US Army Combat Capabilities Development Command conducted research on robotics over the past decade. But, only recently has the military begun to integrate these technologies into its battlefield. They have been using their robots to detect IEDs and retrieve Ravens. The US Marine Corps has also been testing recon robots for urban warfare. These robots are designed to work as a team with Soldiers. These robots can be programmed to execute planned actions and also can make suggestions about changes.
The US Army is creating an algorithm-based learning platform that will allow Soldier robots to communicate with one another. The system will allow the robots to communicate with Soldiers using spoken language and then execute the necessary actions. It will allow robots to ask questions in order to overcome uncertainty. This will enable robots perform joint tasks at operational speeds, and it will also reduce the learning curves for Soldiers.
It is difficult to find the right questions when creating an algorithm-based system of learning. The research team developed a natural language understanding pipeline that processes the spoken language of a Soldier, and based the system on statistical classification techniques. The system was trained using a small dataset of human-robot dialog. This allowed the research team to incrementally tame the variability in natural language. The team is currently working to link the output semantic representations a Soldier's speaking language to the grounding mechanism of the robot.
Algorithm-based learning systems are designed to improve Soldier-robot cooperation in tactical environments. The robots will be able to communicate with Soldiers using natural language. A natural language processing pipeline was developed by the research team that interprets Soldiers' spoken language. The system will eventually have the ability to manage variation in spoken English. This will allow the robots to interpret the intent of the language, which will make them more collaborative.
The algorithm-based learning will also enable the robots ask Soldiers specific questions to gain an understanding of their environment. The questions will be generated from information found on maps. This will make it easier for robots to make autonomous decision-making. The questions are intended to be tactically pertinent. These questions examine the process by which robots make decisions, and the information the Soldiers need. The questions were also developed to gather feedback from Soldiers. The Soldiers' feedback was used to ensure that robots could recognize maps that were relevant for tactical decisions.
Soldier-bot critical has a higher attack rate and fires critical missiles faster than any other Soldier-bot variants. These rockets are six times more destructive than regular rockets. The critical variant also has higher health and can mow down players without crit resistance.