According to MIT, developing a robot or driver-less automobile should start with golf carts.
And along with the National Research Foundation of Singapore, they've come up with SMART (Singapore-MIT Alliance for Research and Technology), a collaboration to create a self-driving golf cart. For six days the self-driving golf carts were tested at a large public garden.
They also developed an phone app that lets potential riders order a ride at one of 10 stations on the island, rerouting vehicles to meet customer demand as needed, which is smart. Unlike transportation like the popular rent-a-bike stations in most cities, these golf carts are programmed to go wherever the need is. Unlike the bikes, which most often end up pilling up at the same drop-off location, these cars can respond to the demand and go back or answer another request from the app.
What sets the SMART program’s vehicles apart is that “we are taking a minimalist solution to the self-driving-car problem,” Rus says. “The golf carts are not as overly instrumented as the DARPA (Defense Advanced Research Projects Agency) were, nor as heavily instrumented as, say, the Google car. We believe that if you have a simple suite of strategically placed sensors and augment that with reliable algorithms, you will get robust results that require less computation and have less of a chance to get confused by ‘fusing sensors,’ or situations where one sensor says one thing and another sensor says something different.”