Tsinghua University, Infinigence AI, and AgiBot propose CEL collective experience learning, with 96 robots verifying a 97.5% success rate

Xinmin Evening News has learned that recently, Tsinghua University, Infinigence AI, and AgiBot jointly proposed a new paradigm called Collective Experience Learning (CEL), and completed large-scale validation in a cluster of 96 real robots. CEL enables robots to learn not only from human demonstrations, but also from the successful experiences of other robots in the collective: when a robot encounters difficulties while performing a task, it can seek solutions from its peers' past experiences and continuously improve its own performance. By sharing and accumulating experience, a robot collective can jointly enhance its capabilities through continuous practice, providing a new technical path for promoting the autonomous evolution and large-scale application of robots. Making robots each other's "teachers" As embodied intelligence gradually moves from the laboratory to the real world, robots need to work in increasingly complex environments. To make them perform well, the key is to enable them to continuously accumulate real-world experience. The current common approach relies on humans to "teach": either a person repeatedly demonstrates actions for the robot to watch, or the person manually corrects the robot when it makes mistakes. But there is a core problem here: robots can be deployed in batches of hundreds or thousands, yet experienced operators are not that numerous and cannot "scale up" alongside the robots, which has become a major bottleneck in the development of embodied intelligence. The idea behind CEL is to give robots a different learning target—not mainly relying on human teaching, but on learning from "peers." The successful experience that one robot figures out through practice can be retained and shared and reused by the entire robot collective. In this way, robots do not have to keep waiting for humans to teach them; instead, they can learn and grow on their own from the experience continuously accumulated by the collective. As the number of robots increases, the experience accumulated by the collective becomes richer, and through a unified learning mechanism that continuously optimizes strategies, the robots' capabilities can become stronger with use and smarter with practice. Nearly a hundred robots "learn as a group" Tests in real scenarios further validated the learning effect of CEL— The experimental scenarios included both home services and industrial production, specifically five tasks: flower arranging, clothes folding, phone charging, stool assembly, and phone packaging. The results were quite impressive: two robots that had not participated in training underwent 600 tests and failed only 15 times, for an overall success rate of 97.5%, and the success rates on all five tasks exceeded the average level of six human operators. Among them, phone packaging is an industrial task that requires completing multiple steps in sequence. After collective experience learning, the robot's success rate on this task rose from 79.2% to 98.3%, with only 2 failures in 120 consecutive tests. This shows that the learned strategies are not only effective on complex tasks but also sufficiently stable. The study also observed a scaling trend of "the more robots, the stronger": when the number of robots participating in training increased from 16 to 96, the success rate rose from 86.7% to 98.3%. That is, within the same actual training time, the larger the scale of robots participating in training, the more real experience can be accumulated, and this experience can in turn be continuously converted into learning gains, making the entire collective smarter and smarter. Industry-academia-research collaboration explores a new future for industrialization The key to the industrialization of embodied intelligence is not just making robots "able to do one thing." The collective learning paradigm jointly launched by Tsinghua University, Infinigence AI, and AgiBot provides a path from "improving the capability of a single robot" to "the continuous evolution of the entire collective." Xinmin Evening News noted that it first solves an obstacle that has long constrained the development of embodied intelligence—"not enough people." In the past, improving robot capabilities relied heavily on experienced operators continuously teaching and manually correcting errors. But people are a scarce resource and can never keep up with the pace of batch robot deployment. Collective learning lets robots learn from each other, and the situation changes completely: the more robots there are, the faster experience accumulates and the faster capabilities improve. The bottleneck of "not enough people" becomes the scale advantage of "the more robots, the stronger." Even more noteworthy is that this collaboration itself is the best footnote to industry-academia-research cooperation. Tsinghua University stands at the academic frontier, Infinigence AI is a leading company in AI infrastructure, and AgiBot possesses complete machines and real scenarios—each of the three contributes its strengths, precisely bridging the hardest stretch of the road from "methods in papers" to "capabilities on the production line," so that cutting-edge algorithms no longer remain in papers but run all the way into the real world. What was validated this time is also a complete chain: real scenarios generate experience, collective learning consolidates capabilities, and large-scale deployment feeds back into more scenarios. Once this chain runs smoothly, other enterprises and other scenarios can directly draw on it, and the growth path of the entire embodied intelligence industry will become clearer as a result.