Capturing the intensity of a 5K race, and encapsulating the sweat, tears, and glory is a tricky task. Camera operators have to plan ahead and prepare to be in the right place at the right time, but often they miss vital parts of a race.
Now, mobile robots may be filming 5K races thanks to Aaron T. Becker, assistant professor of electrical and computer engineering at the University of Houston. Becker plans to direct a team of mobile robots that can change plans based on real-time action and predict likely events.
The filming will be the easy part for the robots. The challenge lies in having them act on their own to capture the most important parts of the race and weaving between obstacles effectively.
The robots will be equipped with cameras and are programmed to gather information as they travel. They also don’t know who will win, so the bots have to be receptive of the racers.
“Unlike the highlight reel in MarioKart, real robots won’t know ahead of time where the interesting parts will be,” says Becker, “but they will know a lot of probability theory, and will be able to calculate the odds of good video footage as a function of race status and robot position.”
Becker is collaborating with Dylan Shell, associate professor of computer science and engineering at Texas A&M University, and Jason O’Kane, professor of engineering and computing at the University of South Carolina.
The project will last for three years, and the robots will film a 5K race on the UH campus every year. Becker says the quality of the 5K documentary should get better each year.
Currently, five robots, including a robotic car that can move at speeds of 10 mph, are being built by a design team of electrical engineering students, which includes Rhema Ike, Farah Luba, Henry Nguyen, and Ramsey Daou.
Ike says the first task will entail training the robotic car to autonomously track a 5K runner the entire race.
“I love making autonomous robots,” says Ike. “The overall goal is to make a system where a robot can actually predict what will happen, and that’s pretty cool.”
In their research paper, the team discusses what they hope to learn and different avenues they can explore with their research. This may start with an athletic competition, but ultimately, they could identify the cause of an unfortunate event by directing robots to produce video footage of live events.