摘要:
In one embodiment, a first image of a physical object external to an autonomous vehicle is received, where the first image is captured by an image sensor attached to the autonomous vehicle. An image recognition is performed on the first image to derive one or more keywords related to the physical object. A list of one or more content items are identified based on the one or more keywords. A first content item selected from the list of content items is augmented onto the first image to generate a second image. The second image is displayed on a display device within the autonomous vehicle.
摘要:
Described is a system that provides the ability for an autonomous driving vehicle to visually communicate with other traffic entities such as other autonomous driving vehicles, non-autonomous driving vehicles, pedestrians, cyclists, and the like. To provide such an ability, the system allows autonomous driving vehicles to communicate using a lighting mechanism. For example, the lighting mechanism may include one or more specialized lights that are provided in addition to any mandated lighting systems required for a vehicle (e.g. brake lights, headlights, turn signals, etc.). Accordingly, the autonomous driving vehicle may communicate with traffic entities to provide additional cues such as intended driving maneuvers, and to provide a mechanism for two-way communication with other autonomous driving vehicles.
摘要:
In one embodiment, systems and methods are disclosed for evaluating autonomous driving vehicle (ADV) driving decisions. A driving scenario is selected, such as a route or destination or type of driving condition. ADV planning and control modules are turned off and do not control the ADV. As a user drives the ADV, sensors detect and periodically log a plurality of objects external to the ADV. Driving control inputs of the human driver are also logged periodically. An ADV driving decision module generates driving decisions with respect to each object detected by the sensors. The ADV driving decisions are logged, but are not used to control the ADV. An ADV driving decision is identified in the logs, and a corresponding human driving decision is extracted, graded, and compared to the ADV driving decision. The ADV driving decision can be graded using the logs and graded human driving decision.
摘要:
Described is a system and method for providing an autonomous driving control mechanism in response to an emergency handling event using an emergency (or backup) control system. For example, in certain conditions such as a hardware or software failure, proper functioning of an autonomous driving control system may become compromised. Accordingly, the system may switch to an emergency decision system to continue to provide autonomous driving control functionality. In addition, the emergency decision system may switch to rules and/or a decision algorithm that prioritizes collision avoidance or safety concerns such as injury or fatality prevention in response to the emergency handling event.
摘要:
In one embodiment, systems and methods are disclosed for a planning-driven framework for an autonomous driving vehicle (ADV) driving decision system. Driving decisions are classified into at least seven categories, including: conservative decision, aggressive decision, conservative parameters, aggressive parameters, early decision, late decision, and non-decision problem. Using the outputs of an ADV decision planning module, an ADV driving decision problem is identified, categorized, and diagnosed. A local driving decision improvement can be determined and executed in a short time frame on the ADV. For a long term solution, if needed, the driving decision problem can be uploaded to an analytics server. The driving decision problems from a large plurality of ADVs can be aggregated and analyzed for improving the ADV decisions system for all ADVs.
摘要:
In one embodiment, an image analysis is performed on an image captured using a camera mounted on an autonomous vehicle, the image representing an exterior environment of an autonomous vehicle. Localization information surrounding the autonomous vehicle is obtained at a point in time when the image is captured. A perception of an audience external to the autonomous vehicle is determined based on the image analysis and the localization information. One or more content items are received from one or more content servers over a network in response to the perception of the audience. A first content item selected from the one or more content items is displayed on a display device mounted on an exterior surface of the autonomous vehicle.
摘要:
Driving statistics of an autonomous vehicle are collected. The driving statistics include driving commands issued at different points in time and route selection information of one or more routes while the autonomous vehicle was driven in a manual driving mode by one or more users. For each user of the autonomous vehicle, one or more user driving behaviors and preferences of the user are determined from at least the driving statistics for predetermined driving scenarios. One or more driving profiles for the user are generated based on the determined user behaviors and preferences under the driving scenarios, where the driving profiles are utilized to control the autonomous vehicle under similar driving scenarios when the user is riding in the autonomous vehicle that operates in an autonomous driving mode.