Qrio

Sony’s Qrio is a 38-DOF humanoid robot from 2003 that walks, runs, dances, recognizes faces and voices, and interacts socially with humans.
Software Type
Closed Source
Software Package
Sony Aperios real-time operating system. OPEN-R software platform for motion and interaction control. Speech recognition and synthesis modules. Facial recognition software.
Actuators
38 motors distributed to provide 38 degrees of freedom: Head: 4 DOF Trunk: 2 DOF Arms: 5 DOF each Fingers: 5 DOF each Legs: 6 DOF each
Compiute
Three 64-bit RISC processors with 192 MB RAM for real-time control, perception, and interaction.
Sensors
wo CCD cameras for stereoscopic vision and face recognition Seven microphones for voice recognition and sound localization Three-axis and two-axis accelerometers, gyroscope for balance Force sensors in each foot for ground contact and stability
Max Op. time
mins

Robot Brief

Qrio (Quest for cuRIOsity), developed by Sony and unveiled in 2003, was an advanced bipedal humanoid entertainment robot designed to interact naturally with humans through speech, face recognition, and expressive body movements. It featured 38 degrees of freedom, enabling it to walk, run, dance, grasp objects, and maintain balance on uneven terrain. Qrio incorporated multiple sensors including CCD cameras, microphones, accelerometers, gyros, and force sensors in its feet, allowing it to perceive its environment, recognize faces and voices, and respond to commands. Powered by three 64-bit RISC processors and running Sony’s Aperios real-time OS with the OPEN-R software platform, Qrio was capable of speech synthesis, understanding spoken commands, and learning new words. It was notable for being the world’s first humanoid robot capable of running, achieved through Sony’s innovative control system based on Zero Moment Point (ZMP) theory. Despite its technological advancements and ability to perform complex dances and social interactions, Sony discontinued Qrio development in 2006 after producing about 100 units, citing strategic shifts.

Use Cases

Qrio walks, runs, dances, recognizes faces and voices, grasps and throws objects, and interacts with humans through speech and gestures. It can maintain balance on uneven surfaces, understand spoken commands, and engage in social behaviors such as waving and nodding, providing entertainment and companionship.

Industries

  • Entertainment: Performs dances, games, and interactive social behaviors.
  • Research: Served as a platform for humanoid robotics and human-robot interaction studies.
  • Security (suggested): Facial recognition and smart sensing capabilities could support monitoring.
  • Education (suggested): Demonstrated robotics and AI concepts.

Specifications

Length
190
mm
Width
260
mm
Height (ResT)
mm
Height (Stand)
-
580
mm
Height (Min)
mm
Height (Max)
mm
Weight (With Batt.)
-
kg
Weight (NO Batt.)
-
6.5
kg
Max Step Height
-
mm
Max Slope
+/-
-
°
Op. Temp (min)
-
°C
Op. Temp (Max)
-
°C
Ingress Rating
-
No items found.

Intro

Qrio is a compact humanoid robot standing 58 cm tall and weighing 6.5 kg, equipped with 38 motors enabling 38 degrees of freedom across its head, trunk, arms, fingers, and legs. It uses two CCD cameras and seven microphones for vision and audio perception, along with accelerometers and force sensors for balance and movement control. Qrio runs on three 64-bit RISC processors and Sony’s Aperios real-time operating system, supporting advanced motion control and human-robot interaction. The robot can perform complex motions such as running and dancing, recognize faces and voices, and respond to spoken commands with synthesized speech. Its expressive body language includes waving, nodding, and shielding itself to avoid damage. Despite its sophistication, Sony ceased Qrio development in 2006.

Connectivity

    • Wireless system (details unspecified, likely Wi-Fi or proprietary)
    • Internal communication buses for sensors and actuators

Capabilities

  • Walking and running with advanced balance control
  • Face and voice recognition with directional hearing
  • Speech synthesis with a vocabulary of over 1,000 words
  • Complex dance routines including Japanese fan dance and salsa
  • Object grasping and throwing
  • Autonomous navigation and obstacle avoidance
  • Expressive social gestures and emotional LED eye lights