Tag Archives: black
#437964 How Explainable Artificial Intelligence ...
The field of artificial intelligence has created computers that can drive cars, synthesize chemical compounds, fold proteins, and detect high-energy particles at a superhuman level.
However, these AI algorithms cannot explain the thought processes behind their decisions. A computer that masters protein folding and also tells researchers more about the rules of biology is much more useful than a computer that folds proteins without explanation.
Therefore, AI researchers like me are now turning our efforts toward developing AI algorithms that can explain themselves in a manner that humans can understand. If we can do this, I believe that AI will be able to uncover and teach people new facts about the world that have not yet been discovered, leading to new innovations.
Learning From Experience
One field of AI, called reinforcement learning, studies how computers can learn from their own experiences. In reinforcement learning, an AI explores the world, receiving positive or negative feedback based on its actions.
This approach has led to algorithms that have independently learned to play chess at a superhuman level and prove mathematical theorems without any human guidance. In my work as an AI researcher, I use reinforcement learning to create AI algorithms that learn how to solve puzzles such as the Rubik’s Cube.
Through reinforcement learning, AIs are independently learning to solve problems that even humans struggle to figure out. This has got me and many other researchers thinking less about what AI can learn and more about what humans can learn from AI. A computer that can solve the Rubik’s Cube should be able to teach people how to solve it, too.
Peering Into the Black Box
Unfortunately, the minds of superhuman AIs are currently out of reach to us humans. AIs make terrible teachers and are what we in the computer science world call “black boxes.”
AI simply spits out solutions without giving reasons for its solutions. Computer scientists have been trying for decades to open this black box, and recent research has shown that many AI algorithms actually do think in ways that are similar to humans. For example, a computer trained to recognize animals will learn about different types of eyes and ears and will put this information together to correctly identify the animal.
The effort to open up the black box is called explainable AI. My research group at the AI Institute at the University of South Carolina is interested in developing explainable AI. To accomplish this, we work heavily with the Rubik’s Cube.
The Rubik’s Cube is basically a pathfinding problem: Find a path from point A—a scrambled Rubik’s Cube—to point B—a solved Rubik’s Cube. Other pathfinding problems include navigation, theorem proving and chemical synthesis.
My lab has set up a website where anyone can see how our AI algorithm solves the Rubik’s Cube; however, a person would be hard-pressed to learn how to solve the cube from this website. This is because the computer cannot tell you the logic behind its solutions.
Solutions to the Rubik’s Cube can be broken down into a few generalized steps—the first step, for example, could be to form a cross while the second step could be to put the corner pieces in place. While the Rubik’s Cube itself has over 10 to the 19th power possible combinations, a generalized step-by-step guide is very easy to remember and is applicable in many different scenarios.
Approaching a problem by breaking it down into steps is often the default manner in which people explain things to one another. The Rubik’s Cube naturally fits into this step-by-step framework, which gives us the opportunity to open the black box of our algorithm more easily. Creating AI algorithms that have this ability could allow people to collaborate with AI and break down a wide variety of complex problems into easy-to-understand steps.
A step-by-step refinement approach can make it easier for humans to understand why AIs do the things they do. Forest Agostinelli, CC BY-ND
Collaboration Leads to Innovation
Our process starts with using one’s own intuition to define a step-by-step plan thought to potentially solve a complex problem. The algorithm then looks at each individual step and gives feedback about which steps are possible, which are impossible and ways the plan could be improved. The human then refines the initial plan using the advice from the AI, and the process repeats until the problem is solved. The hope is that the person and the AI will eventually converge to a kind of mutual understanding.
Currently, our algorithm is able to consider a human plan for solving the Rubik’s Cube, suggest improvements to the plan, recognize plans that do not work and find alternatives that do. In doing so, it gives feedback that leads to a step-by-step plan for solving the Rubik’s Cube that a person can understand. Our team’s next step is to build an intuitive interface that will allow our algorithm to teach people how to solve the Rubik’s Cube. Our hope is to generalize this approach to a wide range of pathfinding problems.
People are intuitive in a way unmatched by any AI, but machines are far better in their computational power and algorithmic rigor. This back and forth between man and machine utilizes the strengths from both. I believe this type of collaboration will shed light on previously unsolved problems in everything from chemistry to mathematics, leading to new solutions, intuitions and innovations that may have, otherwise, been out of reach.
This article is republished from The Conversation under a Creative Commons license. Read the original article.
Image Credit: Serg Antonov / Unsplash Continue reading
#437693 Video Friday: Drone Helps Explore ...
Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We’ll also be posting a weekly calendar of upcoming robotics events for the next few months; here's what we have so far (send us your events!):
ICRES 2020 – September 28-29, 2020 – Taipei, Taiwan
AUVSI EXPONENTIAL 2020 – October 5-8, 2020 – [Online Conference]
IROS 2020 – October 25-29, 2020 – Las Vegas, Nev., USA
CYBATHLON 2020 – November 13-14, 2020 – [Online Event]
ICSR 2020 – November 14-16, 2020 – Golden, Colo., USA
Let us know if you have suggestions for next week, and enjoy today's videos.
Clearpath Robotics and Boston Dynamics were obviously destined to partner up with Spot, because Spot 100 percent stole its color scheme from Clearpath, which has a monopoly on yellow and black robots. But seriously, the news here is that thanks to Clearpath, Spot now works seamlessly with ROS.
[ Clearpath Robotics ]
A new video created by Swisscom Ventures highlights a research expedition sponsored by Moncler to explore the deepest ice caves in the world using Flyability’s Elios drone. […] The expedition was sponsored by apparel company Moncler and took place over two weeks in 2018 on the Greenland ice sheet, the second largest body of ice in the world after Antarctica. Research focused on an area about 80 kilometers east of Kangerlussuaq, where scientists wanted to study the movement of water deep underground to better understand the effects of climate change on the melting ice.
[ Flyability ]
Shane Wighton of the “Stuff Made Here” YouTube channel, whose terrifying haircut machine we featured a few months ago, has improved on his robotic basketball hoop. It’s actually more than an improvement: It’s a complete redesign that nearly drove Wighton insane. But the result is pretty cool. It’s fun to watch him building a highly complicated system while always seeking simple and elegant designs for its components.
[ Stuff Made Here ]
SpaceX rockets are really just giant, explosion-powered drones that go into space sometimes. So let's watch more videos of them! This one is sped up, and puts a flight into just a couple of minutes.
[ SpaceX ]
Neato Robotics makes some solid autonomous vacuums, and these incremental upgrades feature improved battery life and better air filters.
[ Neato Robotics ]
A full-scale engineering model of NASA's Perseverance Mars rover now resides in a garage facing the Mars Yard at NASA's Jet Propulsion Laboratory in Southern California.
This vehicle system test bed rover (VSTB) is also known as OPTIMISM, which stands for Operational Perseverance Twin for Integration of Mechanisms and Instruments Sent to Mars. OPTIMISM was built in a warehouselike assembly room near the Mars Yard – an area that simulates the Red Planet's rocky surface. The rover helps the mission test hardware and software before it’s transmitted to the real rover on Mars. OPTIMISM will share the space with the Curiosity rover's twin MAGGIE.
[ JPL ]
Heavy asset industries like shipping, oil and gas, and manufacturing are grounded in repetitive tasks like locating items on large industrial sites — a tedious task that can take as long 45 minutes to find critical items like a forklift in an area that spans the size of multiple football fields. Not only is this work boring, it’s dangerous and inefficient. Robots like Spot, however, love this sort of work.
Spot can provide real-time updates on the location of assets and complete other mundane tasks. In this case, Spot is using software from Cognite to roam the vast shipyard to locate and manage more than 100,000 assets stored across the facility. What used to take humans hours can be managed on an ongoing basis by Spot — leaving employees to focus on more strategic tasks.
[ Cognite ]
The KNEXT Barista system helps high volume premium coffee providers who want to offer artisan coffee specialities in consistent quality.
[ Kuka ]
In this paper, we study this idea of generality in the locomotion domain. We develop a learning framework that can learn sophisticated locomotion behavior for a wide spectrum of legged robots, such as bipeds, tripeds, quadrupeds and hexapods, including wheeled variants. Our learning framework relies on a data-efficient, off-policy multi-task RL algorithm and a small set of reward functions that are semantically identical across robots.
[ DeepMind ]
Thanks Dave!
Even though it seems like the real risk of COVID is catching it from another person, robotics companies are doing what they can with UVC disinfecting systems.
[ BlueBotics ]
Aeditive develop robotic 3D printing solutions for the production of concrete components. At the heart of their production plant are two large robots that cooperate to manufacture the component. The automation technology they build on is a robotic shotcrete process. During this process, they apply concrete layer by layer and thus manufacture complete components. This means that their customers no longer dependent on formwork, which is expensive and time-consuming to create. Instead, their customers can manufacture components directly on a steel pallet without these moulds.
[ Aeditive ]
Something BIG is coming next month from Robotiq!
My guess: an elephant.
[ Robotiq ]
TurtleBot3 is a great little home robot, as long as you have a TurtleBot3-sized home.
[ Robotis ]
How do you calculate the coordinated movements of two robot arms so they can accurately guide a highly flexible tool? ETH researchers have integrated all aspects of the optimisation calculations into an algorithm. The hot-wire cutter will be used, among other things, to develop building blocks for a mortar-free structure.
[ ETH Zurich ]
And now, this.
[ RobotStart ] Continue reading