Motional Ad LLC

You Hong Eng

James Guo Ming Fu

Scott D Pendleton

Yu Pan

Jiong Yang

Zhiliang Chen

Pan Yu

Provided are methods for scalable and realistic camera blockage dataset generation, which can include generating synthetic images depicting a blockage on or near an imaging sensor. The synthetic images may be created by combining one or more chroma key-extracted partial blockage image with one or more background images, the combination of which can provide a scalable blockage dataset. Metadata for each synthetic image can be generated along with the synthetic image, by annotating the portion of the synthetic image represented by the chroma key-extracted partial blockage image as constituting blockage. The synthetic images can be used to increase the accuracy of machine learning models trained to identify blockage by increasing the volume of data available for such training.

Scalable and realistic camera blockage dataset generation

Embodiments for operational envelope detection (OED) with situational assessment are disclosed. In some embodiments, a method comprises: determining at least one current or future constraint for a trajectory of a vehicle in an environment that is associated with the vehicle becoming immobile for an extended period of time; determining a stopping-reason for immobility of the vehicle based on determining the at least one current or future constraint for the trajectory of the vehicle in the environment; identifying a timeout threshold based on the stopping-reason, wherein the timeout threshold is an amount of time a planning system of the vehicle will wait before initiating at least one remedial action to address the immobility; identifying that the timeout threshold is satisfied; and initiating the at least one remedial action for the vehicle based on the identifying that the timeout threshold is satisfied.

Immobility detection within situational context

Embodiments for operational envelope detection (OED) with situational assessment are disclosed. Embodiments herein relate to an operational envelope detector that is configured to receive, as inputs, information related to sensors of the system and information related to operational design domain (ODD) requirements. The OED then compares the information related to sensors of the system to the information related to the ODD requirements, and identifies whether the system is operating within its ODD or whether a remedial action is appropriate to adjust the ODD requirements based on the current sensor information. Other embodiments are described and/or claimed.

Operational envelope detection with situational assessment

Provided are methods for learning to identify safety-critical scenarios for autonomous vehicles. First state information representing a first state of a driving scenario is received. The information includes a state of a vehicle and a state of an agent in the vehicle's environment. The first state information is processed with a neural network to determine at least one action to be performed by the agent, including a perception degradation action causing misperception of the agent by a perception system of the vehicle. Second state information representing a second state of the driving scenario is received after performance of the at least one action. A reward for the action is determined. First and second distances between the vehicle and the agent are determined and compared to determine the reward for the at least one action. At least one weight of the neural network is adjusted based on the reward.

Growing community of inventors

Singapore, Singapore

You Hong Eng