There's a troublesome Catch-22 when it comes to training someone to do a particularly dangerous job like, say, deactivating landmines left behind in conflict areas. With no margin for error, in-depth training is needed to prepare personnel to perform their task safely and effectively. But the danger of the task makes on-the-job training all but impossible.
That's the hope of technologists at Booz Allen Hamilton, a management and technology consulting and engineering services firm, which is turning to immersive virtual reality environments to address particularly dangerous on-the-job training. Powered by NVIDIA GPUs, the virtual reality application built by the Booz Allen Hamilton team is meant to bring a big dollop of reality and realism to hazardous job training and better prepare workers for the stress they're likely to experience in their roles.
Aside from safety challenges hazardous duty training can be expensive. Says Sandra Marshall, chief technologist at Booz Allen: "There can be high travel costs, and the ability to collect metrics is less than ideal. There's a real need for improvement in training for high- risk jobs."
Marshall and Elyse Heob, lead technologist at Booz Allen, are leading the project. Their latest effort is in medical triage for battlefield settings. The training simulations expose trainees to virtual peril, costs of complexities of live trainings as well as potentially increasing training times.
"It's much easier to give routine exposure of these things in virtual reality," Marshall said. "It's really a life-saving tool."
One reason virtual reality is so promising in high-impact, high-risk fields is that it's been show to trigger comparable emotional and cognitive responses to real-life scenarios. That means that in addition to technical skills and know-how, which perhaps could be acquired through traditional media, trainees are also able to gauge and account for their own responses to stressful stimuli.
To build their learning applications, Marshall and Heob's team has been combining NVIDIA GPUs with an array of VR technologies, including tethered VR platforms, biometric sensors, and eye and object trackers. They've been developing their applications on the open-platform Unity game-development engine.
"Different industries may want similar features," said Marshall, "so we configure those tools so they can be reused."
Eventually, Marshall envisions layering deep learning-infused AI over the apps and teaching them to learn from each training session.