recent A.I The models are surprisingly human-like in their ability to produce text, audio and video when prompted. However, until now these algorithms have largely been associated with the digital world, not the physical, three-dimensional world we live in. In fact, even the best struggle to perform adequately whenever we try to apply these models to the real world.For example, just think how challenging it has been to develop safe and reliable self-driving cars. . Despite being artificially intelligent, not only do these models have no understanding of physics, but they are also often delusional, causing them to make unprecedented mistakes.
This is the year, however, when AI will finally happen Jump from the digital world to the real world in which we live. Extending AI beyond its digital limits calls for reworking the way machines think, combining the digital intelligence of AI with the mechanical prowess of robotics. This is what I call “physical intelligence,” a new form of intelligent machine that can sense dynamic environments, cope with contingencies, and make decisions in real time. Unlike the models used by standard AI, physical intelligence is rooted in physics; In understanding fundamental principles of the real world, such as cause-and-effect.
Such properties 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 powered by a standard AI model and the other powered by a fluid network—to detect objects in a summer forest, 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 detect objects in different conditions — during winter or urban. In the atmosphere — only the Liquid Network drone successfully completed its task. This experiment showed us that, unlike traditional AI systems that stop evolving after their initial training phase, fluid networks continue to learn and adapt from experience, just as humans do.
Physical intelligence is also able to interpret and physically execute 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 physiologically intelligent system that, in less than a minute, based on prompts like “robot that can walk” or “robot that can grip” and can replicate and then 3D-print tiny robots. Objects”.
Other laboratories are also making important achievements. For example, robotics startup Covariant, founded by UC-Berkeley researcher Peter Abiel, is developing chatbots—similar to ChatGTP—that can control robotic arms when asked. They have already secured over $222 million to develop and deploy sorting robots in warehouses globally. A team from Carnegie Mellon University also recently performed that a robot with only a camera and imprecise action can perform dynamic and complex parkour movements—including jumping over obstacles twice its height and intervals twice its length—of a single neural network trained by reinforcement learning using
If 2023 was the year of text-to-image and 2024 was text-to-video, then 2025 will mark the age of physical intelligence with a new generation of devices — not just robots, but anything from power grids to smart homes. also -that can interpret what we are telling them and execute tasks in the real world.
