
Photo: Tom Buehler/MIT CSAIL
ComText, from the Computer Science and Artificial Intelligence Laboratory, allows robots to understand contextual commands.
Despite what you might see in movies, today’s robots are still very limited in what they can do. They can be great for many repetitive tasks, but their inability to understand the nuances of human language makes them mostly useless for more complicated requests.
For example, if you put a specific tool in a toolbox and ask a robot to “pick it up,” it would be completely lost. Picking it up means being able to see and identify objects, understand commands, recognize that the “it” in question is the tool you put down, go back in time to remember the moment when you put down the tool, and distinguish the tool you put down from other ones of similar shapes and sizes.
Recently researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) have gotten closer to making this type of request easier: In a new paper, they present an Alexa-like system that allows robots to understand a wide range of commands that require contextual knowledge about objects and their environments. They’ve dubbed the system “ComText,” for “commands in context.”
The toolbox situation above was among the types of tasks that ComText can handle. If you tell the system that “the tool I put down is my tool,” it adds that fact to its knowledge base. You can then update the robot with more information about other objects and have it execute a range of tasks like picking up different sets of objects based on different commands.
“Where humans understand the world as a collection of objects and people and abstract concepts, machines view it as pixels, point-clouds, and 3-D maps generated from sensors,” says CSAIL postdoc Rohan Paul, one of the lead authors of the paper. “This semantic gap means that, for robots to understand what we want them to do, they need a much richer representation of what we do and say.”
The team tested ComText on Baxter, a two-armed humanoid robot developed for Rethink Robotics by former CSAIL director Rodney Brooks.
The project was co-led by research scientist Andrei Barbu, alongside research scientist Sue Felshin, senior research scientist Boris Katz, and Professor Nicholas Roy. They presented the paper at last week’s International Joint Conference on Artificial Intelligence (IJCAI) in Australia.
How it works
Things like dates, birthdays, and facts are forms of “declarative memory.” There are two kinds of declarative memory: semantic memory, which is based on general facts like the “sky is blue,” and episodic memory, which is based on personal facts, like remembering what happened at a party.
Most approaches to robot learning have focused only on semantic memory, which obviously leaves a big knowledge gap about events or facts that may be relevant context for future actions. ComText, meanwhile, can observe a range of visuals and natural language to glean “episodic memory” about an object’s size, shape, position, type and even if it belongs to somebody. From this knowledge base, it can then reason, infer meaning and respond to commands.
“The main contribution is this idea that robots should have different kinds of memory, just like people,” says Barbu. “We have the first mathematical formulation to address this issue, and we’re exploring how these two types of memory play and work off of each other.”
With ComText, Baxter was successful in executing the right command about 90 percent of the time. In the future, the team hopes to enable robots to understand more complicated information, such as multi-step commands, the intent of actions, and using properties about objects to interact with them more naturally.
For example, if you tell a robot that one box on a table has crackers, and one box has sugar, and then ask the robot to “pick up the snack,” the hope is that the robot could deduce that sugar is a raw material and therefore unlikely to be somebody’s “snack.”
By creating much less constrained interactions, this line of research could enable better communications for a range of robotic systems, from self-driving cars to household helpers.
“This work is a nice step towards building robots that can interact much more naturally with people,” says Luke Zettlemoyer, an associate professor of computer science at the University of Washington who was not involved in the research. “In particular, it will help robots better understand the names that are used to identify objects in the world, and interpret instructions that use those names to better do what users ask.”
The Latest on: Contextual commands
[google_news title=”” keyword=”contextual commands” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]- 3M (MMM) Q2 2024 Earnings Call Transcripton July 26, 2024 at 1:15 pm
Welcome to the 3M second-quarter earnings conference call. [Operator instructions] As a reminder, this call is being recorded Friday, July 26th, 2024. I would now like to turn the call over to Bruce ...
- Russia would lose up to 1.8 million troops and take 5 years to capture the 4 Ukrainian regions it wants: UK Army Chiefon July 26, 2024 at 3:21 am
Spread the loveIn a recent statement, the UK Army Chief addressed the ongoing conflict in Ukraine, suggesting that Russia could potentially suffer significant military losses while attempting to ...
- Why 'Back in My Day' Views of Navy Boot Camp Changes May Be Missing the Pointon July 26, 2024 at 2:59 am
Is Navy boot camp different than veterans remember it? Is it still hard? And what do those changes say about the sailors joining the Navy today?
- Myanmar Rebel Group Claims Capture of Major Military HQ in Shan Stateon July 25, 2024 at 7:03 pm
The fall of the military’s Northeastern Regional Command headquarters would mark a turning-point in the country’s civil war.
- Coconuts, Context and Brat: Let Kamala Harris be a memeon July 25, 2024 at 1:16 pm
Vice President Kamala Harris has been something of a meme machine since before day one in the White House. What’s wrong with that?
- Crane looks to private public partnershipson July 25, 2024 at 11:17 am
To ensure it’s ready to meet the needs of future munitions production, Crane Army Ammunition Activity recently embarked on a 15-year, $285 million modernization ...
- Building Resilient Command and Control Centers with DVLED Technologyon July 24, 2024 at 6:30 am
DVLED technology represents a significant leap forward in display technology. Unlike traditional LCD and projection displays that rely on backlighting and light reflection, DVLED displays generate ...
- Strengthening Command and Control: A Deputy IGP enhances leadership, not undermines iton July 23, 2024 at 3:21 am
In modern policing, effective leadership is paramount. As law enforcement agencies around the world evolve to meet growing and complex challenges, the appointment of a Deputy Inspector General of ...
- All the Minecraft console commands and cheats for console and PCon July 17, 2024 at 5:00 pm
Sure, you can add quite a bit of entertainment to your Minecraft experience with player mods and add-ons, but using not-so-secret console commands to enhance or alter the world of Minecraft can be ...
- Comparing Ronald Reagan/Donald Trump shootings: Context is different, experts sayon July 16, 2024 at 5:19 pm
In American political history, there have been at least 15 "direct assaults" on U.S. presidents, presidents-elect and presidential candidates.
via Google News and Bing News