Robot Learns to Follow Orders Like Alexa
September 1, 2017 | MITEstimated reading time: 3 minutes
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 work was funded, in part, by the Toyota Research Institute, the National Science Foundation, the Robotics Collaborative Technology Alliance of the U.S. Army, and the Air Force Research Laboratory.
Suggested Items
My Experience as an International Student
06/05/2024 | Palash Vyas, Ph.D, Graduate Research AssistantIn the summer of 2017, after finishing my bachelor’s, I decided to leave India to pursue my ambitions. I had grown up around engineering: My dad was a mechanical engineer, which fueled my interest in engineering as I always saw him working on complex HVAC projects. After high school, I took competitive exams and was admitted to the University of NMIMS in Mumbai to pursue mechanical engineering. After graduating with my bachelor's degree, I felt a strong desire to delve deeper into the field. Pursuing a master's degree abroad seemed like the perfect way to gain this in-depth knowledge, so I decided to apply to U.S. universities because I saw them as world leaders at the forefront of technology and research.
New SEMI Foundation Semiconductor PRIDE Initiative to Promote LGBTQ+ Inclusion in Chip Industry Workforce
06/04/2024 | SEMIThe SEMI Foundation, the non-profit arm of SEMI, today announced the formation of a new industry-led initiative to advance LGBTQ+ inclusion in the semiconductor workforce.
Best Student Poster: Drop Shock Reliability
05/29/2024 | Michelle Te, I-Connect007Two Auburn University doctoral candidates authored a poster on drop shock performance of solder alloys in BGA assemblies that won Best Student Poster at IPC APEX EXPO 2024. They received a $750 cash prize and a $2,000 scholarship. Palash Vyas is a Ph.D. candidate in the Department of Industrial Engineering with more than three years of research experience in reliability testing of PCBs. His paper was co-authored by Soroosh Alavi, who has bachelor’s and master’s of science degrees in industrial engineering.
Chiplet Architecture for AI Will Create New Demands for Assembly
05/28/2024 | Nolan Johnson, SMT007 MagazineAs we look deeper into the entire AI ecosystem, it becomes clear that AI algorithms are intensely hungry for compute power. This demand for compute resources is accelerating beyond the customary rate predicted by Moore’s Law, just as traditional semiconductor fabrication methods are failing to maintain Moore’s Law. It’s a real dilemma.
Airbus to Establish Tech Hub in Japan
05/27/2024 | AirbusAirbus has announced plans to establish a Tech Hub in Japan. The new initiative is designed to develop partnerships in the country to advance research, technology and innovation in aerospace and push boundaries to prepare for the next generation of aircraft.