R1-A5-D Ultimate C — mobile-base humanoid with Dex3-1 three-finger hands, wrist RGB cameras, MID360 LiDAR & stereo vision

What's in This Configuration

The R1-A5-D Ultimate C adds integrated tactile sensing to the Dex3-1 three-finger hands — combining force-sensitive fingertips and palm arrays with wrist RGB cameras and the NVIDIA Jetson Orin NX 100 TOPS compute module. The tactile sensors enable pressure mapping, contact detection, and slip prediction across all three fingers, transforming the Dex3-1 from a visually-guided manipulator into a touch-aware dexterous hand. With 16 GB RAM and dual DLA cores, the Orin NX fuses tactile pressure maps, wrist-camera RGB, head stereo depth, and MID360 LiDAR point clouds in real time — enabling research in multi-modal sensorimotor learning, physical human-robot interaction, and compliant grasping on a mobile platform.

Dex3-1 Tactile — Feel What You Grasp

The Dex3-1 Tactile takes the three-finger dexterity of the standard Dex3-1 and adds force-sensitive tactile sensors integrated into the fingertips and palm surfaces of each hand. These sensors deliver real-time pressure maps, contact location data, and slip detection — enabling the hand to feel what it grasps, not just see it. On a mobile platform, this is transformative: the robot can detect when a grasp is unstable during transport, modulate grip force to avoid crushing fragile objects while navigating, and use tactile feedback to complete grasps in visually occluded environments where cameras cannot see. The tactile stream runs at high frequency into the Orin NX 100 TOPS, where it fuses with wrist-camera RGB, head stereo depth, and LiDAR point clouds for a complete multi-modal perception pipeline.

Dex3-1 Tactile three-finger hands with force-sensitive sensors and wrist RGB cameras

Tactile-Visual-LiDAR Fusion — Multi-Modal Perception on the Move

Ultimate C processes synchronized streams from four sensor modalities on the Orin NX 100 TOPS: tactile pressure maps from each Dex3-1 Tactile hand, 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 vision and tactile processing networks in parallel while the GPU handles multi-modal fusion and SLAM — no resource contention even under full load. With 16 GB RAM, the system can hold multiple models simultaneously: a tactile slip detector, a wrist-camera grasp verifier, a head-camera scene parser, a LiDAR localization network, and a tactile-visual-LiDAR fusion policy. This four-modality perception enables research in tactile mobile manipulation, multi-modal sensorimotor learning, physical human-robot interaction, compliant grasping with force feedback while navigating, and embodied AI where touch, vision, and spatial awareness converge.

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 Dex3-1 Tactile hands, wrist cameras, and multi-modal sensor fusion, this compute headroom enables advanced tactile mobile manipulation: run real-time SLAM with MID360 LiDAR, process stereo depth, wrist-camera, and high-frequency tactile streams simultaneously, deploy learned grasp policies with force feedback, and experiment with multi-modal sensorimotor learning — all at once. The dedicated DLA cores offload vision and tactile networks from the GPU, leaving GPU resources free for multi-modal fusion, grasp planning, and compliant control. 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, wrist-mounted RGB cameras, and tactile sensor arrays on each Dex3-1 Tactile hand, the R1-A5-D Ultimate C offers the most complete perception stack for tactile mobile manipulation research — with the Orin NX 100 TOPS processing all four sensor modalities 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 C 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 tactile sensing. ROS 2 native support, dual encoders on every arm joint, and hollow internal wiring make the R1-A5-D Ultimate C a clean slate for reinforcement learning, tactile mobile manipulation research, embodied AI, and multi-modal sensorimotor learning. The built-in Orin NX 100 TOPS with dual DLA cores and 16 GB RAM handles tactile-visual-LiDAR fusion, grasp planning with force feedback, and compliant control locally — with compute headroom for larger models and multi-robot coordination without hardware limits.

Upgrade Path — Grow With Your Research

Ultimate C 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 Dex3-1, BrainCo Revo 2, 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 C Humanoid Robot (mobile base)
• Dex3-1 Tactile 3-finger dexterous 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: