Sign up to save tools and stay up to date with the latest in AI
bg
bg
1

Figure’s humanoid robot takes voice orders to help around the house | TechCrunch

Feb 20, 2025 - techcrunch.com
Figure founder and CEO Brett Adcock announced a new machine learning model called Helix for humanoid robots, following the company's decision to end its collaboration with OpenAI. Helix is a Vision-Language-Action (VLA) model that combines visual data and language prompts to control robots in real-time, allowing them to perform tasks by understanding natural language commands. The model demonstrates strong object generalization, enabling robots to interact with various household items they haven't encountered before. Figure is focusing on applying this technology to its 02 humanoid robot in home environments, which are more complex and variable than industrial settings.

The announcement highlights the challenges of teaching robots to perform household tasks, emphasizing the need for robots to generate intelligent behaviors on-demand without extensive manual programming. Figure aims to prioritize home applications for its robots, despite the current focus on workplace pilots with corporations like BMW. The Helix project is still in its early stages, and the announcement serves as a recruitment tool to attract more engineers to advance the development of this technology.

Key takeaways:

  • Figure founder and CEO Brett Adcock announced a new machine learning model called Helix for humanoid robots, which combines vision and language prompts to control robots in real time.
  • Helix is designed to control two robots at once, enabling them to perform complex household tasks by understanding natural language commands.
  • The model aims to address the challenges of teaching robots to perform tasks in varied and unpredictable home environments, moving beyond industrial applications.
  • The announcement serves as a recruitment tool to attract more engineers to develop the Helix project further, as it is still in the early stages of development.
View Full Article

Comments (0)

Be the first to comment!