Skip to content

Unitree Robotics integration

Unitree Robotics and workflow integration

Unitree Robotics manufactures quadruped and humanoid robots with SDKs for movement control. Their hardware serves inspection, security, and research applications. However, like most robotics platforms, they focus on hardware control rather than operational workflow management.

Unitree robot platforms

Quadruped robots:

  • Go2: Consumer quadruped starting at $1,600 with AI vision capabilities
  • B2: Industrial quadruped for inspection and security applications
  • A2: New industrial model with 100kg load capacity and 20km range (2025)
  • B2-W: Hybrid mobility system with wheeled and walking modes

Humanoid robots:

  • G1 Basic: $21,500 for home use with remote control
  • G1 EDU Standard (U1): $42,435 with 100 TOPS AI computing, 23 DOF, programmable
  • G1 EDU Plus (U2): $52,367 with enhanced waist (3 DOF) and 7 DOF arms (29 total DOF)
  • G1 EDU Ultimate A (U3): $64,292 with Dex3-1 three-finger hands (43 DOF)
  • H1: Advanced humanoid for research (approximately $90,000)

Note: Over 1,000 G1 units shipped as of 2025, making it the best-selling humanoid robot.

Software capabilities

Development SDKs:

  • unitree_sdk2: C++ SDK for Go2, B2, H1, G1 using CycloneDDS
  • unitree_sdk2_python: Python interface for robot development
  • unitree_legged_sdk: SDK for Aliengo, A1, Go1, B1 models
  • ROS/ROS2 integration: Native support for robotics middleware
  • Simulation support: MuJoCo and Isaac Lab for virtual testing

Control capabilities:

  • Low-level motor control and custom gait development
  • UDP and DDS communication protocols
  • SLAM for mapping and autonomous navigation
  • AI and machine learning integration
  • Computer vision with NVIDIA Jetson (EDU models)

Real-world deployments

Unitree robots are currently deployed across multiple industries:

Industrial inspection:

  • Thermal power plants for automated equipment monitoring
  • Petrochemical plants in hazardous zones
  • Power grid substations for infrastructure inspection
  • Brewery operations for routine checks

Logistics and warehousing:

  • Material handling and transport
  • Inventory monitoring
  • Warehouse security patrols

Agriculture and environmental:

  • Seedling monitoring in farming operations
  • Terrain assessment and mapping

Research and development:

  • Academic research programs
  • Carnegie Mellon SoFTA project for stable manipulation while walking
  • Caltech/UT Austin SHIELD safety framework testing

Healthcare and service (emerging):

  • Supply delivery assistance
  • Patient monitoring support
  • Customer service demonstrations

Workflow management gaps

Procedure programming: Unitree robots execute hardcoded Python or C++ scripts deployed individually to each robot. When procedures change, engineers must update code, test in simulation, and redeploy to each unit via SSH.

Knowledge sharing: No built-in mechanism exists for sharing learnings across robot fleets. Optimizations discovered by one robot remain isolated unless manually coded and deployed to others.

Operational tracking: Unitree provides telemetry data (battery status, location, sensor readings) but not process-level tracking. No native capability to log which procedures were executed, when tasks were completed, or maintain compliance audit trails.

Multi-robot coordination: Each robot operates independently with its own code version. No centralized system manages what procedures are deployed where or ensures consistency across fleets.

How Tallyfy could address workflow gaps

Dynamic procedure management: Instead of hardcoded scripts, robots could query Tallyfy for current procedures via API. When inspection methods change, updates propagate to all robots without code deployment.

Centralized knowledge base: Robots could access standardized operating procedures stored in Tallyfy templates. New equipment types or scenarios get documented once and become available fleet-wide.

Process tracking and audit trails: Robots could launch Tallyfy processes and mark tasks complete with sensor data, photos, and timestamps. This creates compliance documentation and operational visibility.

Fleet-wide improvements: When optimizations are discovered, they could be documented in Tallyfy procedures and shared across all robots. Changes to SOPs update centrally rather than requiring individual code deployment.

Potential integration architecture

A Tallyfy connector for Unitree could work as middleware between the robot’s SDK and Tallyfy’s API:

Diagram

What to notice:

  • Connector bridges unitree_sdk2 and Tallyfy REST API
  • Procedures stored centrally, not in robot code
  • All operations logged for compliance tracking

Conceptual implementation:

# Hypothetical connector usage
from unitree_sdk2_python import Robot
import requests
robot = Robot()
api_key = "your_tallyfy_api_key"
# Fetch procedure from Tallyfy
response = requests.get(
"https://api.tallyfy.com/procedures/solar_inspection",
headers={"Authorization": f"Bearer {api_key}"}
)
procedure = response.json()
# Execute steps and report completion
for step in procedure['steps']:
# Robot executes based on step data
sensor_data = robot.collect_data(step['location'])
# Report completion to Tallyfy
requests.post(
f"https://api.tallyfy.com/tasks/{step['id']}/complete",
headers={"Authorization": f"Bearer {api_key}"},
json={"sensor_data": sensor_data}
)

Note: This code is conceptual. No official Tallyfy-Unitree connector currently exists.

Potential use cases

Industrial inspection: Robots could fetch site-specific inspection procedures from Tallyfy rather than running hardcoded scripts. When equipment types change, procedures update centrally without touching robot code.

Warehouse operations: Multiple robots could reference the same Tallyfy procedures for patrol routes, inventory checks, or security protocols. Changes to procedures propagate fleet-wide instantly.

Research collaboration: Academic institutions could share experimental protocols through Tallyfy templates. Each robot would execute identical procedures with automatic data logging for reproducibility.

Compliance documentation: Operations requiring audit trails (pharmaceutical, food safety, regulated industries) could have robots log every procedure step, timestamp, and sensor reading in Tallyfy for regulatory review.

Integration requirements

For Unitree robots:

  • Compatible models: Go2, B2, A2, G1, H1
  • Network connectivity (WiFi or cellular for API access)
  • Python 3.8+ environment for custom connector code
  • unitree_sdk2 or unitree_sdk2_python installed

For Tallyfy:

  • Organization account with API access
  • Templates created for robot procedures
  • API credentials for authentication

Technical considerations:

  • Connector middleware development required
  • Network latency for real-time API calls
  • Fallback behavior if connectivity lost
  • Data formatting between SDK and Tallyfy API

Robotics > AppTronik Apollo integration

AppTronik’s Apollo humanoid robot designed for industrial applications is currently in pilot deployment phase with Mercedes-Benz and GXO Logistics but faces workflow management gaps that Tallyfy could address through dynamic procedure querying centralized fleet knowledge sharing and automatic compliance documentation to enable enterprise-scale operations beyond static task programming.

Robotics > KUKA Robotics integration

KUKA robots ranging from collaborative systems to heavy-duty 1300kg units can integrate with Tallyfy through OPC UA or KUKA.Connect protocols to add workflow management capabilities for procedure documentation process tracking audit trails and fleet visibility that complement their robust motion control and programming tools.

Robotics > Universal Robots integration

Universal Robots cobots excel at hardware and local programming through PolyScope X but rely on static programs that create scaling nightmares for enterprise deployments where dynamic workflow management could enable robots to query procedures adapt to variants and maintain compliance across fleets rather than requiring manual USB updates to isolated controllers.

Integrations > Robotics

This section explores robotics workflow management challenges including communication protocols like OPC UA and ROS integration architecture security requirements human-robot collaboration patterns safety compliance technical readiness organizational considerations and industry applications across manufacturing logistics healthcare and food sectors while addressing protocol complexity network security latency sensitivity and legacy system limitations.