Robotics Q&A: CMU’s Matthew Johnson-Roberson

Johnson-Roberson is one of those dual threats that offers insight from two different — and important — perspectives. In addition to his long academic career, which recently found him working as a professor at the University of Michigan College of Engineering, he also has a solid startup CV.

Johnson-Roberson is also co-founder and serves as co-founder and CTO of robotic last-mile delivery startup Refraction AI.

What role(s) will generative AI play in future robotics?

Generative AI, through its ability to generate new data and solutions, will greatly enhance the capabilities of robots. This enables them to better generalize a wide range of tasks, improve their adaptability to new environments, and improve their ability to autonomously learn and develop.

What are your thoughts on the humanoid form factor?

The humanoid form factor is a complex engineering and design challenge. The desire to mimic human movement and interaction creates a high bar for actuators and control systems. It also presents unique challenges in terms of balance and coordination. Despite these challenges, the humanoid form has the potential to be extremely versatile and intuitively applicable in a variety of social and practical contexts, mirroring natural human interfaces and interactions. But maybe we’ll see other platforms succeed before this one.

After manufacturing and warehouses, what is the next major category for robotics?

Besides manufacturing and warehousing, the agricultural sector presents a great opportunity for robotics to solve the challenges of labor shortage, efficiency, and sustainability. Transportation and last-mile delivery are other arenas where robotics can drive efficiency, reduce costs, and improve service levels. These domains will likely see accelerated adoption of robotic solutions as technologies mature and as regulatory frameworks evolve to support wider deployment.

How far are truly general purpose robots?

The arrival of true general-purpose robots, capable of performing a wide range of tasks in different environments, may still be a distant reality. This requires breakthroughs in many fields including AI, machine learning, materials science, and control systems. The journey towards achieving such versatility is a step-by-step process where robots gradually evolve from task specificity to more multi-functional and finally general purpose.

Will home robots (beyond vacuums) take off in the next decade?

The next decade may witness the emergence of home robots in specific niches, such as elderly care or home security. However, the vision of having a general purpose domestic robot that can autonomously perform various household tasks is likely to be more distant. The challenges are not only technological but also include aspects such as affordability, user acceptance, and ethical considerations.

What important story/trend in robotics is not getting enough coverage?

Despite significant advances in some niche areas and successful robotic implementation in specific industries, these stories are often overshadowed by the appeal of more futuristic or general purpose robotic narratives. Incremental but significant achievements in sectors such as agriculture, healthcare, or special industrial applications deserve more attention because they represent real, visible progress in the field of robotics .

Leave a comment