DRKE’s Post

In #mechatronics, a "singularity" is much less theoretical, as a definition than in AI. Implying an inevitable deviance from the path, over time due to joints, 3d Space and handled materials. Strangely enough, adding Jacobian matrices to contain the error seems still not enough (despite Jacob Robotics being an integral part of many ongoing robotics projects) and just seemingly, adding more kernels or layers, might fix that in the future. So a well known very physical mechatronic #singularity may, one of these days, be contained by evolving tools such as additional complex AI algorithms, that may suffer of a totally different singularity on their own. I guess we love loops. But it's really fascinating. Reality is always more fun.

#Rodneybrooks #Robotics Rodney Brooks’ Three Laws of Robotics: Rodney Brooks is the Panasonic Professor of Robotics (emeritus) at MIT, where he was director of the AI Lab and then CSAIL. He has been cofounder of iRobot, Rethink Robotics, and Robust AI, where he is currently CTO. This article is shared with permission from his blog. Here are some of the things I’ve learned about robotics after working in the field for almost five decades. In honor of Isaac Asimov and Arthur C. Clarke, my two boyhood go-to science fiction writers, I’m calling them my three laws of robotics. * The visual appearance of a robot makes a promise about what it can do and how smart it is. It needs to deliver or slightly over deliver on that promise or it will not be accepted. * When robots and people coexist in the same spaces, the robots must not take away from people’s agency, particularly when the robots are failing, as inevitably they will at times. * Technologies for robots need 10+ years of steady improvement beyond lab demos of the target tasks to mature to low cost and to have their limitations characterized well enough that they can deliver 99.9 percent of the time. Every 10 more years gets another 9 in reliability. Below I explain each of these laws in more detail. But in a related post here are my three laws of artificial intelligence. Note that these laws are written from the point of view of making robots work in the real world, where people pay for them, and where people want return on their investment. This is very different from demonstrating robots or robot technologies in the laboratory. In the lab there is phalanx of graduate students eager to demonstrate their latest idea, on which they have worked very hard, to show its plausibility. Their interest is in showing that a technique or technology that they have developed is plausible and promising. They will do everything in their power to nurse the robot through the demonstration to make that point, and they will eagerly explain everything about what they have developed and what could come next. In the real world there is just the customer, or the employee or relative of the customer. The robot has to work with no external intervention from the people who designed and built it. It needs to be a good experience for the people around it or there will not be more sales to those, and perhaps other, customers. So these laws are not about what might, or could, be done. They are about real robots deployed in the real world. The laws are not about research demonstrations. They are about robots in everyday life. The Promise Given By Appearance My various companies have produced all sorts of robots and sold them at scale. A lot of thought goes into the visual appearance of the robot when it is designed as that tells the buyer or user what to expect from it. The iRobot Roomba was carefully… http://dlvr.it/TBYj4n

I agree 💯 with Rodney Brooks that as we encounter new technology that seems more and more human-like, we tend to assume it generalizes better than it does. We assume that a robot that can pick up a bag of chips and an apple could also pick up a mug. In practice it can’t… at least not without being trained to learn a new policy for a mug. But then it still can’t pick up a soda can. I also agree 💯 that robust high-dimensional robotic controls, the algorithms for robotic motion, remain the critical unsolved problem in robotics. Where I diverge is that I feel like Rodney’s take is too pessimistic. Already now can talk to robots and instruct them what to do. That capability is a game-changer, even in warehouses, enabling robots to work with us in far more natural ways that don’t require complex integrations with warehouse management systems. And I do believe we’re on something approaching an exponential curve of progress enabled by the transformer architecture. LLMs just a start. Cobots exhibiting a far higher level of AI than we’ve seen in any robot to date are already working in production environments. The robotically-enabled future is coming and it’s exciting!

🎉 Thrilled to share that my research article, "An Adaptive Framework for Trajectory Following in Changing-Contact Robot Manipulation Tasks," has been accepted for publication in the "Robotics and Autonomous Systems" journal! 📚 This work, based on my PhD thesis (https://lnkd.in/gkDFBptW), introduces a self-improving adaptive hybrid controller that combines model-based and machine-learned approaches to achieve smooth and reliable trajectory following for robot manipulators. The controller excels in performing contact manipulation tasks amidst changing dynamics, contact changes, and impacts. I am grateful to my supervisors, Mohan Sridharan and Dirk Ruiken, for their invaluable support. I am excited about the upcoming publication and look forward to the conversations it will spark. Stay tuned for updates, and please feel free to reach out with any questions or thoughts. #Research #Robotics #Publication #RobotManipulation

120x improvement in the last 15 years... This is another example of exponential improvements in Computer Vision and Robotics. Of course, this is for the specific problem of solving Rubik's cubes. Now if you add the generalized intelligence of GenAI/LLMs, can you imagine what Electronic/Mechatronic Systems will be capable of in the next 10-15 years? While there is a lot of fear and uncertainty about AI, Robotics, etc, I believe what is important is Imagination... Can we envision what are the big challenges that we want to solve with the kind of electronics capabilities we have in our reach - energy, poverty, transportation, health? If we don't imagine big, we'll end up defaulting to misuse the power to fight amongst ourselves in silly, meaningless wars. "The new top speed is a massive improvement on previous Rubik’s cube robots—in 2009, for example, the record was one minute and four seconds. But that’s already faster than any human, it wouldn’t be until 2016 that a robot completed the puzzle in under a minute. At this point, it sounds like it’s now not so much a question of how fast these robots can go, but how much strain a Rubik’s cube can withstand." https://lnkd.in/gV_kSvHc

Exciting advancements in AI and robotics have opened up new possibilities for real-world interactions. However, as we explore these new frontiers, it's crucial to prioritize safety and security. While consideration of robotic safety is essential, let's not forget that the AI powering these systems must also be safe. What might seem like a minor issue in a text-based AI system can have much more severe consequences when attached to a physical robot. Let's continue to push the boundaries of technology while keeping safety at the forefront of our minds. https://lnkd.in/gCTUA32F

The cobot pioneer will redefine the frontiers of physical AI, showcasing how the ‘ChatGPT moment for robots’ has arrived in a wide range of applications. Artificial intelligence is moving out of its digital confines to power robotic applications with humanlike perception, creating solutions that can handle variation without prior teaching or programming. Nowhere is that more pronounced than at this year’s Automate show in Chicago, May 6-9, where more than 50 Universal Robots throughout the show floor will demonstrate new capabilities – many of them fueled by AI. “We are entering an era of intelligent automation where robots can learn from and adapt to their surroundings in real-time,” says Ujjwal Kumar, Group President of Teradyne Robotics, parent company of Universal Robots. “This opens new possibilities for complex, creative and collaborative tasks, transforming robots from tools into intelligent partners that enhance workplace productivity and creativity.” 50-80x

The cobot pioneer will redefine the frontiers of physical AI, showcasing how the ‘ChatGPT moment for robots’ has arrived in a wide range of applications. Artificial intelligence is moving out of its digital confines to power robotic applications with humanlike perception, creating solutions that can handle variation without prior teaching or programming. Nowhere is that more pronounced than at this year’s Automate show in Chicago, May 6-9, where more than 50 Universal Robots throughout the show floor will demonstrate new capabilities – many of them fueled by AI. “We are entering an era of intelligent automation where robots can learn from and adapt to their surroundings in real-time,” says Ujjwal Kumar, Group President of Teradyne Robotics, parent company of Universal Robots. “This opens new possibilities for complex, creative and collaborative tasks, transforming robots from tools into intelligent partners that enhance workplace productivity and creativity.” 50-80x

 Three Laws of Artificial Intelligence post: very good! Recommended!

I've been thinking a lot about the future of robotics in manufacturing. A natural language interface with AI that can contextualize commands will change everything. It gets really interesting when AI-enabled robots become advanced and capable enough to become autonomous and empowered in a factory to improve efficiency, quality, and output. Some of my thoughts in the article linked below!