An autonomous vehicle is described herein. The autonomous vehicle is configured to determine that a person is proximate the autonomous vehicle at a location that is external to the autonomous vehicle. The autonomous vehicle is further configured to determine that the person is attempting to hail the autonomous vehicle through use of a gesture. The autonomous vehicle identifies the gesture being performed by the person, and responsive to identifying the gesture, identifies a travel intent that the person is imparting to the autonomous vehicle by way of the gesture. The autonomous vehicle then operates based upon the travel intent.

The present disclosure relates to systems, methods, and computer readable media implemented in connection with an unmanned aerial vehicle (UAV) to navigate a UAV along a desired path. For example, systems disclosed herein identify an anticipatory flight path and identify a plurality of reference points on the flight path relative to a current position of the UAV. The systems described herein may further determine reference angles between a current trajectory of the UAV and the reference points to determine an updated trajectory that the UAV should take to stay close to the identified flight path. The systems described herein may further cause the UAV to accelerate in a lateral direction based on the updated trajectory. The features and functionality of systems disclosed herein enable the UAV to accurately follow a complex path having sharp turns with little or no advanced knowledge of the flight path prior to departure.

A system and method for a motorized mobile chair use a plurality of sensors having a plurality of sensor types to detect a plurality of objects and generate sensor data about the detected objects, each of the detected objects being a person, the sensor data about the objects comprising a plurality of range measurements to the people and a plurality of bearing measurements to the people. The system has at least one processor to receive the sensor data about the people, group the detected people into a plurality of zones, determine a closest person in each zone, and generate one or more control signals to cause the motorized mobile chair to match a speed and a direction of the closest person in the zone corresponding to a direction of travel of the motorized mobile chair while at least approximately maintaining a selected space to the closest person in the zone corresponding to the direction of travel of the motorized mobile chair.

A prediction-based system and method for trajectory planning of autonomous vehicles are disclosed. A particular embodiment is configured to: receive training data and ground truth data from a training data collection system, the training data including perception data and context data corresponding to human driving behaviors; perform a training phase for training a trajectory prediction module using the training data; receive perception data associated with a host vehicle; and perform an operational phase for extracting host vehicle feature data and proximate vehicle context data from the perception data, generating a proposed trajectory for the host vehicle, using the trained trajectory prediction module to generate predicted trajectories for each of one or more proximate vehicles near the host vehicle based on the proposed host vehicle trajectory, determining if the proposed trajectory for the host vehicle will conflict with any of the predicted trajectories of the proximate vehicles, and modifying the proposed trajectory for the host vehicle until conflicts are eliminated.

A prediction-based system and method for trajectory planning of autonomous vehicles are disclosed. A particular embodiment is configured to: receive training data and ground truth data from a training data collection system, the training data including perception data and context data corresponding to human driving behaviors; perform a training phase for training a trajectory prediction module using the training data; receive perception data associated with a host vehicle; and perform an operational phase for extracting host vehicle feature data and proximate vehicle context data from the perception data, generating a proposed trajectory for the host vehicle, using the trained trajectory prediction module to generate predicted trajectories for each of one or more proximate vehicles near the host vehicle based on the proposed host vehicle trajectory, determining if the proposed trajectory for the host vehicle will conflict with any of the predicted trajectories of the proximate vehicles, and modifying the proposed trajectory for the host vehicle until conflicts are eliminated.

A domain specific language for use in constructing simulations within real environments is described. In an example, a computing device associated with a vehicle can receive, from one or more sensors associated with the vehicle, sensor data associated with an environment within which the vehicle is positioned. In an example, the vehicle can be an autonomous vehicle. The computing device associated with the vehicle can receive simulated data associated with one or more primitives that are to be instantiated as a scenario in the environment. The computing device can merge the sensor data and the simulated data to generate aggregated data and determine a trajectory along which the vehicle is to drive based at least in part on the aggregated data. The computing device can determine instructions for executing the trajectory and can assess the performance of the vehicle based on how the vehicle responds to the scenario.

A domain specific language for use in constructing simulations within real environments is described. In an example, a computing device associated with a vehicle can receive, from one or more sensors associated with the vehicle, sensor data associated with an environment within which the vehicle is positioned. In an example, the vehicle can be an autonomous vehicle. The computing device associated with the vehicle can receive simulated data associated with one or more primitives that are to be instantiated as a scenario in the environment. The computing device can merge the sensor data and the simulated data to generate aggregated data and determine a trajectory along which the vehicle is to drive based at least in part on the aggregated data. The computing device can determine instructions for executing the trajectory and can assess the performance of the vehicle based on how the vehicle responds to the scenario.

A transportation system, that optimizes at least one operating parameter of a vehicle based on a physiological state of an occupant of the vehicle, includes a sensor that senses a physiological condition of the occupant and that outputs data based on the sensed physiological condition. The transportation system further includes an artificial intelligence system that receives and processes the data to determine an emotional state of the occupant, and optimizes, for achieving a favorable emotional state of the occupant, the at least one operating parameter of the vehicle in response to detecting the emotional state of the occupant.

Systems and methods for using parametric modeling to design scenarios for autonomous vehicle simulation are provided. In particular, a computing system can obtain data identifying a plurality of parameters, each parameter associated with a particular scenario component. The computing system can determine values associated with a first set of parameters in the plurality of parameters. The computing system can determine one or more parameter relationships, such that values associated with a second set of parameters in the plurality of parameters are determined, at least in part, based on the values associated with the first set of parameters. The computing system can initiate a simulation of a scenario based, at least in part, on the values associated with the first set of the parameters and the one or more parameter relationships. The computing system can determine whether the simulated autonomous vehicle has successfully completed the scenario.

Methods and systems autonomously parking and retrieving vehicles are disclosed. Available parking spaces or parking facilities may be identified, and the vehicle may be navigated to an available space from a drop-off location without passengers. Special-purpose sensors, GPS data, or wireless signal triangulation may be used to identify vehicles and available parking spots. Upon a user request or a prediction of upcoming user demand, the vehicle may be retrieved autonomously from a parking space. Other vehicles may be autonomously moved to facilitate parking or retrieval.