About
Description
Unitree Robotics
Unitree R1-A7-D Ultimate B
Mobile-Base Dual-Arm Humanoid Robot with Dex3-1 Three-Finger Dexterous Hands, Wrist RGB Cameras, 7-DOF Arms & Onboard Orin NX 100 TOPS. 20 DOF, 7-DOF Arms, MID360 LiDAR. High-performance visual manipulation research.
20
Total DOF
7+7
Arm DOF
120
Nm Torque
~2
kg Payload
100
TOPS AI
What's in This Configuration
The R1-A7-D Ultimate B is the high-performance visual manipulation platform. It pairs the R1-A7-D autonomous mobile base — complete with 7-DOF arms, MID360 LiDAR, stereo vision, and a removable chassis battery — with Dex3-1 three-finger dexterous hands, wrist-mounted RGB cameras, and the powerful NVIDIA Jetson Orin NX 100 TOPS compute module. The 2.5× AI performance boost over the Smart series enables real-time processing of dual wrist camera streams alongside stereo vision, running larger visual models for grasp pose estimation, visual servoing, and active perception — all onboard without external hardware.
✓ R1-A7-D Mobile Base Body
Full upper-body humanoid on a wheeled autonomous chassis: dual 7-DOF arms, 1-DOF waist, 2-DOF head, 1-DOF pillar, 2-DOF base. 683×520×440 mm collapsed, ~32 kg with battery.
✓ Dex3-1 Three-Finger Hands
Adaptive three-finger dexterous hands with independent finger actuation for power grasps, precision holds, and in-hand manipulation. Pre-installed on both arms.
✓ Wrist RGB Cameras
Wrist-mounted RGB cameras pre-installed on both arms for close-up visual feedback, grasp pose estimation, and visual servoing during manipulation.
✓ MID360 LiDAR
360° surround LiDAR integrated into the mobile chassis for real-time SLAM, obstacle avoidance, and autonomous navigation.
✓ Orin NX 100 TOPS
Built-in NVIDIA Jetson Orin NX delivering 100 TOPS — 2.5× the AI compute of the Smart series for larger vision models and faster multi-stream processing.
✓ Full-Stack Open SDK
Linux framework, ROS 2 native, open APIs for arms, base, audio, vision, lighting. Wrist camera API included. Dual encoders per joint.
Dex3-1 — Three-Finger Dexterity
The Dex3-1 is a three-finger adaptive dexterous hand that bridges the gap between simple parallel grippers and complex multi-DOF anthropomorphic designs. Each of the three fingers is independently actuated, allowing the hand to conform to irregular object shapes, execute stable tripod grasps, and perform basic in-hand manipulation such as finger-gaiting and object reorientation. The opposed thumb configuration provides natural antagonism for both power and precision grasps, while the compact form factor keeps the hand lightweight and responsive. Pre-installed on both 7-DOF arms, the Dex3-1 transforms the Ultimate B into a capable visual manipulation platform where the 100 TOPS Orin NX can fully exploit the richness of dual wrist camera streams for learning-based grasping and active perception.
Wrist-Mounted RGB Cameras — Close-Up Visual Feedback
Ultimate B includes wrist-mounted RGB cameras pre-installed on both arms, providing a local, egocentric view of the manipulation workspace. These cameras capture fine geometric detail, texture, and finger-object contact geometry that the head-mounted stereo pair cannot resolve at distance. The 100 TOPS Orin NX processes both wrist streams in real time alongside the head camera feed, enabling two-scale visual perception: global scene understanding from the head camera and local grasp refinement from the wrists. This dual-stream architecture supports visual servoing, grasp pose estimation from multiple viewpoints, and learning-based manipulation policies that leverage high-resolution close-up visual feedback.
Vision-Wrist Fusion — Two-Scale Perception
Ultimate B fuses two complementary visual modalities on the Orin NX 100 TOPS: the head-mounted binocular camera provides global scene understanding, object detection, and navigation-grade depth estimation, while the wrist-mounted RGB cameras deliver local visual feedback of finger-object interaction at close range. This vision-wrist fusion creates a rich multi-scale representation of manipulation — enabling the robot to locate an object in the scene, plan an approach trajectory, and refine the grasp using wrist-camera feedback in a closed visual servoing loop. The 100 TOPS compute headroom allows running larger visual backbones and more sophisticated fusion algorithms than the Smart series, supporting cutting-edge research in visual imitation learning, active perception, and cross-viewpoint feature matching for manipulation.
7-DOF Arms — Human-Like Redundancy & Reach
The R1-A7-D features seven degrees of freedom per arm — matching the kinematic complexity of the human upper limb. With a 555 mm reach (forearm + upper arm) and 120 Nm peak shoulder torque, these arms can reach around obstacles, maintain orientation while translating the end effector, and execute complex trajectories impossible for simpler 5- or 6-DOF manipulators. Crossed-roller and double-row ball bearings on every joint ensure smooth, precise motion with minimal backlash. Dual encoders per joint provide closed-loop accuracy for research-grade repeatability.
Orin NX 100 TOPS — 2.5× AI Performance for Visual Manipulation
The built-in NVIDIA Jetson Orin NX delivers 100 TOPS of AI compute — a 2.5× leap over the Smart series' 40 TOPS. For the Ultimate B, this extra headroom is transformative: it enables real-time processing of three simultaneous camera streams (head stereo + dual wrist RGB), larger vision backbones for grasp pose estimation, faster visual servoing loops, and onboard training of visual manipulation policies using reinforcement or imitation learning. The Orin NX also accelerates multi-object tracking, dense depth estimation, and visual-LiDAR fusion for navigation — all while leaving compute budget for concurrent LLM inference or scene graph construction. Pre-installed and thermally integrated with the chassis cooling system, the module runs entirely onboard with no external GPU server or cloud dependency.
Autonomous Mobile Base — Navigate, Then Manipulate
The R1-A7-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. Please note: the upper body of this model does not accept a battery.
LiDAR + Stereo Vision — Complete Perception Stack
Ultimate B processes data from two complementary sensors: a MID360 360° LiDAR for metrically accurate mapping and long-range obstacle detection, and a binocular camera head (146°×124° FOV, 60 mm baseline) for colour vision, object recognition, and depth estimation. Fused on the Orin NX 100 TOPS, this dual-modality perception stack supports research in visual-LiDAR SLAM, semantic navigation, and active perception for mobile manipulation — with enough headroom to also process dual wrist camera streams concurrently.
Binocular Vision & Multi-Camera Perception
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. Wrist-mounted RGB cameras on both arms add close-up visual feedback for grasp refinement and visual servoing. Combined with the MID360 LiDAR, the R1-A7-D Ultimate B offers a rich multi-camera perception stack for research in visual manipulation, active perception, and multi-viewpoint learning — all processed on the 100 TOPS Orin NX.
Voice Collaboration & Natural Interaction
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. The extra compute headroom of the Orin NX 100 TOPS allows running larger speech recognition and language models locally alongside visual manipulation tasks.
Collapsible. Mobile. Ready to Deploy.
At 683 × 520 × 440 mm collapsed (1323 mm elevated), the R1-A7-D Ultimate B navigates standard doorways, elevators, and lab aisles. The telescopic pillar lowers the upper body for transport and raises it for manipulation. At approximately 32 kg with battery, it is a self-contained mobile research platform — no external compute rack, no tether cables during operation.
Full-Stack Open Development
Unitree provides a mature, Linux-based robot development framework with open APIs for the underlying system, robotic arms, mobile base, audio, lighting, and visual control. ROS 2 native support, dual encoders on every arm joint, hollow internal wiring, and low-inertia, high-speed inner-rotor permanent magnet synchronous motors make the R1-A7-D Ultimate B a clean slate for reinforcement learning, visual manipulation research, embodied AI, and autonomous navigation studies. The built-in Orin NX 100 TOPS handles perception, planning, and multi-camera stream processing locally without external hardware, with enough headroom for large-model inference and multi-task learning.
Upgrade Path — Grow With Your Research
Ultimate B is the high-performance visual manipulation configuration. Expand capability as your research evolves:
- End Effectors — Upgrade to BrainCo Revo 2 for anthropomorphic dexterity, LinkerBot O6 for high-DOF manipulation, or tendon-driven hands for biomimetic compliance.
- Tactile Sensing — Integrate force-sensitive tactile arrays for contact-aware grasping and multi-modal sensorimotor learning with the Dex3-1.
- Large VLM — Deploy vision-language models for natural-language task specification and scene understanding. The 100 TOPS Orin NX has the headroom to run larger VLMs entirely onboard.
Designed For
Visual Manipulation
High-performance compute for real-time visual servoing, grasp pose estimation, and learning-based manipulation with three-finger adaptive hands.
Dexterous Grasping
Independent finger actuation enables power grasps, precision holds, tripod grasps, and in-hand manipulation with visual feedback.
Active Perception
Dual wrist cameras + head stereo enable active viewpoint selection, multi-view grasp verification, and visual exploration strategies.
Embodied AI & Bimanual Coordination
100 TOPS supports large vision models for bimanual task planning, cross-arm coordination, and multi-object manipulation policies.
Technical Specifications
What's in the Box
- Unitree R1-A7-D Ultimate B Humanoid Robot (mobile base)
- Dex3-1 three-finger dexterous hands (pre-installed, both arms)
- Wrist RGB camera modules (pre-installed, both arms)
- NVIDIA Jetson Orin NX 100 TOPS compute module (pre-installed)
- Removable chassis lithium-ion battery pack
- External power supply & AC cable
- MID360 LiDAR module (pre-installed in chassis)
- 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
R1-A7-D Configuration Guide
Every configuration shares the same R1-A7-D mobile base with 7-DOF arms — the difference is the compute module and end effector. Choose the one that matches your research goals:
* Specifications are based on manufacturer data and may vary slightly by production batch. Optional wrist cameras, tactile sensors, 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.
Description
Unitree Robotics
Unitree R1-A7-D Ultimate B
Mobile-Base Dual-Arm Humanoid Robot with Dex3-1 Three-Finger Dexterous Hands, Wrist RGB Cameras, 7-DOF Arms & Onboard Orin NX 100 TOPS. 20 DOF, 7-DOF Arms, MID360 LiDAR. High-performance visual manipulation research.
20
Total DOF
7+7
Arm DOF
120
Nm Torque
~2
kg Payload
100
TOPS AI
What's in This Configuration
The R1-A7-D Ultimate B is the high-performance visual manipulation platform. It pairs the R1-A7-D autonomous mobile base — complete with 7-DOF arms, MID360 LiDAR, stereo vision, and a removable chassis battery — with Dex3-1 three-finger dexterous hands, wrist-mounted RGB cameras, and the powerful NVIDIA Jetson Orin NX 100 TOPS compute module. The 2.5× AI performance boost over the Smart series enables real-time processing of dual wrist camera streams alongside stereo vision, running larger visual models for grasp pose estimation, visual servoing, and active perception — all onboard without external hardware.
✓ R1-A7-D Mobile Base Body
Full upper-body humanoid on a wheeled autonomous chassis: dual 7-DOF arms, 1-DOF waist, 2-DOF head, 1-DOF pillar, 2-DOF base. 683×520×440 mm collapsed, ~32 kg with battery.
✓ Dex3-1 Three-Finger Hands
Adaptive three-finger dexterous hands with independent finger actuation for power grasps, precision holds, and in-hand manipulation. Pre-installed on both arms.
✓ Wrist RGB Cameras
Wrist-mounted RGB cameras pre-installed on both arms for close-up visual feedback, grasp pose estimation, and visual servoing during manipulation.
✓ MID360 LiDAR
360° surround LiDAR integrated into the mobile chassis for real-time SLAM, obstacle avoidance, and autonomous navigation.
✓ Orin NX 100 TOPS
Built-in NVIDIA Jetson Orin NX delivering 100 TOPS — 2.5× the AI compute of the Smart series for larger vision models and faster multi-stream processing.
✓ Full-Stack Open SDK
Linux framework, ROS 2 native, open APIs for arms, base, audio, vision, lighting. Wrist camera API included. Dual encoders per joint.
Dex3-1 — Three-Finger Dexterity
The Dex3-1 is a three-finger adaptive dexterous hand that bridges the gap between simple parallel grippers and complex multi-DOF anthropomorphic designs. Each of the three fingers is independently actuated, allowing the hand to conform to irregular object shapes, execute stable tripod grasps, and perform basic in-hand manipulation such as finger-gaiting and object reorientation. The opposed thumb configuration provides natural antagonism for both power and precision grasps, while the compact form factor keeps the hand lightweight and responsive. Pre-installed on both 7-DOF arms, the Dex3-1 transforms the Ultimate B into a capable visual manipulation platform where the 100 TOPS Orin NX can fully exploit the richness of dual wrist camera streams for learning-based grasping and active perception.
Wrist-Mounted RGB Cameras — Close-Up Visual Feedback
Ultimate B includes wrist-mounted RGB cameras pre-installed on both arms, providing a local, egocentric view of the manipulation workspace. These cameras capture fine geometric detail, texture, and finger-object contact geometry that the head-mounted stereo pair cannot resolve at distance. The 100 TOPS Orin NX processes both wrist streams in real time alongside the head camera feed, enabling two-scale visual perception: global scene understanding from the head camera and local grasp refinement from the wrists. This dual-stream architecture supports visual servoing, grasp pose estimation from multiple viewpoints, and learning-based manipulation policies that leverage high-resolution close-up visual feedback.
Vision-Wrist Fusion — Two-Scale Perception
Ultimate B fuses two complementary visual modalities on the Orin NX 100 TOPS: the head-mounted binocular camera provides global scene understanding, object detection, and navigation-grade depth estimation, while the wrist-mounted RGB cameras deliver local visual feedback of finger-object interaction at close range. This vision-wrist fusion creates a rich multi-scale representation of manipulation — enabling the robot to locate an object in the scene, plan an approach trajectory, and refine the grasp using wrist-camera feedback in a closed visual servoing loop. The 100 TOPS compute headroom allows running larger visual backbones and more sophisticated fusion algorithms than the Smart series, supporting cutting-edge research in visual imitation learning, active perception, and cross-viewpoint feature matching for manipulation.
7-DOF Arms — Human-Like Redundancy & Reach
The R1-A7-D features seven degrees of freedom per arm — matching the kinematic complexity of the human upper limb. With a 555 mm reach (forearm + upper arm) and 120 Nm peak shoulder torque, these arms can reach around obstacles, maintain orientation while translating the end effector, and execute complex trajectories impossible for simpler 5- or 6-DOF manipulators. Crossed-roller and double-row ball bearings on every joint ensure smooth, precise motion with minimal backlash. Dual encoders per joint provide closed-loop accuracy for research-grade repeatability.
Orin NX 100 TOPS — 2.5× AI Performance for Visual Manipulation
The built-in NVIDIA Jetson Orin NX delivers 100 TOPS of AI compute — a 2.5× leap over the Smart series' 40 TOPS. For the Ultimate B, this extra headroom is transformative: it enables real-time processing of three simultaneous camera streams (head stereo + dual wrist RGB), larger vision backbones for grasp pose estimation, faster visual servoing loops, and onboard training of visual manipulation policies using reinforcement or imitation learning. The Orin NX also accelerates multi-object tracking, dense depth estimation, and visual-LiDAR fusion for navigation — all while leaving compute budget for concurrent LLM inference or scene graph construction. Pre-installed and thermally integrated with the chassis cooling system, the module runs entirely onboard with no external GPU server or cloud dependency.
Autonomous Mobile Base — Navigate, Then Manipulate
The R1-A7-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. Please note: the upper body of this model does not accept a battery.
LiDAR + Stereo Vision — Complete Perception Stack
Ultimate B processes data from two complementary sensors: a MID360 360° LiDAR for metrically accurate mapping and long-range obstacle detection, and a binocular camera head (146°×124° FOV, 60 mm baseline) for colour vision, object recognition, and depth estimation. Fused on the Orin NX 100 TOPS, this dual-modality perception stack supports research in visual-LiDAR SLAM, semantic navigation, and active perception for mobile manipulation — with enough headroom to also process dual wrist camera streams concurrently.
Binocular Vision & Multi-Camera Perception
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. Wrist-mounted RGB cameras on both arms add close-up visual feedback for grasp refinement and visual servoing. Combined with the MID360 LiDAR, the R1-A7-D Ultimate B offers a rich multi-camera perception stack for research in visual manipulation, active perception, and multi-viewpoint learning — all processed on the 100 TOPS Orin NX.
Voice Collaboration & Natural Interaction
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. The extra compute headroom of the Orin NX 100 TOPS allows running larger speech recognition and language models locally alongside visual manipulation tasks.
Collapsible. Mobile. Ready to Deploy.
At 683 × 520 × 440 mm collapsed (1323 mm elevated), the R1-A7-D Ultimate B navigates standard doorways, elevators, and lab aisles. The telescopic pillar lowers the upper body for transport and raises it for manipulation. At approximately 32 kg with battery, it is a self-contained mobile research platform — no external compute rack, no tether cables during operation.
Full-Stack Open Development
Unitree provides a mature, Linux-based robot development framework with open APIs for the underlying system, robotic arms, mobile base, audio, lighting, and visual control. ROS 2 native support, dual encoders on every arm joint, hollow internal wiring, and low-inertia, high-speed inner-rotor permanent magnet synchronous motors make the R1-A7-D Ultimate B a clean slate for reinforcement learning, visual manipulation research, embodied AI, and autonomous navigation studies. The built-in Orin NX 100 TOPS handles perception, planning, and multi-camera stream processing locally without external hardware, with enough headroom for large-model inference and multi-task learning.
Upgrade Path — Grow With Your Research
Ultimate B is the high-performance visual manipulation configuration. Expand capability as your research evolves:
- End Effectors — Upgrade to BrainCo Revo 2 for anthropomorphic dexterity, LinkerBot O6 for high-DOF manipulation, or tendon-driven hands for biomimetic compliance.
- Tactile Sensing — Integrate force-sensitive tactile arrays for contact-aware grasping and multi-modal sensorimotor learning with the Dex3-1.
- Large VLM — Deploy vision-language models for natural-language task specification and scene understanding. The 100 TOPS Orin NX has the headroom to run larger VLMs entirely onboard.
Designed For
Visual Manipulation
High-performance compute for real-time visual servoing, grasp pose estimation, and learning-based manipulation with three-finger adaptive hands.
Dexterous Grasping
Independent finger actuation enables power grasps, precision holds, tripod grasps, and in-hand manipulation with visual feedback.
Active Perception
Dual wrist cameras + head stereo enable active viewpoint selection, multi-view grasp verification, and visual exploration strategies.
Embodied AI & Bimanual Coordination
100 TOPS supports large vision models for bimanual task planning, cross-arm coordination, and multi-object manipulation policies.
Technical Specifications
What's in the Box
- Unitree R1-A7-D Ultimate B Humanoid Robot (mobile base)
- Dex3-1 three-finger dexterous hands (pre-installed, both arms)
- Wrist RGB camera modules (pre-installed, both arms)
- NVIDIA Jetson Orin NX 100 TOPS compute module (pre-installed)
- Removable chassis lithium-ion battery pack
- External power supply & AC cable
- MID360 LiDAR module (pre-installed in chassis)
- 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
R1-A7-D Configuration Guide
Every configuration shares the same R1-A7-D mobile base with 7-DOF arms — the difference is the compute module and end effector. Choose the one that matches your research goals:
* Specifications are based on manufacturer data and may vary slightly by production batch. Optional wrist cameras, tactile sensors, 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.
Unitree
by
Unitree
Unitree R1-A7-D Ultimate B Humanoid Robot Silver
SKU:
R1-A7-D-Ultimate-B
- Regular price
- $22,490.00
- Sale price
- $22,490.00
- 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
