Booster K1 Setup Guide

Workspace requirements

• Minimum floor area: 3 m × 3 m clear, hard, level surface
• Ceiling clearance: Minimum 2.2 m
• No obstacles within the operating radius during WALK mode
• Emergency stop: Ensure the remote controller is charged and within reach before powering on
• Lifting fixture: Required for CUSTOM mode development — the robot must be suspended before entering joint-level control

Unboxing checklist

• Inspect all 22 joints for shipping damage — move each gently by hand in DAMP state
• Verify Ethernet cable is included and your workstation has a free wired port
• Charge the remote controller fully before first use
• Read the Booster Robotics K1 Instruction Manual included in the box

Configure your Ethernet interface

The K1's default wired IP is 192.168.10.102. Set your computer's wired network interface to:

• IP address: 192.168.10.10
• Subnet mask: 255.255.255.0
• Gateway: 192.168.10.1

Verify connectivity

ping 192.168.10.102   # should respond with <5ms latency on wired

Inspect boot status via SSH

ssh booster@192.168.10.102   # password: 123456
booster-cli launch -c status   # confirm service is running

Install the Booster SDK

The official Python SDK is distributed on PyPI and requires Python 3.8 or later.

pip install booster_robotics_sdk_python --user

First SDK connection and status read

import booster

client = booster.BoosterClient("192.168.10.102")
status = client.get_robot_status()

print(f"Mode:    {status.mode}")
print(f"Battery: {status.battery_percentage:.1f}%")
print(f"IMU:     {status.imu_status}")

Manage the robot service (SSH)

booster-cli launch -c start     # start service
booster-cli launch -c stop      # stop service
booster-cli launch -c restart   # restart service

cat /opt/booster/version.txt    # check firmware version

Mode transition sequence: DAMP → PREP → WALK

Always follow this exact sequence. Never skip PREP or go directly from DAMP to WALK.

import booster
import time

client = booster.BoosterClient("192.168.10.102")

# Step 1: Enter PREP — robot stands and holds position
client.change_mode(booster.Mode.PREP)
time.sleep(3)   # IMPORTANT: wait full 3s for balance stabilization
print("Robot standing in PREP mode.")

# Step 2: Enter WALK mode
client.change_mode(booster.Mode.WALK)
time.sleep(2)

# Step 3: Walk forward slowly
client.walk(0.2, 0.0, 0.0)   # forward 0.2 m/s
time.sleep(3)
client.walk(0.0, 0.0, 0.0)   # stop

# Return to standing
client.change_mode(booster.Mode.PREP)

Walking velocity parameters

The client.walk(forward, lateral, angular) call accepts:

• forward: −0.5 to +0.5 m/s (positive = forward)
• lateral: −0.5 to +0.5 m/s (positive = right)
• angular: −1.0 to +1.0 rad/s (positive = turn left)

Remote controller shortcuts

• LT + START: Enter PREP mode
• RT + A: Enter WALK mode (from PREP)
• LT + BACK: Enter DAMP mode
• Left stick: Walk direction · Right stick: Turn
• D-Pad: Head movement

Predefined actions (WALK mode)

client.play_action("wave")            # wave hand
client.play_action("handshake")       # handshake
client.play_action("bow")             # bow
client.play_action("fortune_cat")     # fortune cat pose
client.play_action("new_year_dance")  # new year dance
client.play_action("rock_dance")      # rock dance

Head pose control

Control head yaw (±90°) and pitch (−40° to +30°) using set_head_pose(yaw_rad, pitch_rad). Convert degrees to radians first:

import math

def deg2rad(d): return d * math.pi / 180.0

# Look 30° left and 10° down
client.set_head_pose(deg2rad(30), deg2rad(-10))

# Return to center
client.set_head_pose(0.0, 0.0)

CUSTOM mode — direct joint control

# Enter CUSTOM mode from PREP only, with robot on lifting device
client.change_mode(booster.Mode.CUSTOM)

# Joint indexing: j1=head_yaw, j2=head_pitch, j3–j22=body joints
# Refer to K1 Instruction Manual for full joint map

Built-in agent modes

client.enter_agent("default")   # Booster default agent
client.enter_agent("soccer")    # soccer agent
client.enter_agent("hi_chat")   # conversational AI agent
client.enter_agent("dance")     # dance agent

The k1_agent.py script bridges the Booster K1 to the RoboticsCenter platform via WebSocket, enabling remote operation, joint monitoring, and demonstration data collection from a browser.

Install and launch the agent

pip install websockets

# Real hardware
python k1_agent.py \
  --backend wss://your-backend.run.app \
  --session YOUR_SESSION_ID \
  --node-id k1-lab-01 \
  --telemetry-hz 8

# Mock mode — no K1 hardware required
python k1_agent.py \
  --backend ws://localhost:8000 \
  --session test-session \
  --mock

Telemetry streamed by the agent (8 Hz default)

• Joint angles for 6 primary joints in degrees (j1–j6)
• Motor states: position, RPM, temperature per motor
• Walk velocity components: vx, vy, wz
• Battery percentage and current mode string
• Active agent name (Default / Soccer / Dance / HiChat)
• Millisecond timestamp for frame alignment