Associate Professor Dario Pompili has been awarded a new NSF award for the project titled "Robust, scalable, distributed semantic mapping for search-and-rescue and manufacturing co-robots." This is a three-year $850,000 collaborative effort between Boston University and Rutgers University. Rutgers' share of this award is $426,161.
The goal of this project is to enable multiple co-robots to map and understand the environment they are in to collaborate among themselves and with human operators in education, medical assistance, agriculture, and manufacturing applications. The first characteristic of this project is that the environment is modeled semantically, that is, it contains human-interpretable labels (e.g., object category names) in addition to geometric data. This is achieved through a novel, robust integration of methods from both computer vision and robotics, and allows easier communications between robots and humans in the field. The second characteristic is that the increased computation load due to the addition of human-interpretable information is handled by judiciously approximating and spreading the computations across the entire network.
Specifically, as part of this project, Dario and his team will propose a new optimization framework for semantic mapping that can handle large, dynamic, uncertain environments under significant measurement errors, studying interactions and information exchanges with humans, and allowing an intelligent sharing of the limited computational resources possessed by the network of co-robots as a whole by enabling approximations and balancing of the computations. The novel developed methods will be evaluated by emulating real-world scenarios in manufacturing and for search-and-rescue operations.
You can find more details on the project at the NSF page here: