Robotaxi

A method of operating a shuttle including performing, using at least one central processing unit (CPU), at least one hardware accelerator supporting at least one neural network, and at least one graphics processing unit (GPU) on the shuttle and communicatively coupled to sensors, operations comprising:

• defining a virtual rail comprising a predefined route and one or more stopping points;
• sensing in an environment of the shuttle using the sensors including at least one light detection and ranging (LIDAR) sensor, at least one camera, and at least one global positioning system (GPS) sensor;
• in response to the sensing, controlling propulsion, drive train, and steering systems of the shuttle to propel the shuttle along at least one of the virtual rail or a deviation from the virtual rail, the deviation from the virtual rail being used when one or more conditions are satisfied;
• identifying passengers to ride in the shuttle;
• and
• based at least in part on situational awareness provided by the at least one neural network, autonomously determining whether to selectively stop the shuttle at individual stopping points of the one or more stopping points of the virtual rail to at least one of take on or discharge passengers.

In a shuttle comprising a propulsion, drive train, and steering system to propel the shuttle, and sensors disposed on the shuttle including at least one light detection and ranging (LIDAR) sensor, at least one camera, and at least one global positioning system (GPS) sensor, a control system on the shuttle comprising at least one central processing unit (CPU), at least one hardware accelerator supporting at least one neural network, and at least one graphics processing unit (GPU) communicatively coupled to the sensors, the control system on the shuttle performing operations comprising:

• defining a virtual rail comprising one or more stopping points;
• controlling the propulsion, drive train, and steering system to propel the shuttle along at least one of the virtual rail or a deviation from the virtual rail, the deviation from the virtual rail being used when one or more conditions are satisfied;
• identify passengers to ride in the shuttle;
• and
• based at least in part on situational awareness provided by the at least one neural network, autonomously determining whether to selectively stop the shuttle at individual stopping points of the one or more stopping points of the virtual rail to at least one of take on or discharge passengers.