❌

Normal view

Received β€” 12 June 2026 ⏭ Interesting Engineering

New research shows robot β€˜personality’ in games hinges on timing and turn-taking

12 June 2026 at 18:43

New research has found that humanoid robots could become effective playmates for humans, but only if their behavior aligns with people’s expectations.

A study by researchers at the Norwegian University of Science and Technology (NTNU) explored how people interact with humanoid robots during physical games.

The team conducted controlled laboratory experiments using Pepper, a social robot built to engage with humans, to better understand the experience of playing alongside or against a robot.

The findings suggest that robots can be enjoyable gaming companions when they act naturally and respond appropriately to the flow of play. However, mismatched behavior, awkward movements, or an overly competitive attitude can quickly frustrate users and reduce engagement during interactions.

Robot teammate test

Humanoid robots such as Pepper are designed to look and behave in ways that resemble humans, featuring recognizable traits such as heads, eyes, hands, facial expressions, and conversational abilities.

According to researchers, these human-like characteristics help people relate more easily to robots, but they also create expectations that robots will act in socially appropriate and predictable ways.

To better understand how people interact with robots during play, researchers conducted an experiment in which participants played a physical version of trash-can basketball with Pepper. The game involved throwing crumpled paper balls into a trash can from designated positions chosen to provide a balanced level of challenge for both the human participants and the robot.

The study examined two different gameplay modes. In one mode, participants cooperated with Pepper as teammates working toward a common goal. In the other, they competed directly against the robot. Researchers also varied the order of play, with either the human participant or Pepper taking the first turn.

By comparing these scenarios, the team evaluated how gameplay mode and turn order influenced player engagement, motivation, enjoyment of physical activity, and emotional responses.

The findings revealed that seemingly minor factors, such as who takes the first turn and whether the interaction is cooperative or competitive, can significantly affect how people perceive the experience. β€œOur observations show that robots can actually be good playmates, but only if they behave in ways that make sense to people,” said Yavuz Inal, associate professor at NTNU’s Department of Design in GjΓΈvik, in a statement.

Cooperative play wins

Participants generally reported the most positive experiences when the game began in cooperative mode. However, competitive play also proved highly engaging for many players. Several participants found competing against Pepper more exciting and motivating, particularly when they were allowed to start the game first, which increased their sense of control over the interaction.

Many players also experienced a strong sense of accomplishment when they outperformed the robot. Some even admitted that watching Pepper miss a shot added to the enjoyment. For these participants, competition with the humanoid robot created a fun challenge, clear objectives, and a rewarding sense of mastery that enhanced the overall gaming experience.

The study also found that participants became frustrated with Pepper for reasons similar to those that make people irritated with overly competitive friends or family members during board games.

Frustration was particularly noticeable when the robot started the game in competitive mode. Pepper’s slow pace, long pauses before taking a turn, and apparent determination to win often clashed with participants’ expectations of how a human-like playmate should behave. As a result, some players felt the robot lacked the responsiveness and natural flow needed for enjoyable gameplay. One participant likened the experience to playing against an β€œoverworked printer with arms.”

According to the researchers, people expect robots cast as playmates to act like genuine players. β€œThe results offer a glimpse into a future where robots not only assist us at work and in the healthcare system, but also participate in everyday activities such as play, exercise, and games,” said the team in a statement.

πŸ’Ύ

A new study found that humanoid robots can be fun playmates, but natural behavior and timing are key to enjoyable gameplay.

Watch: Korean humanoid robot performs viral K-POP dance, learns by watching videos

12 June 2026 at 12:25

While China dominates humanoid robotics headlines, a Korean firm showcased a humanoid learning complex motions through an open-source AI framework.

In a recent demonstration, ROBOTIS’ AI Sapiens learned the famous CORTIS REDRED Challenge motion using only smartphone video, eliminating the need for professional motion-capture systems.

The process combined video-based motion capture, motion retargeting, simulation-based reinforcement learning, and Sim2Real transfer.

According to the firm, the demonstration highlights how open-source tools can simplify humanoid robot training, enabling users to generate, learn, and execute full-body motions more easily.

Humanoid learns motion

ROBOTIS has demonstrated the capabilities of its AI Sapiens humanoid robot, an open-source platform for physical AI powered by DYNAMIXEL-Q actuators. The project is designed to make humanoid robot motion learning more accessible by using widely available hardware and open-source software tools.

In the demonstration, AI Sapiens learns and performs a complex full-body motion known as the CORTIS REDRED Challenge. Instead of relying on expensive professional motion-capture systems, the robot learns the movement from video recorded using a standard smartphone camera. This significantly reduces the cost and complexity of collecting training data for humanoid robots.

The motion-learning process begins with video-based motion capture. Human movements recorded on a smartphone are converted into digital motion data that can be processed by software. The captured motions are then passed through a motion retargeting stage, where the human movements are adapted to match the physical structure and joint limitations of the humanoid robot.

After retargeting, the robot is trained in a simulation environment using reinforcement learning. During this stage, the AI repeatedly practices the motion in a virtual world, allowing it to improve balance, coordination, and movement accuracy without risking damage to physical hardware. Simulation training also enables rapid testing and optimization before deploying the motion to the real robot.

Once training is complete, the learned behavior is transferred from simulation to the physical AI Sapiens robot through a Sim2Real pipeline. This process helps ensure that motions developed in the virtual environment can be executed successfully in the real world, despite differences between the simulation and the physical hardware.

Accessible AI robotics

ROBOTIS plans to release the motion generation and learning pipeline as open-source software, giving researchers, developers, educators, and hobbyists access to the tools used in the demonstration. The goal is to lower barriers to humanoid robotics development and enable a wider community to experiment with motion learning and physical AI systems.

According to ROBOTIS, AI Sapiens is a fully open-source humanoid robot platform designed for physical AI research and development. Standing 1.3 meters tall and weighing 34 kilograms, the robot features 23 degrees of freedom across its body, enabling a wide range of human-like movements.

The platform is powered by 23 next-generation DYNAMIXEL-Q quasi-direct-drive (QDD) actuators, including 14 QM-060 units and 9 QM-080 units. These actuators combine low gear reduction ratios, high-torque motors, and integrated control electronics to deliver high backdrivability, low impedance, and precise torque control, making them suitable for dynamic and compliant humanoid motion.

AI Sapiens is powered by an NVIDIA Jetson Orin NX 16GB computer, delivering up to 100 TOPS of AI performance for advanced robotics tasks. It supports Wi-Fi 5, Bluetooth 5.0, dual Ethernet ports, USB connectivity, and 24V/12V power outputs for connecting additional hardware.

The robot is powered by a 46.8V, 9000mAh battery. It is supported by a fully open-source ecosystem that includes hardware bills of materials, CAD files, source code, simulation assets, and development tutorials, enabling researchers and developers to customize and expand the platform.

πŸ’Ύ

Korean humanoid robot learns complex humanoid motions from smartphone video using an open-source physical AI framework.
❌