To interact with the real world, AI will gain physical intelligence

recently Amnesty International The models are surprisingly human-like in their ability to generate text, audio, and video on demand. However, until now these algorithms have largely remained limited to the digital world, rather than the physical 3D world in which we live. In fact, whenever we try to apply these models to the real world, we find that even the most complex conflicts are difficult to perform adequately. Just think, for example, how difficult it is to develop safe and reliable self-driving cars. Despite being artificially intelligent, these models not only have no understanding of physics, but they often hallucinate, leading them to make inexplicable errors.

However, this is the year that AI will finally come to fruition Making the leap from the digital world to the real world in which we live. Extending AI beyond its digital boundaries requires reframing how machines think, integrating the digital intelligence of AI with the mechanical dexterity of robots. This is what I call “physical intelligence,” a new form of intelligent machines that can understand dynamic environments, deal with unpredictability, and make decisions in real time. Unlike the models used in standard AI, physical intelligence is rooted in physics; In understanding basic principles of the real world, such as cause and effect.

These features allow physical intelligence models to interact and adapt to different environments. In my research group at MIT, we are developing models of physical intelligence that we call fluid networks. In one experiment, for example, we trained two drones — one operated by a standard AI model and the other by a fluid network — to locate objects in the forest during the summer, using data captured by human pilots. While both drones performed equally well when tasked with doing exactly what they were trained to do, when they were asked to locate objects in different conditions — during the winter or in an urban environment — only the Liquid Mesh drone successfully completed its mission. . This experiment showed us that unlike traditional AI systems that stop evolving after the initial training phase, liquid networks continue to learn and adapt from experience, just as humans do.

Physical intelligence is also capable of interpreting and executing complex commands derived from text or images, bridging the gap between digital instructions and real-world execution. For example, in my lab, we have developed a physically intelligent system that can, in less than a minute, repeatedly design small robots and then 3D print them based on prompts such as “a robot can walk forward” or “a robot can grasp objects.”

Other laboratories are also making major breakthroughs. For example, robotics startup Covariant, founded by UC Berkeley researcher Peter Appel, is developing chatbots — similar to ChatGTP — that can control robotic arms on demand. They have already secured more than $222 million to develop and deploy sorting robots in warehouses globally. A team from Carnegie Mellon University also recently did this Proven A robot with only a single camera and imprecise operation can perform dynamic and complex parkour moves — including jumping obstacles twice its height and across gaps twice its length — using a single neural network trained via reinforcement learning.

If 2023 was the year of text-to-image and 2024 was the year of text-to-video, then 2025 will mark the age of physical intelligence, with a new generation of devices — not just robots, but everything from power grids to smart homes — that can interpret what… We tell them and perform tasks in the real world.