If we will have robots acting as tour guides and delivering pizzas, then they need to navigate through busy environments. That’s exactly what a new robot made by MIT has been programmed to do. This robon even knows the social norms of movement and can overtake on the left and right. Not only this, it can take one side of a corridor.
To achieve all these things, a suite of cameras and laser sensors are attached at the top of the bot which allow it to recognise humans and stay out of their way. Lead researcher Yu Fan Chen said, “Socially aware navigation is a central capability for mobile robots operating in environments that require frequent interactions with pedestrians”. He added, “For instance, small robots could operate on sidewalks for package and food delivery. Similarly, personal mobility devices could transport people in large, crowded spaces, such as shopping malls, airports, and hospitals”.
Now robots can avoid basic obstacles without much trouble. But the MTI team decided to build a navigation algorithm which obeyed some of the unspoken rules such as leaving a wide berth when someone is passing.
One of the team Michael Everett says, “The part of the field that we thought we needed to innovate on was motion planning. Once you figure out where you are in the world, and know how to follow trajectories, which trajectories should you be following?”.
The researchers say, “Getting the perfect balance between the speed and safety is difficult”. To overcome this problem, the team has used a type of machine learning called reinforcement learning, where systems are trained through trial and error rather than a set of specific commands.
The system can access its environment and adjust its path every tenth of a second, without stopping to reprogram itself each time. It can maintain a walking speed of 1.2 meters per second.
The next step is to update the robot to handle busier crowds in an urban environment, which will involve deciding whether pilot or try through clumps of people or go all the way around them. Everett says, “We want it to be travelling naturally among people and not be intrusive. We want it to be following the same rules as everyone else”.
Researchers have made a video about the research which you can see below: