Researchers from Brown University are developing a new algorithm to help robots better plan their actions in complex environments. It’s designed to help robots be more useful in the real world, but it’s being developed with the help of a virtual world — that of the video game Minecraft.
Basic action planning, while easy for humans, is a frontier of robotics. Part of the problem is that robots don’t intuitively ignore objects and actions that are irrelevant to the task at hand. For example, if someone asked you to empty the trashcan in the kitchen, you would know there’s no need to turn on the oven or open the refrigerator. You’d go right to the trashcan.
Robots, however, lack that intuition. Most approaches to planning consider the entire set of possible objects and actions before deciding which course to pursue. In other words, a robot might actually consider turning on the oven as part of its planning process for taking out the trash. In complex environments, this leads to what computer scientists refer to as the “state-space explosion” — an array of choices so large that it boggles the robot mind.
“It’s a really tough problem,” said Stefanie Tellex, assistant professor of computer science at Brown. “We want robots that have capabilities to do all kinds of different things, but then the space of possible actions becomes enormous. We don’t want to limit the robot’s capabilities, so we have to find ways to shrink the search space.”
The algorithm that Tellex and her students are developing does just that. David Abel, a graduate student in Tellex’s lab, led the work and will present it this week at the International Conference on Automated Planning and Scheduling.
Discovering the likely path
The algorithm augments standard robot planning algorithms using “goal-based action priors” — sets of objects and actions in a given space that are most likely to help an agent achieve a given goal. The priors for a given task can be supplied by an expert operator, but they can also be learned by the algorithm itself through trial and error.
The game Minecraft, as it turns out, provided an ideal world to test how well the algorithm learned action priors and implemented them in the planning process. For the uninitiated, Minecraft is an open-ended game, where players gather resources and build all manner of structures by destroying or stacking 3-D blocks in a virtual world. At over 100 million registered users, it’s among the most popular video games of all time.
“Minecraft is a really good a model of a lot of these robot problems,” Tellex said. “There’s a huge space of possible actions somebody playing this game can do, and it’s really cheap and easy to collect a ton of training data. It’s much harder to do that in the real world.”
Tellex and her colleagues started by constructing small domains, each just a few blocks square, in a model of Minecraft that the researchers developed. Then they plunked a character into the domain and gave it a task to solve — perhaps mining some buried gold or building a bridge to cross a chasm. The agent, powered by the algorithm, then had to try different options in order to learn the task’s goal-based priors — the best actions to get the job done.
“It’s able to learn that if you’re standing next to a trench and you’re trying to walk across, you can place blocks in the trench. Otherwise don’t place blocks,” Tellex said. “If you’re trying to mine some gold under some blocks, destroy the blocks. Otherwise don’t destroy blocks.”
After the algorithm ran through a number of trials of a given task to learn the appropriate priors, the researchers moved to a new domain that it had never seen before to see if it could apply what it learned. Indeed, the researchers showed that, armed with priors, their Minecraft agents could solve problems in unfamiliar domains much faster than agents powered by standard planning algorithms.
Having honed the algorithm in virtual worlds, the researchers then tried it out in a real robot. They used the algorithm to have a robot help a person in the task of baking brownies. The algorithm was supplied with several action priors for the task. For example, one action prior let the robot know that eggs often need to be beaten with a whisk. So when a carton of eggs appears in the robot’s workspace, it is able to anticipate the cook’s need for a whisk and hand him one.
In light of the results, Tellex says she sees goal-based action priors as a viable strategy to help robots cope with the complexities of unstructured environments — something that will be important as robots continue to move out of controlled settings and into our homes.
The work also shows the potential of virtual spaces like Minecraft in developing solutions for real-world robots and other artificial agents. “I think it’s going to provide a way for very rapid iteration for algorithms that we can then run in our robots and have some confidence they’re going to work,” Tellex said.
Read more: Using Minecraft to unboggle the robot mind
The Latest on: Robot planning algorithms
via Google News
The Latest on: Robot planning algorithms
- Coming Soon to a Battlefield: Robots That Can Killon September 7, 2019 at 5:05 am
But drones and systems like Sea Mob are removing the human from the transport, and computer algorithms are learning how to target. The key remaining issue is whether military commanders will let ...
- Personally Speaking: 'Robot revolution gives chance to improve jobs'on September 6, 2019 at 9:05 pm
Skills that can’t be replicated by robots or artificial intelligence ... There are no classrooms, lecture theatres, not even a library. It’s open plan, it has soft furnishings, high benches, low ...
- Perceptron, Inc. (PRCP) CEO Dave Watza on Q4 2019 Results - Earnings Call Transcripton September 5, 2019 at 11:29 am
On the call today, I will update you on our business and the progress we continued to make against our long-term strategic plan. Following ... emitters around our robot-mounted sensor, we are ...
- Samsung's robot chef arms just helped make me a delicious meal at IFAon September 5, 2019 at 6:12 am
The plan also includes robots. At CES in January ... with the same diameter and reach of a human arm. Its sensors and AI algorithms let it work alongside a real person safely, even when they get in ...
- Grab A $50 Discount On The Roborock S6 Robot Vacuum Cleaneron September 3, 2019 at 11:59 pm
The device features the LDS navigation system with next-gen algorithms, so that it can do a better ... 2,000Pa suction power as the Roborock S5. If you've been planning to get a robot vacuum, this may ...
- YES BANK partners with Microsoft to reinvigorate its ‘YES ROBOT’ chatboton September 3, 2019 at 6:31 am
YES ROBOT can provide an indicative loan amount using Machine Learning (ML) and advanced credit scoring algorithms. One of the most pivotal ... media platforms such as Facebook, in future, we plan to ...
- MIT autonomous robot boats gain the ability to change shapeon September 2, 2019 at 5:27 am
The algorithm handles all the planning and tracking that allows a group of Roboat ... The Roboats could use dozens of devices in their shape patterns. A group of Robots in a shape is known as a ...
- MIT’s autonomous boat robots can now shapeshift to form new structureson August 29, 2019 at 12:46 pm
The researchers working on the self-assembling roboats have devised an algorithm that manages all the planning involved in getting groups of the aquatic robots to unlatch from each other ...
- Security Robots Are Now a Thing in San Francisco. How Long Before They’re in Vancouver?on August 23, 2019 at 10:26 am
The egg-shaped rolling robot has GPS and laser scanning built-in and utilizes prediction algorithms and social analytics to identify ... Knightscope’s creators plan to charge an hourly fee to rent the ...
- Meet ‘Mindar,’ the robotic Buddhist prieston August 22, 2019 at 8:49 am
To reverse course, a Kyoto temple has settled on a new plan for connecting with the masses ... The machine is not equipped with machine-learning algorithms, but the robot’s designers said there may ...
via Bing News