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
- S-NET Communications Launches AI-Powered Omnichannel Customer Experience Solution to Help Businesses Engage with Clients with Less Resourceson August 1, 2022 at 4:02 pm
In addition, its advanced AI engine and sentiment analysis capabilities enable organizations to automate their customer’s journey and intelligently connect each client to the virtual or live agent ...
- The Rise of Voice AI; Interview with Skit.ai Co-founder and CEO Sourabh Gupta.on August 1, 2022 at 7:05 am
Sourabh Gupta is the CEO and Co-founder of Skit.ai, an augmented voice intelligence platform designed to empower contact centers to manage customer inquiries more efficiently. In this interview with ...
- Thriving In The Online World: Why Digitally Empowered Agents Are The Future Of Insuranceon August 1, 2022 at 6:45 am
As AI solutions generate more actionable data, the new insurance customer experience will become more personalized and span multiple online and in-person interactions.
- Sony AI Announces New Gran Turismo Sophy™ Milestone with Gran Turismo World Series 2022 Exhibition Raceon August 1, 2022 at 5:00 am
Sony AI this week demonstrated its most recent progress in the development of Gran Turismo Sophy™ (GT Sophy)with an exhibition race against four of the world's top Gran Turismo™ (GT) drivers at the ...
- Missed Out on Nvidia? 3 Artificial Intelligence Stocks to Buy Nowon July 30, 2022 at 3:45 am
World-renowned semiconductor producer Nvidia is widely regarded as a pioneering force behind artificial intelligence (AI), and it remains a leader in the field today. But AI is a ...
- Championing customer experience in FS with AIon July 30, 2022 at 1:00 am
Financial services stands to benefit from greater use of artificial intelligence, with more efficiency and less human error, as Cirrus CEO Jason Roos says.
- Building Better Community Involvement with AI-Powered Virtual Agents in the City of San Jose, CAon July 29, 2022 at 10:49 am
From answering an increase in calls to beautifying the city, AI-powered virtual agents helped the City of San Jose better serve constituents and improve community engagement.
- Transforming Customer Service Starts With Voice AIon July 29, 2022 at 6:00 am
In the thick of our CX transformation journeys, conversational AI is a means for bridging the limits of automation as well as the gaps in workforce management. Now is the time to explore how ...
- Sony AI Wins 2022 ACM SIGAI Industry Award for Excellence in Artificial Intelligenceon July 27, 2022 at 7:00 am
Company recognized for its recent AI breakthrough, Gran Turismo Sophy™, at the 31st Annual International Joint Conference on Artificial ...
- New AI technology may aid in the discovery of therapeutic agents for neurodegenerative disorderson July 25, 2022 at 7:40 pm
A research group from Nagoya University in Japan has developed an artificial intelligence for analyzing cell images that uses machine learning to predict the therapeutic effect of drugs.
via Bing News