Now, robots can learn precise factory control tasks.
#In recent years, significant progress has been made in the field of robotic reinforcement learning technology, such as quadruped walking, grasping, dexterity Control, etc., but most of them are limited to the laboratory demonstration stage. Widely applying robot reinforcement learning technology to actual production environments still faces many challenges, which to a certain extent limits its application scope in real scenarios. In the process of practical application of reinforcement learning technology, it is necessary to overcome multiple complex problems including reward mechanism setting, environment reset, sample efficiency improvement, and action safety guarantee. Industry experts emphasize that solving the many problems in the actual implementation of reinforcement learning technology is as important as the continuous innovation of the algorithm itself. Faced with this challenge, scholars from the University of California, Berkeley, Stanford University, the University of Washington, and Google jointly developed a tool called the Efficient Robot Reinforcement Learning Suite (SERL). An open source software framework dedicated to promoting the widespread use of reinforcement learning technology in practical robotic applications. 
- Project homepage: https://serl-robot.github.io/
- Open source code: https://github.com/rail-berkeley /serl
- ##Thesis title: SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
The SERL framework mainly includes the following components:
1. Efficient reinforcement learning
In the field of reinforcement learning, intelligence An agent (such as a robot) learns how to perform tasks by interacting with its environment. It learns a set of strategies designed to maximize cumulative rewards by trying various behaviors and obtaining reward signals based on the behavioral results. SERL uses the RLPD algorithm to empower robots to learn from real-time interactions and previously collected offline data at the same time, greatly shortening the training time required for robots to master new skills.
2. Various reward stipulation methods
SERL provides a variety of reward stipulation methods, allowing developers to Tailor reward structures to the needs of specific tasks. For example, fixed-position installation tasks can have rewards tailored to the robot's position, and more complex tasks can use classifiers or VICE to learn an accurate reward mechanism. This flexibility helps to precisely guide the robot to learn the most effective strategy for a specific task.
3. No reproduction function
Traditional robot learning algorithms need to reset the environment regularly, proceed as follows A round of interactive learning. In many tasks this cannot be done automatically. The no-reinforcement learning capabilities provided by SERL train both forward-backward policies simultaneously, providing environment resets for each other.
4. Robot control interface
SERL provides a series of Gym environment interfaces for Franka manipulator tasks as standard examples , users can easily extend SERL to different robotic arms.
5. Impedance controller
In order to ensure that the robot can safely and accurately explore and For operation, SERL provides a special impedance controller for the Franka robotic arm to ensure accuracy while ensuring that excessive torque is not generated after contact with external objects.
Through the combination of these technologies and methods, SERL greatly shortens the training time while maintaining a high success rate and robustness, enabling the robot to learn in a short time complex tasks and apply them effectively in the real world.
Figures 1 and 2: Comparison of success rate and number of beats between SERL and behavioral cloning methods in various tasks. With a similar amount of data, the success rate of SERL is several times higher (up to 10 times) than that of clones, and the beat rate is at least twice as fast.
1. PCB component assembly:
Assembling perforated components on PCB boards is a common but challenging robotic task. The pins of electronic components are very easy to bend, and the tolerance between the hole position and the pin is very small, which requires the robot to be both precise and gentle during assembly. With just 21 minutes of autonomous learning, SERL enabled the robot to achieve a 100% task completion rate. Even in the face of unknown interference such as the position of the circuit board moving or the line of sight being partially blocked, the robot can stably complete the assembly work.
3, 4, 5: When performing the mission of the circuit board component, the robot can deal with various interferences that have not been encountered during the training stage and complete the task smoothly. In the assembly process of many mechanical and electronic equipment , we need to install cables accurately along a specific path, a task that places high demands on precision and adaptability. Since flexible cables are prone to deformation during the wiring process, and the wiring process may be subject to various disturbances, such as accidental movement of the cable or changes in the position of the holder, this makes it difficult to deal with using traditional non-learning methods. SERL is able to achieve a 100% success rate in as little as 30 minutes. Even when the gripper position is different from what it was during training, the robot is able to generalize its learned skills and adapt to new wiring challenges, ensuring correct execution of the wiring job.
# Special training can also directly pass the cable through the clip in a different position than during training. 3. Object grabbing and placing operations:
In warehouse management or retail In the industry, robots often need to move items from one place to another, which requires the robot to be able to identify and carry specific items. During the training process of reinforcement learning, it is difficult to automatically reset under-actuated objects. Leveraging SERL's reset-free reinforcement learning capabilities, the robot simultaneously learned two policies with a 100/100 success rate in 1 hour and 45 minutes. Use the forward strategy to put the objects from box A to box B, and then use the backward strategy to put the objects from box B back to box A.
Figures 9, 10, 11: SERL trained two sets of strategies, one to carry objects from the right to the left, and one to move objects from the left back to the right. The robot not only achieves a 100% success rate on training objects, but can also intelligently handle objects it has never seen before. Jianlan Luo is currently a postdoctoral scholar in the Department of Electrical and Computer Science at the University of California, Berkeley, where he collaborates with Professor Sergey Levine at the Berkeley Artificial Intelligence Center (BAIR). His main research interests lie in machine learning, robotics, and optimal control. Before returning to academia, he was a full-time researcher at Google X, working with Professor Stefan Schaal. Prior to that, he obtained a master's degree in computer science and a Ph.D. in mechanical engineering from the University of California, Berkeley; during this time he worked with Professor Alice Agogino and Professor Pieter Abbeel. He has also served as a visiting research scholar at Deepmind's London headquarters. He graduated from the University of California, Berkeley with a bachelor's degree in computer science and applied mathematics majors. Currently, he conducts research in the RAIL laboratory led by Professor Sergey Levine. He has a strong interest in the field of robotic learning, focusing on developing methods that enable robots to quickly and widely acquire dexterous manipulation skills in the real world. He is an electrical engineer at the University of California, Berkeley Fourth-year undergraduate students majoring in Engineering and Computer Science. Currently, he conducts research in the RAIL laboratory led by Professor Sergey Levine. His research interests lie at the intersection of robotics and machine learning, aiming to build autonomous control systems that are highly robust and capable of generalization. He is a researcher engineer at Berkeley RAIL Laboratory , supervised by Professor Sergey Levine. He previously received his bachelor's degree from Nanyang Technological University, Singapore and completed his master's degree from Georgia Institute of Technology, USA. Prior to that, he was a member of the Open Robotics Foundation. His work focuses on real-world applications of machine learning and robotics software technologies.
##He was born in 1991 in Munich Technik The university earns PhDs in mechanical engineering and artificial intelligence. He is a postdoctoral researcher in the Department of Brain and Cognitive Sciences and the Artificial Intelligence Laboratory at MIT, an invited researcher at the ATR Human Information Processing Research Laboratory in Japan, and an adjunct assistant professor in the Department of Kinesiology at Georgia Institute of Technology and Pennsylvania State University in the United States. . He also served as leader of the computational learning group during the Japanese ERATO project, the Jawa Kinetic Brain Project (ERATO/JST). In 1997, he became a professor of computer science, neuroscience, and biomedical engineering at USC and was promoted to tenured professor. His research interests include topics such as statistics and machine learning, neural networks and artificial intelligence, computational neuroscience, functional brain imaging, nonlinear dynamics, nonlinear control theory, robotics, and biomimetic robots.
He was one of the founding directors of the Max Planck Institute for Intelligent Systems in Germany, where he led the Autonomous Motion Department for many years. He is currently chief scientist at Intrinsic, Alphabet's [Google] new robotics subsidiary. Stefan Schaal is an IEEE Fellow. 6. Chelsea Finn
She is a computer science and electrical engineering major at Stanford University assistant professor. Her lab, IRIS, research explores intelligence through large-scale robot interaction and is part of SAIL and the ML Group. She is also a member of the Google Brain team. She is interested in the ability of robots and other intelligent agents to develop a wide range of intelligent behaviors through learning and interaction. She previously completed a PhD in computer science from the University of California, Berkeley, and a bachelor's degree in electrical engineering and computer science from the Massachusetts Institute of Technology. 7. Abhishek Gupta
He is Paul G. Allen of the University of Washington Assistant Professor in the School of Computer Science and Engineering, leading the WEIRD Laboratory. Previously, he was a postdoctoral scholar at MIT, working with Russ Tedrake and Pulkit Agarwal. He completed his PhD on machine learning and robotics at BAIR, UC Berkeley, under the supervision of Professors Sergey Levine and Pieter Abbeel. Prior to that, he also completed his bachelor's degree at the University of California, Berkeley. His main research goal is to develop algorithms that enable robotic systems to learn to perform complex tasks in a variety of unstructured environments, such as offices and homes.He is an electrical engineering and computer science professor at the University of California, Berkeley Associate Professor in the Department of Science. His research focuses on algorithms that enable autonomous agents to learn complex behaviors, particularly general methods that enable any autonomous system to learn to solve any task. Applications for these methods include robotics, as well as a range of other areas where autonomous decision-making is required.
The above is the detailed content of Learn to assemble a circuit board in 20 minutes! The open source SERL framework has a 100% precision control success rate and is three times faster than humans. For more information, please follow other related articles on the PHP Chinese website!
