Gm Cruise Holdings LLC

Diego Plascencia-Vega

Nestor Grace

Dogan Gidon

Feng Tian

Geoffrey Louis Chi-Johnston

Spyros Maniatopoulos

Seunghyun Min

Lei Huang

Christopher Brian Roland

Laura Athena Freeman

Mohamed Mostafa Elshenawy

Hooman Barekatain

Daniel Tien

Srishti Iyer Koduvayur

Ou Jin

Clifton Trigg Hutchinson, Jr

The present technology is directed to training and using a machine learning model to predict a likelihood of a counterfactual safety critical event in autonomous vehicle (AV) driving in a projected scenario occurring after a human takes over control of an AV. An AV management system can identify driving data collected from periods around an occurrence of a human take over event where a human takes over control of an AV. The AV management system can project a scenario that would have resulted if the human did not take over control of the AV based on the driving data and output a counterfactual safety score for the projected scenario. The counterfactual safety score can indicate a probability of a counterfactual collision between the AV and the at least one object in the projected scenario.

Safety measurement for a counterfactual risk in autonomous vehicle driving

A method includes using sensory data produced by at least one onboard sensor of a witness vehicle to predict an imminent collision in an environment of the witness vehicle, the predicted imminent collision involving at least one participant vehicle; and alerting the least one participant vehicle to the predicted imminent collision, wherein the alerting is performed by the witness vehicle and prompts the at least one participant vehicle to perform at least one action to mitigate the predicted imminent collision.

Coordinated vehicle collision avoidance system

A method is described and includes subsequent to an autonomous vehicle becoming immobilized, initiating a local assistance request; subsequent to the initiating, receiving local assistance input from a passenger of the autonomous vehicle; and using the local assistance input to determine an action to be taken by the autonomous vehicle to mobilize the autonomous vehicle.

Local assistance for autonomous vehicle-enabled rideshare service

Systems, methods, and computer-readable media are provided for analyzing a traffic infrastructure element, determining reflectivity information of the traffic infrastructure element based on the analyzing of the traffic infrastructure element, comparing the reflectivity information of the traffic infrastructure element with semantic map information of the traffic infrastructure element, and providing instructions to an autonomous vehicle based on the comparing of the reflectivity information of the traffic infrastructure element with the semantic map information of the traffic infrastructure element.

Utilization of reflectivity to determine changes to traffic infrastructure elements

The present technology is directed to training and the use of a machine learning model to measure the safety of an autonomous vehicle (AV) driving in simulation. An AV management system can run a simulation of an AV autonomously piloting itself and collect simulation driving data. Further, the AV management system can parse the simulation driving data into kinematic and semantic environmental features and output a simulation safety score of the simulation based on the kinematic and semantic environmental features. The simulation safety score indicates a probability of a safety critical event such as a collision or a near-miss between the AV and the at least one simulated object in the simulation.

Safety measurement of autonomous vehicle driving in simulation

The subject disclosure relates to solutions for reducing or eliminating motion sickness experienced by a vehicle occupant/passenger. In some aspects, a process of the disclosed technology includes steps for collecting motion data associated with a vehicle using one or more environmental sensors, tracking eye movements of a user within a cabin of the vehicle, processing the motion data and the eye movements to identify a motion event, and generating a motion compensation signal based on the motion event. Systems and machine-readable media are also provided.

Adaptive adjustments to visual media to reduce motion sickness

The disclosed technology provides solutions for implementing dynamic autonomous vehicle (AV) dispatch services. A process of the disclosed technology can include steps for receiving a dispatch request from a mobile device associated with a user, wherein the dispatch request comprises a first pick-up location associated with the user, dispatching a first autonomous vehicle (AV) to the first pick-up location in response to the dispatch request, and automatically receiving an updated location of the mobile device associated with the user. In some aspects, the process can further include steps for determining a second pick-up location based on a change between the first pick-up location and the updated location, and transmitting an updated dispatch request based on the updated location of the mobile device. Systems and machine-readable media are also provided.

Adaptive dispatch and routing of autonomous vehicles based on threshold distances

Particular embodiments described herein provide for a system and method to help enable a towing vehicle. In an example, the system can identify a location of the disabled vehicle, deploy the towing vehicle to the location of the disabled vehicle, where the towing vehicle uses sensor data from a sensor suite and a perception module to navigate to the location of the disabled vehicle, and use the towing vehicle to tow the disabled vehicle to a new location.

System and method to help enable autonomous towing vehicle

An autonomous vehicle (AV) uses an authentication system to verify that a person on the street attempting to control behavior of the AV is authorized to do so. An authorized person (e.g., a construction worker or a police officer) has an associated beacon that provides a beacon signal, such as a visual symbol or wireless signal. The AV perceives the beacon signal and transmits it to the authentication system. The authentication system looks up the beacon signal in a database and retrieves conditions associated with the beacon signal. If the authentication system and/or AV confirms that the beacon signal is in the database, and the conditions under which the person associated with the beacon signal is authorized to control the AV are met, the AV follows instructions from the person.

Verifying authorized personnel for interaction with autonomous vehicles

The disclosed technology provides solutions for improving the operational efficiency and safety of autonomous vehicles (AVs). In some implementations, the disclosed technology encompasses methods for performing vehicle clustering or platooning, for example, that can include steps for computing navigation routes for each of a plurality of autonomous vehicles (AVs), identifying a route overlap for a first AV and a second AV selected from among the plurality of AVs, and transmitting a clustering instruction to the first AV and the second AV based on the route overlap, wherein the clustering instruction is configured to cause the first AV and the second AV to initiate a clustering configuration. Systems and machine-readable media are also provided.

Coordinated multi-vehicle routing

The present technology utilizes vehicles in a fleet of vehicles to record weather data samples at many locations in a service area. Each vehicle in the fleet becomes a weather station that can record weather data at many locations and frequently. The weather data can be used to make intelligent decisions regarding fleet management.

Highly localized weather data recorded by vehicles in a fleet

Collaborative perception is based on recognition that a fleet of AVs and stationary infrastructure objects equipped with sensors may be configured to communicate with one another in sharing their sensor data, thus benefiting from collaborative perception, rather than being limited to their individual perception. Three specific scenarios of collaborative perception are disclosed. The first scenario relates to two AVs in the vicinity of one another exchanging complexity scores indicative of their respective environments. The second scenario relates to an AV detecting that it has a blind spot and seeking other AVs or infrastructure objects to provide information indicative of the environment in the blind spot. The third scenario relates to providing infrastructure objects equipped with sensors in appropriate locations so that, when an AV is in the vicinity of such objects, the AV may receive information from their sensors.

Growing community of inventors

San Francisco, CA, United States of America

Diego Plascencia-Vega