R1-A5-D Ultimate D — mobile-base humanoid with BrainCo Revo 2 Basic five-finger hands, wrist RGB cameras, MID360 LiDAR & stereo vision

What's in This Configuration

The R1-A5-D Ultimate D upgrades to BrainCo Revo 2 Basic five-finger anthropomorphic hands — bringing a human-like hand form factor to the mobile platform. Each hand features five independently actuated fingers (thumb, index, middle, ring, pinky) with a thumb-opposable architecture that mirrors human hand kinematics. This enables the full GRASP taxonomy: from precision pinches to power grips, tool manipulation, and in-hand reorientation of objects designed for human hands. Combined with wrist RGB cameras and the NVIDIA Jetson Orin NX 100 TOPS compute module with 16 GB LPDDR5 and dual DLA cores, Ultimate D is the platform for researchers exploring anthropomorphic manipulation, affordance learning, and human-robot interaction on a mobile base.

BrainCo Revo 2 Basic — Five Fingers, Human Form

The BrainCo Revo 2 Basic is a five-finger anthropomorphic hand designed to replicate the kinematic structure and grasp capabilities of the human hand. Each hand features five independently actuated fingers — thumb, index, middle, ring, and pinky — with a fully opposable thumb that enables precision pinches, lateral grasps, and power grips across the full GRASP taxonomy. Unlike three-finger alternatives, the five-finger architecture can manipulate tools designed for human hands: screwdrivers, hammers, scissors, keyboards, and door handles. On a mobile platform, this means the robot can navigate to a workstation, pick up a human tool, use it, and return it — opening research in tool-use learning, affordance discovery, and anthropomorphic mobile manipulation. The Orin NX 100 TOPS provides the compute to run hand-pose estimation, grasp planning for five-finger configurations, and visual servoing in real time.

BrainCo Revo 2 Basic five-finger anthropomorphic hands with wrist RGB cameras

Anthropomorphic Grasping — Built for Human Tools

Ultimate D is designed for anthropomorphic mobile manipulation — the ability to use the world as humans do. The BrainCo Revo 2 Basic hands can grasp a hammer by the handle (cylindrical power grip), pick up a screw between thumb and index finger (precision pinch), hold a smartphone with a tripod grasp, and operate a door handle with a hook grasp. The wrist RGB cameras provide close-up visual feedback to verify finger placement and monitor tool orientation during use. Combined with the head stereo camera for scene understanding and MID360 LiDAR for safe navigation, the robot builds a complete perception-action loop: see the tool, navigate to it, grasp it like a human, use it, and put it back. The Orin NX 100 TOPS with dual DLA cores runs hand-pose estimation, affordance prediction, and grasp planning networks in parallel — enabling research in tool-use learning, hand pose estimation, and embodied AI that interacts with human-designed environments.

Vision-LiDAR-Wrist Fusion — Three-Scale Perception for Anthropomorphic Manipulation

Ultimate D processes synchronized streams from three sensor modalities on the Orin NX 100 TOPS: close-up RGB from wrist cameras, scene-level depth from the head binocular camera, and 360° point clouds from the MID360 LiDAR. The dual DLA cores run wrist-camera hand-pose estimation and head-camera scene parsing in parallel while the GPU handles LiDAR SLAM and multi-camera fusion — no resource contention even under full load. With 16 GB RAM, the system can hold multiple perception models in memory: a wrist-camera finger tracker, a head-camera affordance detector, a LiDAR localization network, and a grasp planner for five-finger configurations — all running concurrently. This three-scale perception enables research in anthropomorphic mobile manipulation, tool-use learning, affordance prediction, hand pose research, and embodied AI that operates in human-designed spaces.

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 NX 100 TOPS — Flagship Compute for Entry-Level Manipulation

The built-in NVIDIA Jetson Orin NX delivers 100 TOPS of AI compute across an 8-core CPU, 16 GB LPDDR5, and dual NVDLA V2.0 accelerators. With BrainCo Revo 2 Basic five-finger hands and wrist cameras, this compute headroom enables advanced anthropomorphic mobile manipulation: run real-time SLAM with MID360 LiDAR, process stereo depth and wrist-camera streams simultaneously, deploy learned grasp policies for five-finger configurations, and experiment with tool-use learning and affordance prediction — all at once. The dedicated DLA cores offload vision networks from the GPU, leaving GPU resources free for sensor fusion, hand-pose estimation, and grasp planning. The 16 GB RAM provides space for large models that would not fit on an 8 GB module. No external GPU server, no cloud dependency — just power on and deploy.

Binocular Vision & Scene 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 and wrist-mounted RGB cameras on each BrainCo Revo 2 Basic hand, the R1-A5-D Ultimate D offers a complete perception stack for anthropomorphic mobile manipulation research — with the Orin NX 100 TOPS processing all streams concurrently via DLA-accelerated networks.

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 Ultimate D 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, and visual control. ROS 2 native support, dual encoders on every arm joint, and hollow internal wiring make the R1-A5-D Ultimate D a clean slate for reinforcement learning, anthropomorphic mobile manipulation research, embodied AI, and hand pose estimation studies. The built-in Orin NX 100 TOPS with dual DLA cores and 16 GB RAM handles visual-LiDAR fusion, five-finger grasp planning, and tool-use learning locally — with compute headroom for larger models and multi-robot coordination without hardware limits.

Upgrade Path — Grow With Your Research

Ultimate D is the entry point with flagship compute already installed. The Orin NX 100 TOPS, 16 GB RAM, and dual DLA cores provide headroom to grow:

• End Effectors — Upgrade to BrainCo Revo 2 Tactile, LinkerBot O6, or tendon-driven hands as your manipulation needs evolve. The compute is already ready.
• Wrist Cameras — Add RGB cameras to the grippers for close-up visual feedback and grasp verification.
• Tactile Sensing — Integrate force-sensitive fingertips for contact-aware grasping.
• Large Vision-Language Models — Run VLA policies and multi-modal foundation models locally without quantization.

Designed For

Technical Specifications

What's in the Box

• Unitree R1-A5-D Ultimate D Humanoid Robot (mobile base)
• BrainCo Revo 2 Basic 5-finger anthropomorphic hands with wrist RGB cameras (pre-installed, both arms)
• NVIDIA Jetson Orin NX 100 TOPS compute module with 16 GB RAM & dual DLA cores (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 and compute module. Choose the one that matches your research goals: