CCDC’S ROAD MAP TO MODERNIZING THE ARMY: SYNTHETIC TRAINING ENVIRONMENT
KEEP IT REAL Te STE, which is scheduled for initial operating capability in fourth quarter 2021, will provide a realistic operational environment for training using state-of- the-art mixed-reality technologies. One of STE’s major science and technology focus areas is improving dynamic occlu- sion, or the capability to “portray” or “hide” computer-generated characters and objects behind real things, and to do so in real time from multiple perspectives as actors, objects and users move around in the environment. Te virtual objects and the real scene must be perfectly aligned in order to maintain high levels of real- ism and enable objects to behave as they would under normal conditions.
Te popular mobile device-based game, Pokémon Go, is an example of dynamic occlusion that many people play. Players use their mobile phone or tablet to seek virtual characters that are hidden in the real world. Te characters appear as if they were hiding in and between real-world
We are coupling artificial intelligence with learning science to develop new ways to measure, assess and provide feedback to Soldiers and leadership automatically during and after STE training events.
12 Army AL&T Magazine Spring 2020
HERE’S HOW IT WORKS
Austin Drexler, a researcher at the Institute for Creative Technologies in Los Angeles, helps the author use special interactive goggles to view One World Terrain 3D interactive simulation data in July. (Photo by Joe Lacdan, Defense Media Activity)
objects. Sometimes, however, players will see a character that appears to be on the far side of a room, but is still visible in front. Tis technical issue removes aspects of realism, and when used for military train- ing will have an impact on outcomes.
Augmented reality game fans may encoun- ter dynamic occlusion errors when the view within the game is not layered or aligned appropriately with real-world objects, making the experience feel unnatural— an annoyance to the player. In military scenarios, the problem can adversely affect the learning experience and lead to nega- tive habits if, for example, a Soldier can’t
realistically take cover or if a vehicle crew can’t accurately aim and fire at an enemy.
Occlusion of live, moving objects is chal- lenging, and doing so at long distances is even more so. Current augmented- reality head-mounted displays restrict Soldier training to small, indoor environ- ments because of hardware limitations. For example, today a squad can execute a close-combat urban warfare training event in a room about the size of a basketball court. To work this challenge, the Simu- lation and Training Technology Center is evaluating several depth sensors and deep-learning algorithms to improve the alignment of the virtual and real objects
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100 |
Page 101 |
Page 102 |
Page 103 |
Page 104
