About
Description
Unitree Robotics — Smart Series
Unitree R1-A7 Smart E
Upper-Body Dual-Arm Humanoid Robot with BrainCo Revo 2 Tactile Five-Finger Anthropomorphic Dexterous Hands, Wrist RGB Cameras & Onboard Orin Nano 40 TOPS. 17 DOF, 7-DOF precision arms, 555 mm reach, tactile sensing & full-stack open SDK. The ultimate anthropomorphic tactile manipulation platform.
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 E is the ultimate anthropomorphic tactile manipulation platform. 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 Tactile five-finger anthropomorphic dexterous hands that can both grasp like a human and feel what they touch. Force-sensitive fingertips and palm arrays provide real-time contact feedback across all five fingers, while wrist-mounted RGB cameras deliver close-up visual confirmation. The built-in Orin Nano 40 TOPS compute module handles vision, tactile inference, and multi-modal fusion locally. At just ~13 kg, the R1-A7 Smart E represents the pinnacle of desktop humanoid manipulation research.
✓ 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 Tactile Five-Finger Hands
Anthropomorphic dexterous hands with five independently actuated fingers plus force-sensitive fingertips and palm arrays on both arms. Human-like morphology with tactile sensing.
✓ 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, tactile feature extraction, multi-modal fusion, 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 + Tactile API
Linux framework, ROS 2 native, open APIs for arms, audio, vision, tactile, lighting. Dual encoders per joint. Tactile sensor data streaming included.
Dual 7-DOF Arms. Redundant Kinematics. Human-Like Dexterity.
The R1-A7 Smart E 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 Tactile — Five-Finger Anthropomorphic Dexterity That Feels
The BrainCo Revo 2 Tactile combines the human-like morphology of the Revo 2 Basic with a comprehensive tactile sensing layer. Each hand features five independently actuated fingers with human-like joint architecture, plus force-sensitive arrays covering the fingertips and palm. This means the robot can perform the full repertoire of human grasps — precision pinches, power grips, tripod holds, lateral pinches — while simultaneously measuring contact forces, detecting slip, and modulating grip strength in real time. The tactile feedback transforms anthropomorphic manipulation from a visual-only exercise into a true multi-modal sensorimotor skill. Whether grasping a fragile egg, threading a needle, or shaking a human hand, the Revo 2 Tactile provides the sensory grounding that makes dexterous behavior robust, adaptive, and safe.
Tactile Anthropomorphic Grasping — Feeling What You Grasp
With the BrainCo Revo 2 Tactile hands, the R1-A7 Smart E performs tactile anthropomorphic grasping that bridges the gap between human and robot manipulation. The five-finger configuration supports every grasp type in the human taxonomy, while the tactile sensors provide continuous feedback on contact quality, force distribution, and slip detection. This enables force-controlled manipulation of fragile and deformable objects that would be impossible with vision-only or simpler end effectors. The robot can detect when a grasp is too tight and relax its fingers, feel when an object is slipping and increase grip force, and even explore unknown objects through tactile exploration — all on a compact desktop platform. This capability is essential for research in multi-modal sensorimotor learning, physical human-robot interaction, and advanced dexterous manipulation where contact awareness is as important as visual perception.
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 tactile hands, wrist cameras become even more powerful — they capture finger configurations, contact points, and object pose relative to the palm, enabling detailed visual analysis of grasp quality while the tactile sensors confirm contact forces. This visual-tactile redundancy ensures robust manipulation even when one modality is ambiguous or occluded.
Tactile-Vision-Wrist Fusion — Three-Modal Perception for Manipulation
The R1-A7 Smart E fuses three sensing modalities into a unified perception stack: stereo vision from the head for global scene understanding, close-up RGB from the wrist cameras for local hand-object interaction, and tactile sensing from the hand arrays for contact force feedback. The binocular camera proposes grasps and tracks objects across the workspace. The wrist cameras verify finger positioning and capture grasp geometry in detail. The tactile sensors confirm contact quality, detect slip, and provide force measurements for closed-loop control. The Orin Nano 40 TOPS processes all three streams simultaneously, enabling real-time multi-modal sensor fusion that mimics human sensorimotor coordination. This three-modal architecture is the foundation for the most advanced embodied AI research — from tactile exploration of unknown objects to force-aware 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 tactile anthropomorphic hands, the R1-A7 Smart E achieves human-like reach envelopes with force-aware 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 E ships with a built-in NVIDIA Jetson Orin Nano delivering 40 TOPS of AI compute. This means visual perception, tactile feature extraction, multi-modal fusion, and grasp planning all run in real time locally. Object detection models process head camera frames, finger keypoint detectors analyze wrist camera feeds, tactile CNNs classify contact patterns, and reinforcement learning policies fuse all three modalities — all without external GPU servers or cloud dependency. Just plug in power and start training the most advanced multi-modal manipulation policies on a desktop platform.
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 E 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 E a clean slate for reinforcement learning, teleoperation research, multi-modal sensorimotor learning, and embodied AI. The built-in Orin Nano 40 TOPS handles model training and inference for visual perception, tactile feature extraction, and multi-modal fusion without external hardware. The open SDK includes full control over all five fingers per hand plus high-frequency tactile sensor data streaming, ready for your custom force controllers, slip detectors, and learning algorithms.
Upgrade Path — Grow With Your Research
Start with Smart E and expand as your projects evolve. The R1-A7 platform is fully modular:
- End Effectors — Swap BrainCo Revo 2 Tactile for LinkerBot Hand O6 (6-DOF, tactile and non-tactile versions), Dex3-1 or Dex3-1 Tactile 3-finger hands, or tendon-driven hands for alternative dexterity paradigms.
- 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, wrist camera, and tactile processing.
- Upper-Body Battery — Add the Li-ion battery pack for ~1.5 hours of cord-free operation.
Designed For
Tactile Anthropomorphic Manipulation
Research force-aware human-like grasping, in-hand manipulation, tool use, and dexterous object handling with five-finger tactile hands on a compact desktop platform.
Multi-Modal Sensorimotor Learning
Train RL and imitation learning policies that fuse vision, wrist camera, and tactile feedback for robust, adaptive manipulation strategies that mimic human sensorimotor coordination.
Physical Human-Robot Interaction
Safe handovers, collaborative assembly, responsive interaction, and social robotics where tactile awareness enables natural, force-sensitive contact with humans.
Advanced University Research
Cutting-edge research in tactile sensing, anthropomorphic robotics, multi-modal perception, dexterous control, and embodied AI on the most capable desktop humanoid platform.
Technical Specifications
Description
Unitree Robotics — Smart Series
Unitree R1-A7 Smart E
Upper-Body Dual-Arm Humanoid Robot with BrainCo Revo 2 Tactile Five-Finger Anthropomorphic Dexterous Hands, Wrist RGB Cameras & Onboard Orin Nano 40 TOPS. 17 DOF, 7-DOF precision arms, 555 mm reach, tactile sensing & full-stack open SDK. The ultimate anthropomorphic tactile manipulation platform.
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 E is the ultimate anthropomorphic tactile manipulation platform. 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 Tactile five-finger anthropomorphic dexterous hands that can both grasp like a human and feel what they touch. Force-sensitive fingertips and palm arrays provide real-time contact feedback across all five fingers, while wrist-mounted RGB cameras deliver close-up visual confirmation. The built-in Orin Nano 40 TOPS compute module handles vision, tactile inference, and multi-modal fusion locally. At just ~13 kg, the R1-A7 Smart E represents the pinnacle of desktop humanoid manipulation research.
✓ 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 Tactile Five-Finger Hands
Anthropomorphic dexterous hands with five independently actuated fingers plus force-sensitive fingertips and palm arrays on both arms. Human-like morphology with tactile sensing.
✓ 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, tactile feature extraction, multi-modal fusion, 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 + Tactile API
Linux framework, ROS 2 native, open APIs for arms, audio, vision, tactile, lighting. Dual encoders per joint. Tactile sensor data streaming included.
Dual 7-DOF Arms. Redundant Kinematics. Human-Like Dexterity.
The R1-A7 Smart E 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 Tactile — Five-Finger Anthropomorphic Dexterity That Feels
The BrainCo Revo 2 Tactile combines the human-like morphology of the Revo 2 Basic with a comprehensive tactile sensing layer. Each hand features five independently actuated fingers with human-like joint architecture, plus force-sensitive arrays covering the fingertips and palm. This means the robot can perform the full repertoire of human grasps — precision pinches, power grips, tripod holds, lateral pinches — while simultaneously measuring contact forces, detecting slip, and modulating grip strength in real time. The tactile feedback transforms anthropomorphic manipulation from a visual-only exercise into a true multi-modal sensorimotor skill. Whether grasping a fragile egg, threading a needle, or shaking a human hand, the Revo 2 Tactile provides the sensory grounding that makes dexterous behavior robust, adaptive, and safe.
Tactile Anthropomorphic Grasping — Feeling What You Grasp
With the BrainCo Revo 2 Tactile hands, the R1-A7 Smart E performs tactile anthropomorphic grasping that bridges the gap between human and robot manipulation. The five-finger configuration supports every grasp type in the human taxonomy, while the tactile sensors provide continuous feedback on contact quality, force distribution, and slip detection. This enables force-controlled manipulation of fragile and deformable objects that would be impossible with vision-only or simpler end effectors. The robot can detect when a grasp is too tight and relax its fingers, feel when an object is slipping and increase grip force, and even explore unknown objects through tactile exploration — all on a compact desktop platform. This capability is essential for research in multi-modal sensorimotor learning, physical human-robot interaction, and advanced dexterous manipulation where contact awareness is as important as visual perception.
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 tactile hands, wrist cameras become even more powerful — they capture finger configurations, contact points, and object pose relative to the palm, enabling detailed visual analysis of grasp quality while the tactile sensors confirm contact forces. This visual-tactile redundancy ensures robust manipulation even when one modality is ambiguous or occluded.
Tactile-Vision-Wrist Fusion — Three-Modal Perception for Manipulation
The R1-A7 Smart E fuses three sensing modalities into a unified perception stack: stereo vision from the head for global scene understanding, close-up RGB from the wrist cameras for local hand-object interaction, and tactile sensing from the hand arrays for contact force feedback. The binocular camera proposes grasps and tracks objects across the workspace. The wrist cameras verify finger positioning and capture grasp geometry in detail. The tactile sensors confirm contact quality, detect slip, and provide force measurements for closed-loop control. The Orin Nano 40 TOPS processes all three streams simultaneously, enabling real-time multi-modal sensor fusion that mimics human sensorimotor coordination. This three-modal architecture is the foundation for the most advanced embodied AI research — from tactile exploration of unknown objects to force-aware 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 tactile anthropomorphic hands, the R1-A7 Smart E achieves human-like reach envelopes with force-aware 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 E ships with a built-in NVIDIA Jetson Orin Nano delivering 40 TOPS of AI compute. This means visual perception, tactile feature extraction, multi-modal fusion, and grasp planning all run in real time locally. Object detection models process head camera frames, finger keypoint detectors analyze wrist camera feeds, tactile CNNs classify contact patterns, and reinforcement learning policies fuse all three modalities — all without external GPU servers or cloud dependency. Just plug in power and start training the most advanced multi-modal manipulation policies on a desktop platform.
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 E 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 E a clean slate for reinforcement learning, teleoperation research, multi-modal sensorimotor learning, and embodied AI. The built-in Orin Nano 40 TOPS handles model training and inference for visual perception, tactile feature extraction, and multi-modal fusion without external hardware. The open SDK includes full control over all five fingers per hand plus high-frequency tactile sensor data streaming, ready for your custom force controllers, slip detectors, and learning algorithms.
Upgrade Path — Grow With Your Research
Start with Smart E and expand as your projects evolve. The R1-A7 platform is fully modular:
- End Effectors — Swap BrainCo Revo 2 Tactile for LinkerBot Hand O6 (6-DOF, tactile and non-tactile versions), Dex3-1 or Dex3-1 Tactile 3-finger hands, or tendon-driven hands for alternative dexterity paradigms.
- 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, wrist camera, and tactile processing.
- Upper-Body Battery — Add the Li-ion battery pack for ~1.5 hours of cord-free operation.
Designed For
Tactile Anthropomorphic Manipulation
Research force-aware human-like grasping, in-hand manipulation, tool use, and dexterous object handling with five-finger tactile hands on a compact desktop platform.
Multi-Modal Sensorimotor Learning
Train RL and imitation learning policies that fuse vision, wrist camera, and tactile feedback for robust, adaptive manipulation strategies that mimic human sensorimotor coordination.
Physical Human-Robot Interaction
Safe handovers, collaborative assembly, responsive interaction, and social robotics where tactile awareness enables natural, force-sensitive contact with humans.
Advanced University Research
Cutting-edge research in tactile sensing, anthropomorphic robotics, multi-modal perception, dexterous control, and embodied AI on the most capable desktop humanoid platform.
Technical Specifications
Unitree
by
Unitree
Unitree R1-A7 Smart E Humanoid Robot
- Regular price
- $17,690.00
- Sale price
- $17,690.00
- 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
