Tsinghua University, Infinigence AI, and AgiBot jointly propose a collective experience learning paradigm, validated with 96 robots
Tsinghua University, Infinigence AI, and AgiBot have jointly proposed a new paradigm called Collective Experience Learning (CEL) and completed large-scale validation in a cluster of 96 real robots. The experiments covered five tasks: flower arrangement, clothes folding, phone charging, stool assembly, and phone packaging. Two robots that did not participate in training completed 600 test trials with 15 failures, for an overall success rate of 97.5%, and the success rates on all five tasks exceeded the average level of six human operators. The success rate on the phone packaging task rose from 79.2% to 98.3%; when the number of robots participating in training increased from 16 to 96, the success rate rose from 86.7% to 98.3%.
Why read this
AI score 65
Validation with 96 real robots on collective experience sharing, providing concrete data on how success rates improve with the number of robots in large-scale training.
Topics
Body · AI translation
Beijing News Shell Finance Report (Reporter Luo Yidan) On October 30, the reporter learned that 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 allows robots to not only rely on learning from human demonstrations, but also to draw on the successful experiences of other robots in the collective: when a robot encounters difficulties while executing 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.
The idea behind CEL is to give robots a different learning target—not mainly relying on humans to teach them, 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, but 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.
It is understood that tests in real scenarios verified the learning effectiveness of CEL. The experimental scenarios included both household 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 6 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 increased 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 research also observed a scaling trend of "the more machines, 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, in 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.
English text is being prepared.
2 The CPC Central Committee holds a press conference to introduce and interpret the spirit of the Fifth Plenary Session of the 20th CPC Central Committee 132,000
English text is being prepared.
4 From Honghu to the store, how does the channel catfish "swim" to the dining table under Bantianyao's fivefold controls? 63,000
English text is being prepared.
Latest
96 robots validated as a group, Tsinghua University, Infinigence AI, and AgiBot jointly propose the Collective Experience Learning paradigm 3 minutes ago
Competing for entry points, building ecosystems, and exploring commercialization, Tang Daosheng responds to WorkBuddy's progress and boundaries 3 minutes ago
Improving the exit mechanism for social organizations, the Ministry of Civil Affairs issues cancellation guidelines 3 minutes ago
China decides to extend the maximum stay in China for APEC Business Travel Card holders to 90 days 12 minutes ago
Hot discussion
The CPC Central Committee holds a press conference to introduce and interpret the spirit of the Fifth Plenary Session of the 20th CPC Central Committee