Gm Cruise Holdings LLC

Sarah M Rizk

Charles Bruce Matlack

Patrick Tyler Haas

Chen Xie

Michael Rusignola

Yanni Cao

Christopher Brian Roland

Jaimin Liang-Yan Hsu

Varun Bharadwaj

Linsen Chong

Zsolt Parnaki

Riccardo Pavesi

Joseph James Reid

Luke Pulaski

Rahul Narula

Chung Ngan Ho

Anmol Garg

John Habeb Khawam

Anusha Sridhar Rao

Zachary Wright Garcia

A methodology is described for determining a time for responding to an initial encounter by a vehicle with a map error in a map segment, wherein the initial encounter is detected by a detector. A method includes identifying an error type associated with the map error, wherein the error type is one of a first error type and a second error type; determining at least one additional factor associated with the initial encounter; determining a response time for the map error based on the error type and the at least one additional factor; and initiating a mitigating action in response to the initial encounter within the response time, wherein the response time comprises an amount of time from the initial encounter with the map error to a time at which a mitigating action should be taken.

Methodology for establishing time of response to map discrepancy detection event

A map database stores data describing a set of connected roadways, each having one or more lanes. A coverage system selects lanes from the map database along which AVs can stop, such as parking lanes. The coverage system generates buffer regions for each of the stopping lanes, where each buffer region includes an area within a given distance of the respective lane. The coverage system combines the buffer regions to generate a coverage area, and provides a display of the coverage area overlayed over a map of roads corresponding to the coverage area.

Service area coverage for autonomous vehicle fleets

Service disruption prevention through monitoring dynamic geofencing is disclosed. The present disclosure seeks to prevent (or drastically reduce the probability) mass vehicle recovery events due to fragile portions of the map. Tooling is used to actively monitor chokepoints and new avoidance areas. Comprised by the operational design domain (ODD), geofences are actively changed in response to the state of the chokepoints and avoidance areas. Varying states can be assigned to a plurality of geofences within the ODD, for example, if a geofence reaches a critical state, one or more areas can be cut off from the ODD.

Service disruption prevention through dynamic geofences

Systems, methods, and computer-readable media are provided for determining operator availability to provide remote assistance to an autonomous vehicle, determining which of a first plurality of routes will provide a positive ride experience based on the operator availability, and selecting a route of the first plurality of routes for a user based on the determining of which of the first plurality of routes will provide a positive ride experience.

Joint optimization of robotic vehicle routing for ride quality, safety, and operator demand

A map database stores data describing a set of connected roads each having one or more lanes, each having one or more lanes. The map database further stores data describing at an avoidance area comprising an area in the map database that an autonomous vehicle (AV) avoids traversing. A routability system determines at least one lane that can be accessed by the AV if the AV traverses the avoidance area, and generates a restored coverage area corresponding to the at least one lane. The restored coverage area corresponds to an area of restored coverage provided by the AV traversing the avoidance area. The routability system computes a score based on the restored coverage area, the score indicating an impact of restoring access by the AV to the avoidance area.

Identifying high-priority avoidance areas in maps for routing autonomous vehicles

Growing community of inventors

San Francisco, CA, United States of America

Sarah M Rizk