Booster T1
Booster RoboticsHumanoid robotAnnounced
Booster T1 is described by the manufacturer as a humanoid robot development platform designed for developers. It stands 1.18 m tall, weighs about 30 kg, and has 23 degrees of freedom in its Basic/Standard configuration, extendable to 31 with an optional gripper or 41 with an optional dexterous hand. Booster states it walks at 1 m/s, turns at 1.5 rad/s, and runs about 2 hours while walking or 4 hours while standing on a 10.5 Ah battery. It won the RoboCup 2025 Soccer 'AdultSize' category, and Booster's product page cites use by research groups at Purdue University, Carnegie Mellon University, UC Berkeley and Tsinghua University. Booster publishes an official C++/Python SDK and a ROS 2 interface package for it, alongside open-source repositories for reinforcement-learning training (Booster Gym, with 'Out-of-the-Box Booster T1 Support'), sim-to-real/sim-to-sim deployment (Booster Deploy) and robot-description files (Booster Assets), plus a third-party MuJoCo Menagerie model and MuJoCo Playground locomotion environment.
EDITORIALOverview reviewed against the cited sources by WBH, .
- HEIGHT
- 1.18 m
- WEIGHT
- ~30 kg
- DOF
- 23 DoF · 31 DoF (With Gripper) · 41 DoF (With Dexterous Hand)
- RUNTIME
- 2 h (walking)
Last verified24 sources
DATA · 30 FIELDS
Specifications
- Official source
- Community measured
- Not published
| Height | 1.18 mStanding. The product page's marketing copy separately rounds this to '~1.2m'. | Official source [3] |
|---|---|---|
| Weight | ~30 kgManufacturer states 'About 30kg' (docs) / '~30kg' (product page). | Official source [1][3] |
| Degrees of Freedom | 23 DoF · 31 DoF (With Gripper) · 41 DoF (With Dexterous Hand)Basic/Standard configuration. | Official source [1][3] |
| Locomotion | Bipedal (omnidirectional walking) | Official source [2] |
| Walking Speed | 1 m/s | Official source [3] |
| Turning Speed | 1.5 rad/s | Official source [3] |
| DoF per Leg | 6 | Official source [3] |
| DoF per Arm | 4 (expandable) · 7 (With Gripper / Dexterous Hand)Basic/Standard. | Official source [1][3] |
| Waist DoF | 1 | Official source [3] |
| Head DoF | 2 | Official source [3] |
| Joint Movement Space | Waist ±58°; Hip/Knee/Ankle ranges published | Official source [1] |
| Walking Noise | ≤70 dBPublished as an upper bound ('≤70dB'). | Official source [3] |
| Operating Temperature | -10℃ to 45℃ | Official source [3] |
| Operating Humidity | 5% to 90%, non-condensing | Official source [3] |
| Certification | CE/FCC | Official source [3] |
| Ingress protection | Not published | Not published |
| Max Joint Torque | 130 N·mOverall actuator peak torque figure; not broken out per joint. | Official source [1] |
|---|
| Battery | 10.5 Ah | Official source [1] |
|---|---|---|
| Runtime | 2 h (walking)4 h standing, per product page; docs give 'Battery Life: 2h' without specifying activity. | Official source [1][3] |
| Charging Time | ≤2 hPublished as an upper bound ('≤2h'). | Official source [3] |
| Battery Cycle Life | ≥500 cyclesPublished as a lower bound ('≥500 times'). | Official source [3] |
| Compute | AGX Orin – 200 TOPS (Basic) · Intel i7 + AGX Orin – 200 TOPS (Standard/Customized) | Official source [1][3] |
|---|---|---|
| Perception Sensors | Depth camera, 9-axis IMU, 6-mic arrayThe docs specifications table lists only 'Depth Camera / Microphone Array / Speaker' without naming the IMU or mic count; the product page adds the IMU and specifies a circular 6-mic array. | Official source [1][3] |
| Connectivity | Wi-Fi 6, Bluetooth 5.2, USB/Ethernet | Official source [1] |
| End Effector | Gripper (optional, 1 DoF/hand) (Customized (Gripper)) · Dexterous hand (optional, 6 DoF/hand) (Customized (Dexterous Hand)) | Official source [1] |
|---|---|---|
| Hand DoF | 1 (Gripper) · 6 (Dexterous Hand) | Official source [1] |
| Availability | Available to order | Official source [1][11][12] |
|---|---|---|
| Warranty | 1 year | Official source [1] |
| Firmware Support | Active through firmware 1.7.2 (Aug 2026)Confirms T1 devices are still covered by current firmware, alongside K1/T2. | Official source [9] |
| Indicative price | Not published | Not published |
DATA · SOFTWARE & SIMULATION
Development
| INTERFACE | SUPPORT | PACKAGE / VERSION | SRC |
|---|---|---|---|
| SDK | Official | Booster Robotics SDK (C++, github.com/BoosterRobotics/booster_robotics_sdk) with high-level RPC clients and low-level Fast DDS topics; Python delivered via the 'booster_robotics_sdk_python' pip package. A separate 'boosteros' Python SDK client (pip) explicitly lists 'Booster K1 / T1 / T2' as supported models. | [5][7][16] |
| ROS 2 | Official | booster_ros2_interface (booster_robotics_sdk_ros2 repo) provides ROS 2 message/service definitions (LowState, MotorState, ImuState, etc.); the SDK's Fast DDS transport is compatible with ROS 2's DDS mechanism, and booster_deploy's real-robot path requires 'ROS 2 with booster_interface', already installed on the robot. | [17][19] |
| Isaac Sim / Lab | Official | Booster Gym trains T1 locomotion policies in NVIDIA Isaac Gym (legacy Isaac Gym, not Isaac Sim/Lab) and cross-validates them in MuJoCo before deployment. Booster's newer Isaac-Lab-based framework, Booster Train, currently targets the K1 robot rather than T1. | [18] |
| MuJoCo | Official | Officially supported for sim-to-sim testing and deployment (booster_gym's play_mujoco.py, booster_deploy's --mujoco flag with a T1 mjcf_path). Also has a community-maintained Booster T1 model in Google DeepMind's MuJoCo Menagerie and a T1 joystick locomotion environment in MuJoCo Playground. | [18][22][23][24] |
| Gazebo | Not published | No Gazebo package or documentation for T1 found in the retrieved sources. | |
| URDF / MJCF | Official | booster_assets ships official URDF/XML descriptions for three T1 variants: T1 (23 DoF), T1 Locomotion (23 DoF, fixed head/arms/waist), and T1 with 7-DoF Arms (29 DoF). A derived MJCF model (Apache-2.0) is also published in the third-party MuJoCo Menagerie. | [20][22] |
| Languages | Official | Python (booster_robotics_sdk_python, boosteros) and C++ (booster_robotics_sdk). | [8][16] |
| Teleoperation | Official | The BoosterRobot Python SDK exposes a Hand-Guiding Manager to record/manage hand-guiding sessions; booster_deploy supports task selection and velocity teleoperation via a GameSir or Booster remote controller, or a keyboard. | [7][19] |