TechMedix Insights
Failure modes & predictive maintenance
Real failure signatures we track across autonomous fleets — what breaks, the telemetry that flags it, and how early TechMedix predicts it. Every entry is derived from the same platform models that power the live console.
Humanoids
43-DOF bimanual humanoid with Dex1 hands. VLA-capable via UnifoLM-VLA-0. Official TechMedix partner platform.
Compact humanoid at ~178cm with 26 DOF. Official TechMedix partner platform with full URDF model available for interactive 3D teardown.
Full-size humanoid at ~178cm, ~70kg with 360° depth sensing via 3D LiDAR + depth camera. 14 DOF in arms (7×2), extended battery for long-shift warehouse and logistics deployment.
Full-size humanoid at ~178cm with 29 DOF. Hydraulic actuation on legs, electric on arms. Extended range and payload vs H1. Official TechMedix partner platform with full URDF model.
Commercial humanoid for automotive assembly. 28 total DOF, 16 DOF hands, 20kg payload. OpenAI-trained reasoning. BMW Group deployment.
Tesla's 3rd-gen humanoid. 173cm / 57kg, 22 DOF hands, FSD-derived perception stack, designed for Tesla factory operations.
Warehouse-specialized bipedal. 175cm / ~65kg, 16kg payload, 4h battery with hot-swap capability. Deployed at Amazon for tote handling and logistics.
Open-source reference humanoid. 25+2 DOF, DIY-kit available, 1.2 m tall, 35 kg. Full BOM and assembly manual published. Designed for researchers and builders.
Industrial humanoid (~175cm, ~80kg) designed for logistics and defence. 19 DOF upper body, π0 diffusion policy control. Deployed for real-world military evaluation.
1.2 m open-source biped. CERN-OHL-S-2.0 hardware, GPL-2.0 software. 25 actuated DOF, MuJoCo sim model, full mechanical CAD (7 subassemblies), electrical wiring harness. DIY kit $15K — ships summer 2026.
Ultra-lightweight humanoid at $4,900. 20 DOF, PMSM motors, 2-DOF head. Entry-level platform for education, research, and entertainment.
Open-source DIY humanoid kit by Menlo Research (asimovinc). 1.2 m, 35 kg, 25+2 DOF. Full CAD, electrical schematics, and MuJoCo simulation models publicly available under CERN-OHL-S-2.0.
Entry humanoid in the UWORLD U1 line. Balanced height and payload for research, education, and light enterprise trials. MSRP $16,500.
Mid-tier UWORLD U1 with expanded payload and longer runtime. Dexterous hands and unrestricted developer access for AI training. MSRP $23,400.
Flagship UWORLD U1. Industrial-grade full-size humanoid with maximum payload, extended runtime, and the full UWORLD perception stack. MSRP from $121,400.
Industrial & AMR
Industrial quadruped (~60kg). 40kg sustained walking load / 120kg standing payload, IP67-rated. The fastest running industrial quadruped at 6m/s. Modular expandable architecture for inspection, survey, and security.
Industry-standard inspection quadruped. Arm-optional, API-first, payload-extensible. Deployed in 50+ industries.
Autonomous mobile robot for warehouse pod movement. LiDAR-only navigation, no camera dependence for safety.
True open-source 6-DOF robot arm — hardware blueprints, full BOM, and 3D print files published on GitHub. Python SDK, ROS1, ROS2, Isaac Sim, and LeRobot compatible. Same simulation stack as ROBO-1. Pre-integration: monitoring adoption curve for full TechMedix onboarding.
6-DOF robot arm with gripper, built for teachable, repeatable automation. Train a policy once on demonstration data, deploy to any ROBO-1 in the fleet. Native LeRobot support, MuJoCo digital twin, Agent API.
Flagship edge AI compute module for humanoid robots, surgical systems, and industrial AI. Blackwell GPU, 128GB LPDDR5X, 40-130W. Ships with JetPack 7 / Ubuntu 24.04 / CUDA 13.0. Developer kit $3,499, GA August 2025.
100% solar-powered agricultural robot for chemical-free weed control at plant level. 350W panel, all-wheel drive, stereo depth vision (gen2), intelligent mesh fleet coordination. Featured by NVIDIA Robotics (April 2026). Deployed in California Central Valley.
Drones & UAVs
50L agricultural spray drone. Dual atomized + broadcast spreading. Active phased-array radar obstacle avoidance.
Enterprise inspection drone (~1.1kg). NVIDIA Jetson-based autonomy, 48MP EO + 640×512 thermal dual sensor. IP55-rated. Used in infrastructure inspection.
Fixed-wing VTOL delivery drone. 16km delivery radius (32km roundtrip), 112km/h cruising speed, 3.6kg payload. Autonomous dock-to-dock with precision descent droid. Medical and commercial delivery.
Larger-capacity variant of T50. 60L tank, extended tank increases center-of-gravity shift failure risk.
Enterprise inspection platform. RTK positioning. Modular payload system. High IP rating for outdoor ops.
Delivery Robots
Sidewalk delivery robot (~73kg). LiDAR + camera fusion, 4-wheel drive, 10km/h top speed. Deployed in LA and Dallas for food delivery.
Campus delivery robot (~23kg). 6-wheel drive, 10kg payload. L4 autonomy with remote assist. Operates in 50+ cities.
Micromobility
4th-gen shared e-scooter. 350W motor, swappable battery, 37mi range, IoT-connected with GNSS. UL 2271/2272 certified. Deployed in 200+ cities.
3rd-gen shared scooter. 1kWh battery (IP68-rated), 30mi range, GPS geofencing, reinforced frame. 350W motor. UL-certified.
Commercial cargo e-bike. 750W motor, 350lb total payload. Used for last-mile delivery fleets and campus logistics.
Data Center
Autonomous security rover. 360° sensor coverage, 24-hr continuous patrol, deployed in data centers and corporate campuses.
Autonomous floor-scrubbing robot. 5,000 sqm/hr coverage, 45L tank. Standard fit for large data center raised-floor environments.
Inventory AMR for high-density warehouse and data center supply rooms. 68kg payload, 8hr runtime, autonomous navigation.
How TechMedix predicts failures
The methodology behind the 48-hour prediction window — telemetry ingestion, failure-mode modeling, and confidence scoring.
Read the methodology →Don't wait for it to break
Get the failure-mode brief
Free 30-minute diagnostic review with a BlackCat engineer. We'll show you exactly which signatures apply to your fleet and how the 48-hour alert window works.
Field guides & deep dives
Practical writing on predictive maintenance and failure modes.