Software Intelligence

Software Stacks

Eight frameworks powering humanoid robots in 2026 — from physics simulation and RL training to foundation models and runtime middleware. Every stack evaluated for kit-builder relevance.

Frameworks & Platforms

Foundation ModelProprietary

Flagship VLA (vision-language-action) model with diffusion transformer architecture. Cross-embodiment generalization — one model, many robot bodies.

Key Capabilities

  • Natural language instruction following for manipulation + locomotion
  • Sim-to-real pipeline: reduces training from 3 months → 36 hours
  • Cross-embodiment transfer across different humanoid form factors
  • Integrated perception, cognition, and loco-manipulation in one model
  • Parallel GPU training: thousands of robot instances simultaneously

Used By

NEURA RoboticsXPENG RoboticsAeiRobotLightwheelFoxlinkSkild AIGeneral Robotics

Kit Relevance

The de facto industrial standard if you can afford NVIDIA hardware. Requires Jetson AGX Thor or Orin. Highest capability, highest cost.

MuJoCo

Google DeepMind (originally Emo Todorov)

SimulationOpen Source

The most widely used physics engine in academic humanoid RL. Fast, accurate contact-rich dynamics. Free and open-source since 2022.

Key Capabilities

  • Fast contact-rich physics (ideal for bipedal + dexterous hands)
  • MuJoCo Playground: rapid humanoid RL prototyping wrappers
  • Integrates with JAX, PyTorch, and standard RL libraries
  • Domain randomization for sim-to-real
  • pip install mujoco — works on any Linux box with GPU

Used By

StanfordMIT CSAILETH ZurichGoogle DeepMindUnitree (training)Boston Dynamics (research)Asimov (asimov-mjlab)

Kit Relevance

Start here for research and prototyping. Free, well-documented, massive community. Pair with RSL-RL for the RL algorithm layer.

RSL-RL

ETH Zurich Robotic Systems Lab (Marco Hutter's group)

RL TrainingOpen Source

RL training library specifically for legged robot locomotion. Optimized for massively parallel GPU training. Behind ANYmal's locomotion.

Key Capabilities

  • PPO optimized for robotics (thousands of parallel agents)
  • Native Isaac Lab / Isaac Gym integration
  • Curriculum learning + domain randomization
  • Battle-tested by world's best legged robotics lab
  • pip install rsl-rl-lib (v2.1.1)

Used By

ETH ZurichUnitree (community pipelines)Asimov (asimov-mjlab)Humanoid-Gym projectAcademic labs worldwide

Kit Relevance

THE RL algorithm library for training locomotion policies. Free, battle-tested. Use with Isaac Lab (simulation) + domain randomization.

LeRobot

Hugging Face

Imitation LearningOpen Source

Open-source robotics framework with HuggingFace Hub integration. v0.5.0 added humanoid support (Unitree G1). Imitation learning focus.

Key Capabilities

  • Hardware-agnostic Python API for robot control
  • v0.5.0: Unitree G1 humanoid — locomotion, manipulation, teleoperation
  • Pre-trained policy models on HuggingFace Hub
  • Real-Time Chunking and LoRA fine-tuning
  • Best for teaching by demonstration rather than pure RL

Used By

Academic labsUnitree G1 usersOpenArm buildersHobbyist builders

Kit Relevance

Best for imitation learning. Teach your robot to do tasks by demonstration. Pull pre-trained models from the Hub and fine-tune in hours.

Physical Intelligence pi0 (OpenPI)

Physical Intelligence (SF, founded 2023, $400M+ funded)

Foundation ModelOpen Source

Generalist robot foundation model — diffusion-based VLA trained across diverse robot embodiments. The 'GPT-3 for robot motor control.'

Key Capabilities

  • One model handles many robot types and many tasks
  • Flow matching / diffusion-based action generation
  • Fine-tune on a few hours of task-specific data
  • Demonstrated on Franka, UR5, ALOHA bimanual
  • Vision + language instruction → motor commands

Used By

Research labsRobotics startupsCompatible with standard arms (Franka, UR5)

Kit Relevance

Most advanced open foundation model for manipulation. Fine-tune on your gripper/hand. Pairs with separate locomotion stack (RSL-RL for legs, pi0 for arms/hands).

OpenMind OM1

OpenMind

Robot OSOpen Source

Hardware-agnostic robot OS — the 'Android moment' for robotics. FABRIC layer for fleet learning. Plug-and-play LLM integration.

Key Capabilities

  • Hardware-agnostic: AMD64 + ARM64, any robot form factor
  • FABRIC: decentralized identity + cross-robot data sharing
  • Plug-and-play: swap GPT, Gemini, or other LLMs as cognitive modules
  • Modules: voice, vision, SLAM, navigation
  • Docker-based deployment, React-based monitoring UI

Used By

Early developer communityHardware partners

Kit Relevance

Promising OS layer for kit builders who want AI (voice, vision, reasoning) without stitching LLM APIs manually. FABRIC fleet learning is interesting for kit fleets.

K-Scale K-OS + K-Bot

K-Scale Labs (US, ~2024)

Full PlatformOpen Source

Fully open-source humanoid: hardware CAD, Rust-based OS, simulation, ML models. K-Bot: ~140cm, ~35kg, ~$8,999. The 'RISC-V of humanoids.'

Key Capabilities

  • K-Bot: full humanoid, $8,999 Founder's Edition (deliveries mid-2025)
  • K-OS: Rust-based — safer, faster than ROS2 C++/Python
  • EdgeVLA: on-device vision-language-action inference
  • K-Sim: simulation with sim-to-real transfer
  • Modular: swappable batteries, plug-and-play sensors

Used By

Academic researchersHardware hackersRobotics startups

Kit Relevance

MOST RELEVANT to Huma's kit ambitions. Direct comparison: K-Bot $8,999 vs our Kit 01 $11K. Study their architecture closely — competitive AND complementary.

LDA-1B

Open release (~2026; 30k-hour heterogeneous human + robot data)

Foundation ModelOpen Source

Open-source 1.6B-parameter robot foundation model. Trained on ~30,000 hours of mixed human and robot demonstrations — multi-embodiment from the start.

Key Capabilities

  • 1.6B parameters — runs on a single consumer GPU for inference
  • Heterogeneous training corpus (humans + robots) for cross-embodiment transfer
  • Open weights, fine-tunable for kit-class actuator topologies
  • Live demo footage circulated April 2026

Used By

Early adopters in open-source humanoid community

Kit Relevance

Lightweight alternative to GR00T / pi0 for kit builders without H100-class compute. Worth benchmarking against pi0 on a Kit-02-class arm.

SimulationProprietary

Photorealistic, GPU-accelerated robot simulation built on Omniverse. Compose chassis/wheels/joints with real physics, attach RGB cameras and 2D LiDAR, drive everything via OmniGraph + ROS 2 with live RViz streaming.

Key Capabilities

  • Drag-and-drop URDF/USD robot composition
  • Physically-accurate sensor simulation (RGB, depth, 2D LiDAR, IMU)
  • OmniGraph visual programming for control wiring
  • ROS 2 bridge: simulator state streams into RViz/Gazebo-style tooling
  • Pairs with Isaac Lab for parallel RL training

Used By

NVIDIA-aligned humanoid programsRobotics curriculum providersIndustrial digital-twin teams

Kit Relevance

Best 'design-your-humanoid-virtually-first' tool. Natural input layer to HUMA's compiler: design in Isaac Sim, export BOM, pipe through /builder for cross-dimension validation. Could front-end a future 'design + compile + order kit' funnel.

ROS2 Jazzy Jalisco

Open Robotics / Intrinsic (Alphabet)

MiddlewareOpen Source

Industry-standard runtime middleware. Not AI/training — the plumbing connecting sensors, actuators, planners. The default for production humanoids.

Key Capabilities

  • ros2_control: hardware abstraction for joint interfaces
  • MoveIt2: arm/hand motion planning (OMPL, STOMP)
  • Nav2: autonomous navigation (SLAM, path planning)
  • URDF/Xacro: robot model description
  • Gazebo/Webots simulation bridges

Used By

Figure AIAgility RoboticsPAL RoboticsSoftbankUnitree (SDK)Most European academic humanoids

Kit Relevance

Mandatory for ecosystem interoperability. Use as runtime middleware. Standard 2026 stack: ros2_control (hardware) + MoveIt2 (manipulation) + custom RL locomotion node.

Recommended Kit Builder Stack

The 2026 cheat sheet — what to use at each layer if you are building a humanoid robot kit from scratch.

LayerRecommendation
SimulationIsaac Lab (NVIDIA, free) or MuJoCo (free) — Isaac Lab for scale, MuJoCo for accessibility
Rl AlgorithmRSL-RL (pip installable, ETH-quality PPO for legged robots)
Sim To RealAdaptive Domain Randomization + Humanoid-Gym benchmarks
Locomotion PolicyTrain with RSL-RL + Isaac Lab, deploy as ROS2 node
Manipulation Policypi0 (OpenPI) for generalist tasks, fine-tuned on your gripper
CognitionOM1 or direct LLM API integration (GPT-4, Gemini, etc.)
MiddlewareROS2 Jazzy + ros2_control + MoveIt2 + custom locomotion node
Imitation LearningLeRobot (Hugging Face) — especially for manipulation skill acquisition
Full Open SourceK-Scale K-Bot (hardware + K-OS Rust) — study this architecture
Nvidia PathGR00T N1.6 + Isaac Lab + Jetson AGX Thor — best tooling, highest cost

Sim-to-Real Pipeline

Best-practice 2026 pipeline for transferring locomotion policies from simulation to physical hardware.

1

Isaac Lab (simulation, 4,096-16,384 parallel instances on A100/H100)

2

RSL-RL (PPO training, ETH Zurich)

3

Adaptive Domain Randomization (auto-adjusting mass, friction, motor gains, latency, terrain)

4

Humanoid-Gym evaluation (zero-shot sim-to-real benchmarks)

5

ROS2 deployment on real hardware

6

Brief real-world fine-tuning (1-4 hours) if needed

Competitor Spotlight

K-Scale Labs K-Bot

$8,999 (Founder's Edition)

Direct Competitor

Height

~140cm

Weight

~35kg

Open Source

Fully — hardware CAD, K-OS (Rust), K-Sim, ML models

Status

Deliveries started mid-2025

Significance

Direct competitor to Huma Kit 01 ($11K). Cheaper, ships with its own Rust-based OS. BUT: no compile-or-not-compile validation, no research portal, no market intelligence.