart D can perform anthropomorphic grasping that mirrors human hand behavior. The five-finger configuration supports the full taxonomy of human grasps — power grips for large objects, precision grips for small items, tripod grasps for spherical objects, and lateral pinches for flat components. Each finger moves independently, allowing the hand to conform to irregular object geometries and maintain stable contact across multiple points. This level of dexterity is essential for research in human-robot handover, tool use, domestic manipulation, and embodied AI where the robot must interact with human-designed environments and objects. The compact desktop form factor puts this anthropomorphic capability within reach of any research lab or university classroom.
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 five-finger hands, wrist cameras become even more critical — they capture finger configurations, contact points, and object pose relative to the palm, enabling detailed analysis of grasp quality and hand posture. Combined with the anthropomorphic hand design, wrist cameras support visual imitation learning from human hand videos and grasp pose estimation for complex multi-finger configurations.
Vision-Wrist Fusion — Two-Scale Perception for Anthropomorphic Manipulation
The R1-A7 Smart D fuses stereo vision from the head with close-up RGB feeds from the wrist cameras into a unified perception stack. 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 hand-object interaction, capturing finger positions, contact geometry, and grasp stability in detail. Together, these two visual scales create a complete manipulation perception pipeline: the head camera finds the object, the wrist camera guides the fingers, and the Orin Nano 40 TOPS processes both streams in real time to execute precise anthropomorphic grasps. This dual-scale visual architecture is essential for research in visual dexterous manipulation, grasp pose estimation, and imitation learning from human demonstrations.
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 five-finger anthropomorphic hands, the R1-A7 Smart D achieves human-like reach envelopes with natural grasping 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 D ships with a built-in NVIDIA Jetson Orin Nano delivering 40 TOPS of AI compute. This means visual perception, grasp pose estimation, and hand tracking all run in real time locally. Object detection models process head camera frames, finger keypoint detectors analyze wrist camera feeds, and reinforcement learning policies execute with sub-millisecond latency — all without external GPU servers or cloud dependency. Just plug in power and start training anthropomorphic 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 D 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
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 D a clean slate for reinforcement learning, teleoperation research, imitation learning from human hand videos, and embodied AI. The built-in Orin Nano 40 TOPS handles model training and inference for visual perception and grasp planning without external hardware. The open SDK includes full control over all five fingers per hand, enabling custom grasp controllers and anthropomorphic motion primitives.
Upgrade Path — Grow With Your Research
Start with Smart D and expand as your projects evolve. The R1-A7 platform is fully modular:
- End Effectors — Upgrade from BrainCo Revo 2 Basic to BrainCo Revo 2 Tactile (adds force-sensitive fingertips and palm arrays), Dex3-1 or Dex3-1 Tactile 3-finger hands, LinkerBot Hand O6 (6-DOF, tactile and non-tactile versions), or tendon-driven hands.
- Tactile — Add the BrainCo Revo 2 Tactile upgrade to bring force sensing to your anthropomorphic 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 and wrist camera processing.
- Upper-Body Battery — Add the Li-ion battery pack for ~1.5 hours of cord-free operation.
Designed For
Anthropomorphic Manipulation
Research human-like grasping, in-hand manipulation, tool use, and dexterous object handling with five-finger anthropomorphic hands on a compact desktop platform.
Human-Robot Interaction
Natural handovers, collaborative tasks, and social robotics research where human-like hand morphology improves trust, predictability, and interaction quality.
University Labs
Teaching anthropomorphic robotics, grasp taxonomy, dexterous control, and embodied AI on an open platform with human-like end effectors and full SDK access.
Embodied AI & Imitation Learning
Train policies from human hand videos, learn dexterous behaviors through demonstration, and study transfer learning between human and robot manipulation.
Technical Specifications
Unitree
by
Unitree
Unitree R1-A7 Smart D Humanoid Robot
- Regular price
- $13,690.00
- Sale price
- $13,690.00
- Regular price
-
Shipping calculated at checkout.
Providing the best new Tech Experience, Energy Independence and Robotics Ways of Optimisation
Providing the best new Tech Experience, Energy Independence and Robotics Ways of Optimisation
Packaging note:
Equipment is being supplied in a manufacturer packaging
