Raytheon is developing a machine-learning technology under a $6 million contract from the US Defense Advanced Research Projects Agency for the Competency Aware Machine Learning program.
Systems will be able to communicate the abilities they have learned, the conditions under which the abilities were learned, the strategies they recommend and the situations for which those strategies can be used.
Ilana Heintz, principal investigator for CAML at Raytheon BBN Technologies said the CAML system turned tools into partners.
“It will understand the conditions where it makes decisions and communicate the reasons for those decisions.”
“The system will learn from a video-game-like process.
“Instead of giving the system rules, the researchers will tell the system what choices it has in the game and what the ultimate goal is.
“By repeatedly playing the game, the system will learn the most effective ways to meet the goal.”
Dr Heintz said the system would explain itself by recording the conditions and strategies it used to come up with successful outcomes.
“People need to understand an autonomous system’s skills and limitations to trust it with critical decisions.”
Once the system has developed these skills, the Raytheon team will apply it to a simulated search and rescue mission.
Users will create the conditions surrounding the mission, while the system will make recommendations and give users information about its competence in those particular conditions.
For example, the system might say, “In the rain, at night, I can distinguish between a person and an inanimate object with 90 percent accuracy, and I have done this more than 1000 times”.