MIT researchers build UQ-DAAAM, a robot memory system that corrects mislabeled objects
Overview
MIT researchers have developed UQ-DAAAM, a robot memory system that measures uncertainty in object descriptions and corrects mislabeled entries as the robot moves.
MIT News says that in tests the system raised the robot's confidence and improved the accuracy of its answers about objects, their locations, and when it saw them.
The work is scheduled for presentation at the Conference on Neural Information Processing Systems. The report describes only the test results cited above and does not give benchmark figures.
Written by AI from the articles below · updated Nov 5, 12:59 AM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- MIT News · AIOfficialMIT researchers develop UQ-DAAAM to help robots correct mislabeled memories
AIMIT researchers developed UQ-DAAAM, a robot memory system that measures uncertainty in object descriptions and corrects mislabeled entries as the robot moves. In tests, it raised the robot's confidence and improved the accuracy of its answers about objects, their locations, and when it saw them. The work will be presented at the Conference on Neural Information Processing Systems.
Heat Trend
Not enough continuous observations to show a trend yet.