Abstract: Techniques are disclosed for determining a safety metric or other performance metric associated with a vehicle. The techniques may comprise receiving a driving simulation scenario associated simulating a simulated vehicle. Based at least in part on map data and the driving simulation scenario, a road segment of the map data may be determined. A simulation of the vehicle may be initiated in accordance with the driving simulation scenario, the simulation including the road segment. A safety metric associated with autonomous operation of the simulated vehicle in a region comprising the road segment may be determined based at least in part on the simulation.

Abstract: Techniques for determining a metrics associated with a vehicle are disclosed. The techniques may comprise receiving a driving simulation scenario associated with a simulated vehicle. Based at least in part on the scenario and a dataset of recorded driving associated with operation of a test vehicle, a plurality of driving events present in the dataset may be determined. Based at least in part on the plurality of driving events, a first metric associated with a likelihood of occurrence of the driving simulation scenario may be determined. A simulation may be instantiated based at least in part on the driving simulation scenario. Based at least in part on the simulation, a safety metric indicative of the safe performance of the simulated vehicle in the simulation may be determined. An aggregate safety metric may be determined based at least in part on the safety metric and the first metric.

Abstract: Techniques for determining a metrics associated with a vehicle are disclosed. The techniques may comprise receiving a driving simulation scenario associated with a simulated vehicle. Based at least in part on the scenario and a dataset of recorded driving associated with operation of a test vehicle, a plurality of driving events present in the dataset may be determined. Based at least in part on the plurality of driving events, a first metric associated with a likelihood of occurrence of the driving simulation scenario may be determined. A simulation may be instantiated based at least in part on the driving simulation scenario. Based at least in part on the simulation, a safety metric indicative of the safe performance of the simulated vehicle in the simulation may be determined. An aggregate safety metric may be determined based at least in part on the safety metric and the first metric.

Abstract: A vehicle collects video data of an environment surrounding the vehicle including traffic entities, e.g., pedestrians, bicyclists, or other vehicles. The captured video data is sampled and the sampled video frames are presented to users to provide input on a traffic entity's state of mind. The system determines an attribute value that describes a statistical distribution of user responses for the traffic entity. If the attribute for a sampled video frame is within a threshold of the attribute of another video frame, the system interpolates attribute for a third video frame between the two sampled video frames. Otherwise, the system requests further user input for a video frame captured between the two sampled video frames. The interpolated and/or user based attributes are used to train a machine learning based model that predicts a hidden context of the traffic entity. The trained model is used for navigation of autonomous vehicles.

Abstract: Systems and methods for predicting user interaction with vehicles. A computing device receives an image and a video segment of a road scene, the first at least one of an image and a video segment being taken from a perspective of a participant in the road scene and then generates stimulus data based on the image and the video segment. Stimulus data is transmitted to a user interface and response data is received, which includes at least one of an action and a likelihood of the action corresponding to another participant in the road scene. The computing device aggregates a subset of the plurality of response data to form statistical data and a model is created based on the statistical data. The model is applied to another image or video segment and a prediction of user behavior in the another image or video segment is generated.

Abstract: Systems and methods for predicting user interaction with vehicles. A computing device receives an image and a video segment of a road scene, the first at least one of an image and a video segment being taken from a perspective of a participant in the road scene and then generates stimulus data based on the image and the video segment. Stimulus data is transmitted to a user interface and response data is received, which includes at least one of an action and a likelihood of the action corresponding to another participant in the road scene. The computing device aggregates a subset of the plurality of response data to form statistical data and a model is created based on the statistical data. The model is applied to another image or video segment and a prediction of user behavior in the another image or video segment is generated.

Abstract: Systems and methods for predicting user interaction with vehicles. A computing device receives an image and a video segment of a road scene, the first at least one of an image and a video segment being taken from a perspective of a participant in the road scene and then generates stimulus data based on the image and the video segment. Stimulus data is transmitted to a user interface and response data is received, which includes at least one of an action and a likelihood of the action corresponding to another participant in the road scene. The computing device aggregates a subset of the plurality of response data to form statistical data and a model is created based on the statistical data. The model is applied to another image or video segment and a prediction of user behavior in the another image or video segment is generated.

Abstract: A vehicle collects video data of an environment surrounding the vehicle including traffic entities, e.g., pedestrians, bicyclists, or other vehicles. The captured video data is sampled and presented to users to provide input on a traffic entity's state of mind. The user responses on the captured video data is used to generate a training dataset. A machine learning based model configured to predict a traffic entity's state of mind is trained with the training dataset. The system determines input video frames and associated dimension attributes for which the model performs poorly. The dimension attributes characterize stimuli and/or an environment shown in the input video frames. The system generates a second training dataset based on video frames that have the dimension attributes for which the model performed poorly. The model is retrained using the second training dataset and provided to an autonomous vehicle to assist with navigation in traffic.

Abstract: Systems and methods for predicting user interaction with vehicles. A computing device receives an image and a video segment of a road scene, the first at least one of an image and a video segment being taken from a perspective of a participant in the road scene and then generates stimulus data based on the image and the video segment. Stimulus data is transmitted to a user interface and response data is received, which includes at least one of an action and a likelihood of the action corresponding to another participant in the road scene. The computing device aggregates a subset of the plurality of response data to form statistical data and a model is created based on the statistical data. The model is applied to another image or video segment and a prediction of user behavior in the another image or video segment is generated.

Abstract: Systems and methods for predicting user interaction with vehicles. A computing device receives an image and a video segment of a road scene, the first at least one of an image and a video segment being taken from a perspective of a participant in the road scene and then generates stimulus data based on the image and the video segment. Stimulus data is transmitted to a user interface and response data is received, which includes at least one of an action and a likelihood of the action corresponding to another participant in the road scene. The computing device aggregates a subset of the plurality of response data to form statistical data and a model is created based on the statistical data. The model is applied to another image or video segment and a prediction of user behavior in the another image or video segment is generated.

Abstract: Systems and methods for predicting user interaction with vehicles. A computing device receives an image and a video segment of a road scene, the first at least one of an image and a video segment being taken from a perspective of a participant in the road scene and then generates stimulus data based on the image and the video segment. Stimulus data is transmitted to a user interface and response data is received, which includes at least one of an action and a likelihood of the action corresponding to another participant in the road scene. The computing device aggregates a subset of the plurality of response data to form statistical data and a model is created based on the statistical data. The model is applied to another image or video segment and a prediction of user behavior in the another image or video segment is generated.

Abstract: Systems and methods for predicting user interaction with vehicles. A computing device receives an image and a video segment of a road scene, the first at least one of an image and a video segment being taken from a perspective of a participant in the road scene and then generates stimulus data based on the image and the video segment. Stimulus data is transmitted to a user interface and response data is received, which includes at least one of an action and a likelihood of the action corresponding to another participant in the road scene. The computing device aggregates a subset of the plurality of response data to form statistical data and a model is created based on the statistical data. The model is applied to another image or video segment and a prediction of user behavior in the another image or video segment is generated.

Abstract: A vehicle collects video data of an environment surrounding the vehicle including traffic entities, e.g., pedestrians, bicyclists, or other vehicles. The captured video data is sampled and presented to users to provide input on a traffic entity's state of mind. The user responses on the captured video data is used to generate a training dataset. A machine learning based model configured to predict a traffic entity's state of mind is trained with the training dataset. The system determines input video frames and associated dimension attributes for which the model performs poorly. The dimension attributes characterize stimuli and/or an environment shown in the input video frames. The system generates a second training dataset based on video frames that have the dimension attributes for which the model performed poorly. The model is retrained using the second training dataset and provided to an autonomous vehicle to assist with navigation in traffic.

Abstract: A vehicle collects video data of an environment surrounding the vehicle including traffic entities, e.g., pedestrians, bicyclists, or other vehicles. The captured video data is sampled and the sampled video frames are presented to users to provide input on a traffic entity's state of mind. The system determines an attribute value that describes a statistical distribution of user responses for the traffic entity. If the attribute for a sampled video frame is within a threshold of the attribute of another video frame, the system interpolates attribute for a third video frame between the two sampled video frames. Otherwise, the system requests further user input for a video frame captured between the two sampled video frames. The interpolated and/or user based attributes are used to train a machine learning based model that predicts a hidden context of the traffic entity. The trained model is used for navigation of autonomous vehicles.

Abstract: Systems and methods for predicting user interaction with vehicles. A computing device receives an image and a video segment of a road scene, the first at least one of an image and a video segment being taken from a perspective of a participant in the road scene and then generates stimulus data based on the image and the video segment. Stimulus data is transmitted to a user interface and response data is received, which includes at least one of an action and a likelihood of the action corresponding to another participant in the road scene. The computing device aggregates a subset of the plurality of response data to form statistical data and a model is created based on the statistical data. The model is applied to another image or video segment and a prediction of user behavior in the another image or video segment is generated.

Abstract: A computing device receives an image and a video segment of a road scene, the first at least one of an image and a video segment being taken from a perspective of a participant in the road scene and then generates stimulus data based on the image and the video segment. Stimulus data is transmitted to a user interface and response data is received, which includes at least one of an action and a likelihood of the action corresponding to another participant in the road scene. The computing device aggregates a subset of the plurality of response data to form statistical data and a model is created based on the statistical data. The model is applied to another image or video segment and a prediction of user behavior in the another image or video segment is generated.

Abstract: Systems and methods for predicting user interaction with vehicles. A computing device receives an image and a video segment of a road scene, the first at least one of an image and a video segment being taken from a perspective of a participant in the road scene and then generates stimulus data based on the image and the video segment. Stimulus data is transmitted to a user interface and response data is received, which includes at least one of an action and a likelihood of the action corresponding to another participant in the road scene. The computing device aggregates a subset of the plurality of response data to form statistical data and a model is created based on the statistical data. The model is applied to another image or video segment and a prediction of user behavior in the another image or video segment is generated.