Why did the frog cross the road? Well, a new artificial intelligent (AI) agent that can play the classic arcade game Frogger not only can tell you why it crossed the road, but it can justify its every move in everyday language.
Developed by Georgia Tech, in collaboration with Cornell and the University of Kentucky, the work enables an AI agent to provide a rationale for a mistake or errant behavior, and to explain it in a way that is easy for non-experts to understand.
This, the researchers say, may help robots and other types of AI agents seem more relatable and trustworthy to humans. They also say their findings are an important step toward a more transparent, human-centered AI design that understands people’s preferences and prioritizes people’s needs.
“If the power of AI is to be democratized, it needs to be accessible to anyone regardless of their technical abilities,” said Upol Ehsan, Ph.D. student in the School of Interactive Computing at Georgia Tech and lead researcher.
“As AI pervades all aspects of our lives, there is a distinct need for human-centered AI design that makes black-boxed AI systems explainable to everyday users. Our work takes a formative step toward understanding the role of language-based explanations and how humans perceive them.”
The study was supported by the Office of Naval Research (ONR).
Researchers developed a participant study to determine if their AI agent could offer rationales that mimicked human responses. Spectators watched the AI agent play the videogame Frogger and then ranked three on-screen rationales in order of how well each described the AI’s game move.
Of the three anonymized justifications for each move – a human-generated response, the AI-agent response, and a randomly generated response – the participants preferred the human-generated rationales first, but the AI-generated responses were a close second.
Frogger offered the researchers the chance to train an AI in a “sequential decision-making environment,” which is a significant research challenge because decisions that the agent has already made influence future decisions. Therefore, explaining the chain of reasoning to experts is difficult, and even more so when communicating with non-experts, according to researchers.
In case the study participants weren’t familiar, the game’s goal of getting the frog safely home without being hit by moving vehicles or drowned in the river was explained to them. The simple game mechanics of moving up, down, left or right, allowed the participants to see what the AI was doing, and to reasonably evaluate if the rationales on the screen clearly justified the move.
The participants judged the rationales based on:
- Confidence – the person is confident in the AI to perform its task
- Human-likeness – looks like it was made by a human
- Adequate justification – adequately justifies the action taken
- Understandability – helps the person understand the AI’s behavior
AI-generated rationales that were ranked higher by participants were those that showed recognition of environmental conditions and adaptability, as well as those that communicated awareness of upcoming dangers and planned for them. Redundant information that just stated the obvious or misrepresented the environment were found to have a negative impact.
“This project is more about understanding human perceptions and preferences of these AI systems than it is about building new technologies,” said Ehsan. “At the heart of explainability is sensemaking. We are trying to understand that human factor.”
A second related study validated the researchers’ decision to design their AI agent to be able to offer one of two distinct types of rationales:
- Concise, “focused” rationales or
- Holistic, “complete picture” rationales
In this second study, participants were only offered AI-generated rationales after watching the AI play Frogger. They were asked to select the answer that they preferred in a scenario where an AI made a mistake or behaved unexpectedly. They did not know the rationales were grouped into the two categories.
By a 3-to-1 margin, participants favored answers that were classified in the “complete picture” category. Responses showed that people appreciated the AI thinking about future steps rather than just what was in the moment, which might make them more prone to making another mistake. People also wanted to know more so that they might directly help the AI fix the errant behavior.
“The situated understanding of the perceptions and preferences of people working with AI machines give us a powerful set of actionable insights that can help us design better human-centered, rationale-generating, autonomous agents,” said Mark Riedl, professor of Interactive Computing and lead faculty member on the project.
A possible future direction for the research will apply the findings to autonomous agents of various types, such as companion agents, and how they might respond based on the task at hand. Researchers will also look at how agents might respond in different scenarios, such as during an emergency response or when aiding teachers in the classroom.
The Latest on: AI agents
via Google News
The Latest on: AI agents
- 28 Years and Running: IBM Awarded Most Patents in 2020 – a “Sharp Uptick” in AIon January 12, 2021 at 11:05 am
For the 28th year in a row, IBM copped more U.S. patents than any other company, 9,130 in all, including what the company said was a “sharp uptick” in AI-related patents. Patents were awarded to more ...
- Avaya Expanding AI-powered Contact Center Capabilities to Improve Customer Experience, Participating with AWS Contact Center Intelligenceon January 12, 2021 at 10:00 am
Avaya (NYSE: AVYA), a global leader in solutions to enhance and simplify communications and collaboration, today announced an expansion of its artific ...
- Observe.AI Partners with UJETon January 12, 2021 at 7:36 am
Observe.AI, a provider of artificial intelligence technology for contact centers, is partnering with UJET, a cloud contact center provider, making it the first workforce optimization (WFO) solution ...
- How To Find The Right Business Insurance Using AIon January 12, 2021 at 2:58 am
No longer just a hallmark of science-fiction, AI is pushing the business world even further with its integration into several business sectors, including insurance.
- Pega Acquires Qurious.io for AI-Powered Speech Analyticson January 12, 2021 at 1:44 am
(NASDAQ: PEGA), the software company that crushes business complexity, today announced its acquisition of Qurious.io, Inc., a cloud-based real-time speech analytics solution powered by artificial ...
- Five9 Agent Assist and Inference Studio Platform Win 2021 BIG Innovation Awardson January 12, 2021 at 12:05 am
(NASDAQ: FIVN), a leading provider of the intelligent cloud contact center, today announced that Five9 Agent Assist has been named a winner in the 2021 BIG Innovation Awards presented by the ...
- AI devs claim they’ve created a robot that demonstrates a ‘primitive form of empathy’on January 11, 2021 at 11:15 am
Columbia University researchers have developed a robot that displays a "glimmer of empathy" by visually predicting how another machine will behave.
- AI and automation are linchpins for post-pandemic business successon January 8, 2021 at 6:19 am
In both the short term and the long term, and across back- and front-office applications, AI has the potential to add value to business workflows, augment employee capabilities, and harness the power ...
- How AI-Powered Virtual Agents Can Upgrade Municipal Serviceson January 7, 2021 at 5:10 am
Providing citizens with easier access to municipal and state services can be difficult and costly, yet the improvement in "living experience" can be dramatic.
- Conversational AI in 2021: 3 top trends to look out foron January 5, 2021 at 10:57 pm
AI space, fueled by a global pandemic that has necessitated a shift in how vendors, businesses and consumers view the technology. That’s not to say that business has been bad. Markets and Markets ...
via Bing News