A newly developed robot at MIT is able to follow pedestrian traffic rules – a step towards what future robots that will be ‘socially aware’.
The capabilities of the robot are being dubbed as “socially aware navigation” that enables it to pace along side pedestrians while following the basic traffic rules and being able to navigate through crowd without bumping into anyone. The robot, which resembles a knee-high kiosk on wheels, successfully avoided collisions while keeping up with the average flow of pedestrians.
“Socially aware navigation is a central capability for mobile robots operating in environments that require frequent interactions with pedestrians,” said Yu Fan Chen, a former graduate student at Massachusetts Institute of Technology (MIT) in the US.
Pedestrians too have to follow some rules though they may not be as stringent as those applicable for vehicles like keeping to their lanes, overtaking from specific side, keeping enough distance from front vehicles, etc.
For a robot to make its way autonomously through a heavily trafficked environment, it must solve four main challenges: localisation (knowing where it is in the world), perception (recognising its surroundings), motion planning (identifying the optimal path to a given destination), and control (physically executing its desired path).
Researchers used standard approaches to solve the problems of localisation and perception.
For the latter, they outfitted the robot with off-the-shelf sensors, such as webcams, a depth sensor, and a high-resolution lidar sensor. For the problem of localisation, they used open-source algorithms to map the robot’s environment and determine its position. To control the robot, they employed standard methods used to drive autonomous ground vehicles.
The tricky part was to navigate in pedestrian-heavy environments, where individual paths are often difficult to predict. Usually roboticists try to program a robot to compute an optimal path that accounts for everyone’s movements.
The team found a way around such limitations, enabling the robot to adapt to unpredictable pedestrian behaviour while continuously moving with the flow and following typical social codes of pedestrian conduct.
They used reinforcement learning, a type of machine learning approach, in which they performed computer simulations to train a robot to take certain paths, given the speed and trajectory of other objects in the environment.
The team also incorporated social norms into this offline training phase, in which they encouraged the robot in simulations to pass on the right, and penalised the robot when it passed on the left.