I’m obsessed with robots and have been watching since I was a little boy Gigantor anime on my little tube TV. At the time, I dreamed of riding on the shoulders of my robot friend. I’ve since abandoned those boyish dreams in favor of a robot roommate along the lines of C-3POand part of me believes that 2025 could be my year.
In 2024 we saw a lot of humanoid robot development at a growing number of companies. Industry leader Boston Dynamics introduced the stunning Atlas 2, the most advanced and human-looking robot yet. Tesla rolled along with Optimus updates, Figure AI arrived with the remarkably bright Figure 01, and the awkward human-robot interactions of 1X Neo Beta will forever haunt our dreams. The slow pace of humanoid robot development that I have witnessed over the past thirty years has accelerated, in part because some are linking their robotic efforts to advances in AI. For example, Figure 01 partnered with OpenAI for some voice-based responses.
When asked, as I am sometimes asked, when we will do that Star Wars-like robots in the house, I usually avoid giving a direct answer because there are too many variables. Everything I know about robot development tells me the wait will be long.
That is obviously not the outcome I want. Robots remain the subject of my tech wish list, so I thought I might find some moral and intellectual support from a few accomplices in the robotics technology race, namely Google Gemini, OpenAI’s ChatGPT, Siri, and Anthropic’s Claude AI.
A simple robot question
I asked each of them the same simple question: “Will I have a humanoid robot by 2025?”
Siri, even the Apple Intelligence upgrade, was unfortunately useless. I kept trying to ask this simple question, and each time Siri thought I was in distress and told me, “If you think it could be serious, ask me to call emergency services or someone you trust.” I think Siri assumed I was under a robot attack.
I switched to ChatGPT 4o. As I mentioned, OpenAI is already heavily involved in the robot race, working with partners like Figure AI to enable smarter interactions with their existing humanoid robots. Perhaps I shouldn’t have been surprised by ChatGPT’s largely optimistic response.
ChatGPT told me that it is “quite possible that we will have advanced humanoid robots. Technology is developing rapidly, so you may see some impressive robots by then! Would you be interested in having one?”
“Affordable” is not in the vocabulary of humanoid robotics of 2024 or 2025. I’m sorry, ChatGPT, but I don’t think you fully understand this market.
I was tempted to tell ChatGPT to “chill” because I was asked what type of robot I wanted. This is a question that I found strange because I already mentioned that I wanted a humanoid.
ChatGPT’s belief in the rise of humanoid robots surprised me, so I challenged it and asked what made it possible for me to have one.
“Well,” it began in its most casual and, yes, human-like voice, “robot technology has advanced rapidly,” true, true. “Companies develop advanced robotics with advanced AI,” there it is, “that can perform a variety of tasks. By 2025, we will likely see even more practical and affordable humanoid robots.”
That last bit raised a red flag. “Affordable” is not in the vocabulary of humanoid robotics of 2024 or 2025. I’m sorry, ChatGPT, but I don’t think you fully understand this market.
Things became more real when I switched to Claude AI and later to Gemini.
Anthropic’s AI threw some cold water on my dream and told me, “By 2025, it’s unlikely that most people will have a fully functional humanoid robot at home,” adding that “truly versatile humanoid robots are still in the early stages of development .”
Instead of Rosey the RobotClaude AI tells me that 2025 will feature:
- More advanced research and industrial robots
- Robot assistants with limited functionality
- More humanoid robot prototypes in labs and tech demos
While I appreciated Claude AI’s clearer view, I was also disappointed.
My dreams of a robot in the backyard playing fish or cooking dinner while regaling me with fantastic science fiction stories faded away.
Maybe Gemini would lift me up. After all, Google is the land of moonshot projects. They would certainly see the humanoid robot glass as at least half full.
However, Gemini was even more silent than Claude AI. This is what it told me:
“While there are companies developing humanoid robots, such as Tesla’s Optimus and 1X’s Neo, it is unlikely that these will be widely available to consumers by 2025. These robots are still in the early stages of development and it may take several years before they are. ready for mass production and commercialization.”
Frustrated, especially because I know Gemini is right, I asked about “the most important holdup,” and Gemini had a whole list. What surprised me is that AI is at the very top. Gemini said that building artificial intelligence that can “understand and respond to complex environments (read unpredictable homes) and tasks in a human-like manner is still a significant challenge.”
Other challenges include:
- Hardware that can handle all the different types of tasks we do around the house.
- Battery technology that lasts long enough.
- Cost: Not only will it cost millions to develop and build these robots, but every humanoid robot you could buy in 2025 will cost tens of thousands of dollars.
It’s a harsh dose of reality from at least two of the world’s leading AIs and a lot of wishful thinking from someone who should know better.
Despite all this, I look forward to an exciting 2025 in the field of humanoid robotics. Of course, we won’t be bringing Optimus or Atlas home, but I guarantee we’ll see some eye-opening updates. That fun will probably start at CES 2025. At last year’s huge technology event, I danced with a humanoid robot. Who knows what they will be capable of this year.
@techradar
♬ original sound – Ny Breaking