跳至内容

购物车

您的购物车是空的。

MEET M1: THE DESKTOP EMBODIED AI PLATFORM FOR SIM-TO-REAL RL. MEET M1: THE DESKTOP EMBODIED AI PLATFORM FOR SIM-TO-REAL RL.

MEET M1: THE DESKTOP EMBODIED AI PLATFORM FOR SIM-TO-REAL RL.

✓ 100% Refundable ✓ Ships Sep 2026 ✓ Discord Access

$2,4992799
RESERVE NOW

LIMITED Founder Edition
99 OF 200 UNITS LEFT

Reserve your spot to co-create the open RL platform.

LIMITED Founder Edition 
99 OF 200 UNITS LEFT LIMITED Founder Edition 
99 OF 200 UNITS LEFT

BECOME A FOUNDING MAKER

01

RESERVE NOW

Lock in Founder Price.
100% refundable before dispatch.

02

UNLOCK VIP PRIVILEGES

Priority shipping.
Discord Co-Creator access — shape the SDK with us

03

priority dispatch

Ships September 2026.
You'll get early beta access.

LIMITED Founder Edition

ONLY 99 UNITS LEFT

M1 DUAL-MODE HUMANOID · OPEN PLATFORM · ON-DEVICE AI

BUY NOW

M1

AN INTELLIGENCE THAT GROWS WITH YOU.

ENGINEERED FOR REAL-WORLD RL DISCOVERY.

ENGINEERED FOR REAL-WORLD RL DISCOVERY.

Sim-to-real policy transfer 01

Sim-to-real policy transfer

Train locomotion and balance policies with reference workflows in Isaac Gym. Designed for PyTorch/ONNX model export and sim-to-real pipelines via the Reinforced Imitation Framework.

Open SDK with full-stack control 02

Open SDK with full-stack control

Gain direct access at every layer with the Python SDK or the M1 Spine SDK for low-latency control. Designed for ROS 2 integration and Linux + OTA workflows.

On-device spatial vision 03

On-device spatial vision

Equipped with dual binocular cameras for high-precision local depth perception. Supports on-device SLAM, obstacle negotiation, and visual spatial reasoning with no cloud latency required.

10 TOPS NPU (BPU) and high-frequency sensor streaming 04

10 TOPS NPU (BPU) and high-frequency sensor streaming

Execute neural network inference locally on the 10 TOPS NPU (BPU). Stream motor torque, thermal states, 6-axis IMU data, and bus metrics into your training logs or ROS 2 environment.

20-DoF high-torque actuator array 05

20-DoF high-torque actuator array

Actuators engineered for dynamic balance, low inertia, and high impact recovery. Designed to withstand real-world trial-and-error policy testing.

Versatile bipedal and wheeled form factor 06

Versatile bipedal and wheeled form factor

A compact 50 cm, 2.7 kg (≈ 6 lb) desktop humanoid. Transitions between bipedal and wheeled modes to support diverse control policies in tight spaces.

SWIPE TO EXPLORE 01 — 06

05 / TECHNICAL SPECIFICATIONS

COMPACT BODY.
SERIOUS CAPABILITY.

DIMENSIONS / MM LENGTH (FRONT–REAR): 195 WIDTH (LEFT–RIGHT): 125 HEIGHT (TOP–BOTTOM): 494 DUAL-ARM SPAN 20.08 INCHES WEIGHT ROBOT BODY: 6.17 LBS MOBILITY BASE: 3.08 LBS CHARGING DOCK: 6.17 LBS
Height 4′3″ · Weight 66 lbs · Width 1′4″ Standing and wheeled mobility modes.
Bipedal mode: 0.05 m/s
Wheeled mode: 0.6 m/s
Supports autonomous following
MOBILITY
Endurance: ~2 hours
BATTERY AND POWER
80% in 1 hour
FAST CHARGING
Bipedal: 1.58 inches
Wheeled: 0.79 inches
OBSTACLE HANDLING
LDS LIDAR: whole-home mapping
iTOF depth: detects small household obstacles
Vision camera: recognition & avoidance
IMU: posture and motion tracking
SENSING SYSTEM
Voice / App
INTERACTION MODES
Multiple languages
Natural, continuous conversation
VOICE INTELLIGENCE
Stainless steel · aluminum alloy
ABS · rubber · silicone · glass
MATERIALS & CRAFTSMANSHIP
M1
COMPACT BODY.
SERIOUS CAPABILITY. COMPACT BODY.
SERIOUS CAPABILITY.

06 / FAQ

FAQ
Section

The essentials, answered clearly.

Yes — full refund any time before dispatch.

Yes — US, EU, UK, Canada, Australia, Japan, and Singapore at launch. Import duties may apply.

1-year standard warranty, extendable to 3 years. VIPs receive 12-hour priority response.

Yes. M1 provides reference workflows designed specifically for Isaac Gym. Policies trained in PyTorch can be easily exported via ONNX and deployed to the physical robot through the Reinforced Imitation Framework for efficient sim-to-real transfer. Example training scripts and reference policies are available directly through the private developer Discord community.

Yes. M1 features an integrated 10 TOPS NPU (BPU) optimized for local neural network inference, processing real-time spatial data directly from the dual binocular cameras. Developers can deploy custom models via the standard ONNX toolchain, and the Joyin engineering team is available to assist with model quantization recipes and operator optimization.

M1 runs a flexible Linux host environment with native ROS 2 message-bus support, allowing developers to connect custom software components and external nodes. Detailed I/O specifications, hardware expansion capabilities, and pinout diagrams will be fully detailed in the forthcoming hardware developer guide.

To safeguard the robot's high-torque actuators during dynamic policy testing, M1 features built-in hardware force limits by default. This ensures safe operation and long-term durability during aggressive movement, push recovery, and contact-rich reinforcement learning experiments.