일일 평균 가격
USD 기준 금액
Mobile-Base Dual-Arm Humanoid Robot with Tendon-Driven Dexterous Hands & Wrist RGB Cameras. 16 DOF, Orin Nano 40 TOPS, MID360 LiDAR, stereo vision & full-stack open SDK. The ultimate research-grade tendon-driven mobile manipulation platform.
R1-A5-D Smart H — mobile-base humanoid with tendon-driven dexterous hands, wrist RGB cameras, MID360 LiDAR & stereo vision
The R1-A5-D Smart H represents the pinnacle of the R1-A5-D lineup, featuring tendon-driven dexterous hands that deliver research-grade anthropomorphic dexterity. Unlike gear-driven or linkage-based alternatives, the tendon-driven mechanism uses cable-and-pulley actuation routed through the wrist — enabling high-DOF finger control, backdrivable compliance, and human-like grasping dynamics. This is the configuration for researchers who demand the most biomimetic manipulation capabilities available on a mobile humanoid platform.
The tendon-driven hands on the R1-A5-D Smart H use cable-and-pulley actuation — the same biomechanical principle that powers human fingers. Motors mounted in the forearm pull polymer or steel tendons routed through the wrist joint to actuate each finger independently. This architecture delivers several advantages over conventional gear-driven or linkage-based hands: backdrivability — the fingers yield when pushed and report contact forces for natural force control; lightweight distal segments — all heavy actuators stay proximal, keeping the fingers agile and fast; high-DOF articulation — independent control of multiple joints per finger enables human-like grasp postures across the full GRASP taxonomy; and compliant interaction — tendon elasticity absorbs impacts and enables safe physical human-robot interaction without rigid force transmission. The result is a hand that moves, feels, and responds like a human hand — essential for research in biomimetic manipulation, neuroscience-inspired robotics, and advanced embodied AI.
Tendon-driven dexterous hands with cable-and-pulley actuation and wrist RGB cameras
Smart H is the only R1-A5-D configuration to feature true tendon-driven actuation — enabling the full range of human grasp types from precision pinches to power grips and in-hand manipulation. The tendon architecture allows independent control of each finger joint with backdrivable compliance, meaning the hand can adapt its grip shape to object geometry in real time, sense contact forces through the same tendons that drive motion, and execute delicate manipulation tasks like rotating objects in-hand or threading needles while the mobile base navigates between workstations. This biomimetic approach bridges the gap between robotic manipulation and human motor control — opening research frontiers in neuroscience-inspired robotics, prosthetics validation, and human-level dexterity benchmarks.
Smart H processes synchronized streams from four sensor modalities on the Orin Nano 40 TOPS: proprioceptive tendon tension and joint encoder data from each hand, close-up RGB from wrist cameras, scene-level depth from the head binocular camera, and 360° point clouds from the MID360 LiDAR. The tendon-driven architecture adds a unique dimension — force transparency — where every actuated joint simultaneously serves as a motor and a sensor. Push on a finger and it yields, reporting exactly how hard you pushed. This force-proprioceptive stream fuses with visual and LiDAR data for a complete multi-modal perception pipeline: visual servoing guides the hand to the object, LiDAR ensures safe navigation, and tendon force feedback closes the grasp loop — enabling research in force-aware mobile manipulation, slip detection and compensation during locomotion, and sensorimotor learning with biomimetic actuation.
The R1-A5-D chassis adds 3 degrees of freedom to the upper body: a telescopic pillar for height adjustment and a 2-DOF wheeled base for omnidirectional navigation. Combined with the MID360 LiDAR and stereo camera head, the robot builds real-time maps, plans paths, and avoids obstacles autonomously — then stops precisely to manipulate. The removable lithium-ion battery in the chassis delivers approximately 1.5 hours of untethered operation.
The built-in NVIDIA Jetson Orin Nano delivers 40 TOPS of AI compute, handling simultaneous streams from tendon proprioception, wrist RGB cameras, head binocular vision, and MID360 LiDAR while executing high-dimensional control policies for tendon-driven hands. Run visual-LiDAR fusion networks, grasp stability predictors, tendon tension optimization, and reinforcement learning algorithms with large action spaces locally with sub-millisecond latency. No external GPU server, no cloud dependency — just power on and deploy.
A binocular camera head delivers a 146° × 124° field of view with a 60 mm stereo baseline for scene-level understanding. RGB streams at 1280×720@30 Hz and depth at 544×448@10 Hz. Combined with the MID360 LiDAR, wrist RGB cameras, and tendon proprioceptive feedback from each hand, the R1-A5-D Smart H offers the most complete perception stack for research in biomimetic mobile manipulation, active perception, and sensorimotor learning.
Four-array beamforming microphones and dual 3 W speakers enable clear voice capture and synthesis in noisy labs, warehouses, or classrooms. The open audio framework supports custom wake words, multilingual TTS, and integration with LLMs for conversational command-and-control — even while the base is in motion.
At 683 × 520 × 440 mm collapsed (1323 mm elevated), the R1-A5-D Smart H navigates standard doorways, elevators, and lab aisles. The telescopic pillar lowers the upper body for transport and raises it for manipulation. At approximately 30 kg with battery, it is a self-contained mobile research platform — no external compute rack, no tether cables during operation.
Collapsed (683 mm) and elevated (1323 mm) configurations for navigation and manipulation
Unitree provides a mature, Linux-based robot development framework with open APIs for the underlying system, robotic arms, mobile base, audio, lighting, visual control, and tendon-driven hand control. ROS 2 native support, dual encoders on every arm joint, and hollow internal wiring make the R1-A5-D Smart H a clean slate for reinforcement learning, biomimetic manipulation research, embodied AI, and autonomous navigation studies. The built-in Orin Nano 40 TOPS handles multi-modal perception and planning locally without external hardware.
Smart H is the top tendon-driven mobile configuration. Expand further with platform-level upgrades:
| Model | Unitree R1-A5-D Smart H (Mobile Base) |
| Dimensions (Collapsed) | 683 × 520 × 440 mm (H × W × D) |
| Dimensions (Elevated) | 1323 × 520 × 440 mm (H × W × D) |
| Weight (with Battery) | ~30 kg |
| Total DOF | 16 (Arm 5×2, Waist 1, Head 2, Pillar 1, Base 2) |
| Arm Reach | 420 mm (forearm + upper arm) |
| Peak Shoulder Torque | 60 Nm |
| Max Arm Payload | ~2 kg (posture-dependent) |
| End-Effector Precision | ±0.1 mm |
| End Effectors | Tendon-driven dexterous hands with wrist RGB cameras (both arms, pre-installed) |
| Hand Actuation | Tendon-driven (cable-and-pulley) with proximal motor placement and backdrivable joints |
| Wrist Cameras | RGB camera integrated into each tendon-driven hand for close-up visual feedback |
| Vision | Binocular camera — RGB 1280×720@30 Hz, Depth 544×448@10 Hz, FOV 146°×124° |
| LiDAR | MID360 360° LiDAR (chassis-integrated) |
| 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 (built-in) |
| Audio | 4-array microphone + dual 3 W speakers |
| Connectivity | Wi-Fi 6, Bluetooth 5.2, OTA updates |
| Power | Removable chassis Li-ion battery (~1.5 h) + external DC PSU. Upper body does not accept a battery. |
| SDK & Interfaces | Linux-based framework, ROS 2, open APIs for arm/base/audio/vision/tendon/lighting |
| Controllers | Standard dual-hand controllers included |
| Warranty | 12 months on the entire unit |
Every configuration shares the same R1-A5-D mobile base — the difference is the end effector. Choose the one that matches your research goals:
| Config | Hand | Features |
|---|---|---|
| Smart A | Dex1-1 V2 | Entry-level parallel grippers, Orin Nano 40 TOPS, MID360 LiDAR |
| Smart B | Dex3-1 (RGB) | 3-finger dexterous hand with wrist RGB camera |
| Smart C | Dex3-1 Tactile (RGB) | 3-finger hand with tactile sensors + wrist RGB camera |
| Smart D | BrainCo Revo 2 Basic (RGB) | 5-finger anthropomorphic hand with wrist RGB camera |
| Smart E | BrainCo Revo 2 Tactile (RGB) | 5-finger hand with tactile sensors + wrist RGB camera |
| Smart F | LinkerBot O6 (RGB) | 6-DOF dexterous hand with wrist RGB camera |
| Smart G | LinkerBot O6 Tactile (RGB) | 6-DOF hand with tactile sensors + wrist RGB camera |
| Smart H | Tendon-driven dexterous hand (RGB) | Advanced tendon-driven mechanism for research-grade biomimetic dexterity |
* Specifications are based on manufacturer data and may vary slightly by production batch. Optional compute modules and alternative end effectors sold separately.
Unitree® is a registered trademark of Unitree Robotics. Images are for reference; actual product appearance may differ.
Users must maintain a sufficient safety distance. This is a civilian robot — comply with local laws and regulations.
Mobile-Base Dual-Arm Humanoid Robot with Tendon-Driven Dexterous Hands & Wrist RGB Cameras. 16 DOF, Orin Nano 40 TOPS, MID360 LiDAR, stereo vision & full-stack open SDK. The ultimate research-grade tendon-driven mobile manipulation platform.
R1-A5-D Smart H — mobile-base humanoid with tendon-driven dexterous hands, wrist RGB cameras, MID360 LiDAR & stereo vision
The R1-A5-D Smart H represents the pinnacle of the R1-A5-D lineup, featuring tendon-driven dexterous hands that deliver research-grade anthropomorphic dexterity. Unlike gear-driven or linkage-based alternatives, the tendon-driven mechanism uses cable-and-pulley actuation routed through the wrist — enabling high-DOF finger control, backdrivable compliance, and human-like grasping dynamics. This is the configuration for researchers who demand the most biomimetic manipulation capabilities available on a mobile humanoid platform.
The tendon-driven hands on the R1-A5-D Smart H use cable-and-pulley actuation — the same biomechanical principle that powers human fingers. Motors mounted in the forearm pull polymer or steel tendons routed through the wrist joint to actuate each finger independently. This architecture delivers several advantages over conventional gear-driven or linkage-based hands: backdrivability — the fingers yield when pushed and report contact forces for natural force control; lightweight distal segments — all heavy actuators stay proximal, keeping the fingers agile and fast; high-DOF articulation — independent control of multiple joints per finger enables human-like grasp postures across the full GRASP taxonomy; and compliant interaction — tendon elasticity absorbs impacts and enables safe physical human-robot interaction without rigid force transmission. The result is a hand that moves, feels, and responds like a human hand — essential for research in biomimetic manipulation, neuroscience-inspired robotics, and advanced embodied AI.
Tendon-driven dexterous hands with cable-and-pulley actuation and wrist RGB cameras
Smart H is the only R1-A5-D configuration to feature true tendon-driven actuation — enabling the full range of human grasp types from precision pinches to power grips and in-hand manipulation. The tendon architecture allows independent control of each finger joint with backdrivable compliance, meaning the hand can adapt its grip shape to object geometry in real time, sense contact forces through the same tendons that drive motion, and execute delicate manipulation tasks like rotating objects in-hand or threading needles while the mobile base navigates between workstations. This biomimetic approach bridges the gap between robotic manipulation and human motor control — opening research frontiers in neuroscience-inspired robotics, prosthetics validation, and human-level dexterity benchmarks.
Smart H processes synchronized streams from four sensor modalities on the Orin Nano 40 TOPS: proprioceptive tendon tension and joint encoder data from each hand, close-up RGB from wrist cameras, scene-level depth from the head binocular camera, and 360° point clouds from the MID360 LiDAR. The tendon-driven architecture adds a unique dimension — force transparency — where every actuated joint simultaneously serves as a motor and a sensor. Push on a finger and it yields, reporting exactly how hard you pushed. This force-proprioceptive stream fuses with visual and LiDAR data for a complete multi-modal perception pipeline: visual servoing guides the hand to the object, LiDAR ensures safe navigation, and tendon force feedback closes the grasp loop — enabling research in force-aware mobile manipulation, slip detection and compensation during locomotion, and sensorimotor learning with biomimetic actuation.
The R1-A5-D chassis adds 3 degrees of freedom to the upper body: a telescopic pillar for height adjustment and a 2-DOF wheeled base for omnidirectional navigation. Combined with the MID360 LiDAR and stereo camera head, the robot builds real-time maps, plans paths, and avoids obstacles autonomously — then stops precisely to manipulate. The removable lithium-ion battery in the chassis delivers approximately 1.5 hours of untethered operation.
The built-in NVIDIA Jetson Orin Nano delivers 40 TOPS of AI compute, handling simultaneous streams from tendon proprioception, wrist RGB cameras, head binocular vision, and MID360 LiDAR while executing high-dimensional control policies for tendon-driven hands. Run visual-LiDAR fusion networks, grasp stability predictors, tendon tension optimization, and reinforcement learning algorithms with large action spaces locally with sub-millisecond latency. No external GPU server, no cloud dependency — just power on and deploy.
A binocular camera head delivers a 146° × 124° field of view with a 60 mm stereo baseline for scene-level understanding. RGB streams at 1280×720@30 Hz and depth at 544×448@10 Hz. Combined with the MID360 LiDAR, wrist RGB cameras, and tendon proprioceptive feedback from each hand, the R1-A5-D Smart H offers the most complete perception stack for research in biomimetic mobile manipulation, active perception, and sensorimotor learning.
Four-array beamforming microphones and dual 3 W speakers enable clear voice capture and synthesis in noisy labs, warehouses, or classrooms. The open audio framework supports custom wake words, multilingual TTS, and integration with LLMs for conversational command-and-control — even while the base is in motion.
At 683 × 520 × 440 mm collapsed (1323 mm elevated), the R1-A5-D Smart H navigates standard doorways, elevators, and lab aisles. The telescopic pillar lowers the upper body for transport and raises it for manipulation. At approximately 30 kg with battery, it is a self-contained mobile research platform — no external compute rack, no tether cables during operation.
Collapsed (683 mm) and elevated (1323 mm) configurations for navigation and manipulation
Unitree provides a mature, Linux-based robot development framework with open APIs for the underlying system, robotic arms, mobile base, audio, lighting, visual control, and tendon-driven hand control. ROS 2 native support, dual encoders on every arm joint, and hollow internal wiring make the R1-A5-D Smart H a clean slate for reinforcement learning, biomimetic manipulation research, embodied AI, and autonomous navigation studies. The built-in Orin Nano 40 TOPS handles multi-modal perception and planning locally without external hardware.
Smart H is the top tendon-driven mobile configuration. Expand further with platform-level upgrades:
| Model | Unitree R1-A5-D Smart H (Mobile Base) |
| Dimensions (Collapsed) | 683 × 520 × 440 mm (H × W × D) |
| Dimensions (Elevated) | 1323 × 520 × 440 mm (H × W × D) |
| Weight (with Battery) | ~30 kg |
| Total DOF | 16 (Arm 5×2, Waist 1, Head 2, Pillar 1, Base 2) |
| Arm Reach | 420 mm (forearm + upper arm) |
| Peak Shoulder Torque | 60 Nm |
| Max Arm Payload | ~2 kg (posture-dependent) |
| End-Effector Precision | ±0.1 mm |
| End Effectors | Tendon-driven dexterous hands with wrist RGB cameras (both arms, pre-installed) |
| Hand Actuation | Tendon-driven (cable-and-pulley) with proximal motor placement and backdrivable joints |
| Wrist Cameras | RGB camera integrated into each tendon-driven hand for close-up visual feedback |
| Vision | Binocular camera — RGB 1280×720@30 Hz, Depth 544×448@10 Hz, FOV 146°×124° |
| LiDAR | MID360 360° LiDAR (chassis-integrated) |
| 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 (built-in) |
| Audio | 4-array microphone + dual 3 W speakers |
| Connectivity | Wi-Fi 6, Bluetooth 5.2, OTA updates |
| Power | Removable chassis Li-ion battery (~1.5 h) + external DC PSU. Upper body does not accept a battery. |
| SDK & Interfaces | Linux-based framework, ROS 2, open APIs for arm/base/audio/vision/tendon/lighting |
| Controllers | Standard dual-hand controllers included |
| Warranty | 12 months on the entire unit |
Every configuration shares the same R1-A5-D mobile base — the difference is the end effector. Choose the one that matches your research goals:
| Config | Hand | Features |
|---|---|---|
| Smart A | Dex1-1 V2 | Entry-level parallel grippers, Orin Nano 40 TOPS, MID360 LiDAR |
| Smart B | Dex3-1 (RGB) | 3-finger dexterous hand with wrist RGB camera |
| Smart C | Dex3-1 Tactile (RGB) | 3-finger hand with tactile sensors + wrist RGB camera |
| Smart D | BrainCo Revo 2 Basic (RGB) | 5-finger anthropomorphic hand with wrist RGB camera |
| Smart E | BrainCo Revo 2 Tactile (RGB) | 5-finger hand with tactile sensors + wrist RGB camera |
| Smart F | LinkerBot O6 (RGB) | 6-DOF dexterous hand with wrist RGB camera |
| Smart G | LinkerBot O6 Tactile (RGB) | 6-DOF hand with tactile sensors + wrist RGB camera |
| Smart H | Tendon-driven dexterous hand (RGB) | Advanced tendon-driven mechanism for research-grade biomimetic dexterity |
* Specifications are based on manufacturer data and may vary slightly by production batch. Optional compute modules and alternative end effectors sold separately.
Unitree® is a registered trademark of Unitree Robotics. Images are for reference; actual product appearance may differ.
Users must maintain a sufficient safety distance. This is a civilian robot — comply with local laws and regulations.
가격 변동 내역
관측 날짜별로 평균한 일일 데이터 포인트 하나를 표시합니다.
USD 기준 금액
기록된 모든 상품 가격을 협정 세계시 기준 날짜별로 평균합니다.
🍪 쿠키 설정
성능 측정을 위해 쿠키를 사용합니다. 개인정보 처리방침