Skateboarding Humanoid Robot: ATR, Kyoto University, and AIST Push the Boundaries of Robotics

Introduction

A collaborative research team from ATR (Advanced Telecommunications Research Institute International), Kyoto University, and the National Institute of Advanced Industrial Science and Technology (AIST) is developing a humanoid robot capable of freely riding a skateboard. While "Why a skateboard?" might be your first reaction, this research encapsulates critical technical challenges essential for practical humanoid robot applications.

Why Skateboarding?

Skateboarding is one of the most challenging skills even for humans to master. It requires maintaining balance on an unstable board while controlling direction through weight shifts and responding instantaneously to changes in the road surface. If a robot can accomplish this complex task, it demonstrates breakthroughs in several key areas:

  • Dynamic Balance Control: Maintaining posture under constantly changing conditions, not just in static states
  • Predictive Control: The ability to anticipate upcoming changes and respond proactively
  • Whole-Body Coordination: Complex movements integrating arms, legs, and torso in unison
  • Environmental Adaptability: Real-time response to changes in surface conditions

Global Humanoid Robot Development Landscape

Boston Dynamics "Atlas"

Boston Dynamics' "Atlas" has amazed the world with its advanced athletic abilities, performing parkour and backflips. In 2024, the company unveiled a fully electric new Atlas, aiming for practical applications in manufacturing and logistics.

Tesla "Optimus"

Tesla, led by Elon Musk, is accelerating development of its humanoid robot "Optimus." The company has announced plans to begin limited sales in 2025 following demonstration tests at its own factories.

Honda "ASIMO" Legacy

Honda's "ASIMO," introduced in 2000, made a global impact as a pioneer in bipedal walking robots. While the ASIMO project has concluded, its technology continues to influence next-generation mobility development.

Figure AI "Figure 02"

Startup Figure AI, backed by massive investments from OpenAI, NVIDIA, and others, is developing the general-purpose humanoid robot "Figure 02." By integrating AI, the company aims to achieve more natural movements and decision-making capabilities.

China's Rapid Advancement

In China, multiple companies including UBTECH and Unitree have entered humanoid robot development, rapidly advancing their technological capabilities with government support. They aim to capture market share with competitively priced products.

Japan's Strengths and the Significance of This Research

Japanese robotics technology has led the world in industrial robots. However, in the humanoid robot sector, the rise of American and Chinese players has been remarkable in recent years.

The ATR, Kyoto University, and AIST collaboration is not merely a "showpiece" but holds significant importance in several ways.

Deepening Fundamental Research

The fundamental research approach unique to universities and research institutions allows tackling root technical challenges without rushing toward commercial results.

Industry-Academia-Government Collaboration Model

The cooperation between different types of organizations—ATR (private research institute), Kyoto University (academic institution), and AIST (national research and development agency)—enables a multifaceted approach.

Real-World Application Potential

Technologies developed through skateboarding directly translate to practical applications, such as robots navigating debris at disaster sites or construction robots moving across unstable scaffolding.

Technical Challenges

Developing a skateboard-riding robot presents several technical difficulties.

Sensor Technology

The robot must perceive its own posture, board tilt, and road conditions in real-time. High-precision IMUs (Inertial Measurement Units) and force sensors are key.

Control Algorithms

To handle unpredictable disturbances, hybrid approaches combining Model Predictive Control (MPC) and reinforcement learning with traditional PID control are required.

Actuator Performance

Actuators capable of delivering large forces instantaneously while also enabling delicate control—similar to human muscles—are essential.

Future Outlook

If this research succeeds, humanoid robot capabilities will advance significantly. Future applications may include:

  • More natural assistance in nursing and welfare with fluid movements
  • Off-road mobility for disaster rescue operations
  • Flexible task handling at construction and manufacturing sites
  • Applications in sports training and education

Japanese robotics technology may once again lead the world.

What About Your Country?

In Japan, unique approaches like this are advancing fundamental humanoid robot research. What is the state of humanoid robot development in your country? What applications are anticipated? We'd love to hear about your country's robotics scene and what you hope robots will achieve in the future.

References

Reactions in Japan

A skateboarding robot might look like a joke at first, but it's actually super important as research for mobility on uneven terrain. This could become foundational technology for robots that work at disaster sites.

I agree 0
I disagree 0

ATR, Kyoto University, and AIST—what an impressive combination. Being able to do this kind of industry-academia-government collaboration for fundamental research is one of Japan's strengths.

I agree 0
I disagree 0

Honestly, Japan feels behind compared to Boston Dynamics' Atlas... But I hope this kind of steady research will lead to future breakthroughs.

I agree 0
I disagree 0

It's interesting as research, but is it worth spending taxpayer money on this? I'd rather see investment in more practical things.

I agree 0
I disagree 0

As an engineer, let me say that skateboarding is an ideal problem setting for dynamic balance control research. It tests the ability to respond to unpredictable disturbances.

I agree 0
I disagree 0

If robots can ride skateboards, surfing next? lol Actually, predicting waves would be super difficult.

I agree 0
I disagree 0

Japan's robotics tech is world-class in industrial applications, but has low visibility in humanoid robots. I hope research like this helps us catch up!

I agree 0
I disagree 0

I work in elder care. If this technology eventually leads to robots that can move reliably even in unstable environments, it would be a huge help.

I agree 0
I disagree 0

Ever since ASIMO ended, humanoid research in Japan seemed to quiet down. I'm happy to see it heating up again like this.

I agree 0
I disagree 0

Impressive work from Kyoto University researchers. I think this research topic strikes a good balance between academic curiosity and practicality.

I agree 0
I disagree 0

Feels like Tesla's Optimus and Chinese robots are overtaking us. Japan needs to speed up development with commercialization in mind.

I agree 0
I disagree 0

I'm a university student studying control engineering. I definitely want to read the paper when this research is published. Curious about the MPC and reinforcement learning combination.

I agree 0
I disagree 0

Want to see the video! Curious about what level they can actually ride at.

I agree 0
I disagree 0

Research like this often ends without technology transfer to companies. I'd like to know the roadmap to practical application.

I agree 0
I disagree 0

I work as a robotics engineer, and this kind of fundamental research supports product development 10 years down the line. Please don't just demand short-term results.

I agree 0
I disagree 0

AIST might be low-profile, but it's a crucial institution supporting the foundation of Japan's technological capabilities. It deserves more attention.

I agree 0
I disagree 0

Will bipedal robots like Gundam really become reality someday? So exciting to think about.

I agree 0
I disagree 0

As someone in construction, I'm hopeful. Job sites are full of unstable footing, so without this kind of technology, robots won't be usable.

I agree 0
I disagree 0

Voices from Around the World

Michael Chen

Japanese robotics research always takes creative approaches. I think using skateboarding as a challenge is as technically significant as Boston Dynamics' parkour. As an American researcher, I admire this emphasis on fundamental research.

Emma Williams

We have humanoid robot research in the UK too, but it's not as systematic as Japan's. The ATR and university collaboration model is fascinating. We should strengthen our industry-academia partnerships as well.

Hans Mueller

From the perspective of Germany's industrial robotics sector, this kind of dynamic control research is very important. Flexible operations in manufacturing require exactly this technology. Looking forward to technical exchanges with Japan.

Liu Wei

China is also investing heavily in humanoid robot development, but Japan's approach differs in its emphasis on fundamental research. We who rush toward commercialization should perhaps recognize the importance of such research.

Sarah Johnson

I work with a disaster response team in Canada. Mobility on uneven terrain is one of the most critical challenges for disaster robots. If this research is commercialized, it could contribute to rescue operations worldwide.

Roberto Silva

In Brazil, investment in robotics research is limited, so I envy Japan's research environment. I hope we can build a similar industry-academia-government collaboration model in our country.

Anna Kowalski

I work at a robotics startup in Poland. The approach of generating practical technology from a seemingly playful challenge like skateboarding is instructive for European researchers too.

James Anderson

Honestly, this seems behind compared to Boston Dynamics and Tesla. Is Japan losing in commercialization by being too fixated on fundamental research?

Kim Min-jun

Similar research is progressing in Korea too. If Japan and Korea could collaborate, we might lead the world with robotics technology from Asia.

Marie Dupont

As a French researcher, I respect how Japanese research institutions approach fundamental research with a long-term perspective. The EU should build similar support structures.

David Thompson

I work for a mining company in Australia. Robots working in hazardous environments need exactly this kind of dynamic balance control. Looking forward to the commercialization of this research.

Priya Sharma

Robotics education is growing in India too. Research like this from Japan provides excellent learning materials for students worldwide. I hope they share their findings openly.

Carlos Rodriguez

From Mexico here. I've admired Japanese robotics since childhood through anime. It's moving to see real research catching up to anime.

Olga Petrov

Humanoid robot research is conducted in Russia too, but international cooperation is difficult now. I hope Japan's research findings will be widely shared in the international community.

Ahmed Hassan

I teach robotics at a university in Egypt. I believe that if research like this is transferred to developing countries, lives around the world will improve.

Nguyen Thi Lan

I work at an IT company in Vietnam. I respect Japan's technical capabilities, but can they compete with Chinese products on cost? Pricing strategy for commercialization seems important too.