R1-A5-D Smart H — mobile-base humanoid with tendon-driven dexterous hands, wrist RGB cameras, MID360 LiDAR & stereo vision

What's in This Configuration

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.

Tendon-Driven Dexterous Hands — Biomimetic Actuation for Research-Grade Dexterity

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

Anthropomorphic Grasping — Human-Like Dexterity on the Move

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.

Tendon-Visual-LiDAR Fusion — Complete Multi-Modal Perception

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.

Autonomous Mobile Base — Navigate, Then Manipulate

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.

Orin Nano 40 TOPS — AI Compute for Tendon-Driven Mobile Control

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.

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. 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.

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.

Collapsible. Mobile. Ready to Deploy.

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

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, 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.

Upgrade Path — Grow With Your Research

Smart H is the top tendon-driven mobile configuration. Expand further with platform-level upgrades:

• Compute Module — Swap to the 100 TOPS expansion for large-model inference, multi-modal learning, and multi-robot coordination.

Designed For

Technical Specifications

What's in the Box

• Unitree R1-A5-D Smart H Humanoid Robot (mobile base)
• Tendon-driven dexterous hands with wrist RGB cameras (pre-installed, both arms)
• NVIDIA Jetson Orin Nano 40 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-A5-D Configuration Guide

Every configuration shares the same R1-A5-D mobile base — the difference is the end effector. Choose the one that matches your research goals:

* 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 r