Thought you knew laser tag? Think again. A Singapore-based startup is taking laser tag into the 21<sup>st century using artificial intelligence, 3D printing and drones.
Tag Team Inc has spent the last six years coming up with its own laser tag technologies to upgrade the existing game, which involves teams of players armed with guns that fire infrared beams. The players wear targets that are sensitive to infrared and have to run around within an arena earning points by shooting other players while avoiding being hit themselves.
To expand beyond the basic concept of laser tag, which has essentially stayed the same since it was invented in 1979, Tag Team Inc has added several different features to its games.
In a game called "Laser Drone Tag", teams have to not only shoot each other, but also need to hit the target on a drone in the air (tethered to a fishing rod for safety). The team that manages to hit the drone 20 times first wins.
The startup has also developed its own interactive video game "Ninja Squad", which is played in the laser tag arena on a large TV screen. Five players armed with 3D printed swords and bows fight virtual enemies.
Every move they take is captured by the sensors in the weapons, and together the embedded system on the weapons and Tag Team Inc's servers identify the movement so that the computer can respond almost instantaneously. And towards the end of the game, a drone is released that shoots at the players from the air on behalf of the computer.
Inventing everything from scratch
Everything about Tag Team Inc's patent-pending system, from the weapons to the video game to the machine learning behind it was developed by the startup from scratch. All the hardware and the software had to be able to work together, and the firm's software developers and mathematicians also had to get the computers to learn to detect patterns, which is the hard part.
"It's been a difficult journey – we've had a lot of frustrations and technical problems. Even six months ago if you'd asked me about it, I wouldn't have sounded optimistic. But when the neural networks finally started learning, that's when things began coming together," Tag Team Inc's executive director Tony Tan Lay Thiam told IBTimes UK.
Neural networks are large networks of artificially intelligent classical computers that are trained using computer algorithms to solve complex problems in a similar way to the human central nervous system, whereby different layers examine different parts of the problem and combine to produce an answer.
In the last two years, computer scientists have demonstrated that neural networks can process images to produce surprising results, such as psychedelic paintings and amazing selfie filters, or use the images to learn to recognise and detect patterns, such as recognising blurred faces from photographs, or predicting social unrest several days in advance. However, it is still difficult to teach computers to think like a human, and research continues.
Neural networks for interactive games
Tag Team Inc developed its own model that combines various forms of machine learning, from neural networks to supervised and unsupervised learning, as well as its own printed circuit board (PCB) containing sensors that can understand spatial movement, orientation and gesture with limited sight.
"What makes us unique is the fact that we want things to work fast. We cannot put a very powerful computer into the weapons, so the real-time analysis is critical for us," explained Tan, a Cambridge University graduate in engineering.
"We use many neural networks with a few layers in each as the embedded system cannot handle too much computing power. We believe everything should be in the gadget, the question is how to analyse it and figure out what is going on."
The startup now has two laser tag recreational facilities in Singapore, but it is also keen to sell its system to other centres around the world. And since everything was developed in-house, it is possible to create other games that use the same technology but offer a tailored experience.
Tag Team Inc has been awarded a contract to develop a customised simulation and training game for a law enforcement agency, but it says that the options are endless for interactive games, and the technology could easily be adapted for the advertising industry.
The firm, which won a best innovative start-up award from the Singapore Infocomm Technology Federation (SiTF) in 2016, is keen to hear from partners and potential seed investors to help it take its technology to the next level.