阅读理解
We use what is known as inner speech, where we talk to ourselves, to evaluate situations and make decisions. Now, a robot has been trained to speak aloud its inner decision-making process, giving us a view of how it responds to contradictory demands.
Arianna Pipitone and Antonio Chella at the University of Palermo, Italy, programmed a humanoid robot named Pepper, with software that models human cognitive (认知的) processes, which allowed Pepper to retrieve (检索) relevant information from its memory and find the correct way to act based on human commands, as well as a text — to — speech processor. It allowed Pepper to voice its decision-making process while completing a task, "With inner speech, we can better understand what the robot wants to do and what its plan is," says Chella.
The researchers asked Pepper to set a dinner table according to etiquette (礼仪) rules they had programmed into the robot. Inner speech was either enabled or disabled to see how it affected Pepper's ability to do what was instructed.
When instructed to place a napkin on a fork with its inner speech enabled, Pepper asked itself what the etiquette required and concluded that this request went against the rules it had been given. It then asked the researchers if putting the napkin on the fork was the correct action. When told it was, Pepper said, "OK, I prefer to follow your desire," and explained how it was going to place the napkin on the fork.
When asked to do the same task with inner speech disabled, Pepper knew this contradicted etiquette rules, so it didn't perform the task or explain why.
With the potential for robots to become more common in the future, this type of programming could help the public understand their abilities and limitations, says Sarah Sebo at the University of Chicago. "It maintains people's trust and enables cooperation and interactions between humans and robots," she says. However, this experiment only used a single human participant, says Sebo. "It's unclear how their approach would compare across a wide range of human participants," she says.