Abstract: A system for providing remote assistance to an autonomous vehicle is disclosed herein. The system includes at least one remote assistance button configured to be selectively activated to initiate remote assistance for the autonomous vehicle. Each remote assistance button corresponds to a dedicated remote assistance function for the autonomous vehicle. For example, the system can include remote assistance buttons for causing the autonomous vehicle to stop, decelerate, or pull over. The system includes a controller configured to detect activation of the remote assistance button(s) and to cause remote assistance to be provided to the autonomous vehicle in response to the activation. For example, the autonomous vehicle may perform an action corresponding to the activated button with input assistance from the controller but without the system taking over control of the autonomous vehicle.

Abstract: An autonomous vehicle is operated using a main autonomy system that analyzes data collected by a sensor system of the autonomous vehicle to determine a trajectory of travel of the autonomous vehicle, and wherein the main autonomy system provides instructions to a propulsion system of the autonomous vehicle to cause the propulsion system to navigate the autonomous vehicle according to the trajectory. In response to determining that navigating the autonomous vehicle according to the trajectory is likely to result in collision, instructions are provided from a parallel autonomy system to the propulsion system to cause the autonomous vehicle to avoid collision. In response to detecting a fault in the main autonomy system, control of the propulsion system is provided from the main autonomy system to a failover autonomy system, wherein the failover autonomy system is configured to override the propulsion system.

Abstract: A system for providing remote assistance to an autonomous vehicle is disclosed herein. The system includes at least one remote assistance button configured to be selectively activated to initiate remote assistance for the autonomous vehicle. Each remote assistance button corresponds to a dedicated remote assistance function for the autonomous vehicle. For example, the system can include remote assistance buttons for causing the autonomous vehicle to stop, decelerate, or pull over. The system includes a controller configured to detect activation of the remote assistance button(s) and to cause remote assistance to be provided to the autonomous vehicle in response to the activation. For example, the autonomous vehicle may perform an action corresponding to the activated button with input assistance from the controller but without the system taking over control of the autonomous vehicle.

Abstract: An autonomous vehicle is operated using a main autonomy system that analyzes data collected by a sensor system of the autonomous vehicle to determine a trajectory of travel of the autonomous vehicle, and wherein the main autonomy system provides instructions to a propulsion system of the autonomous vehicle to cause the propulsion system to navigate the autonomous vehicle according to the trajectory. In response to determining that navigating the autonomous vehicle according to the trajectory is likely to result in collision, instructions are provided from a parallel autonomy system to the propulsion system to cause the autonomous vehicle to avoid collision. In response to detecting a fault in the main autonomy system, control of the propulsion system is provided from the main autonomy system to a failover autonomy system, wherein the failover autonomy system is configured to override the propulsion system.

Abstract: Methods and systems for object detection using multiple sensors are described herein. In an example embodiment, a vehicle's computing device may receive sensor data frames indicative of an environment at different rates from multiple sensors. Based on a first frame from a first sensor indicative of the environment at a first time period and a portion of a first frame that corresponds to the first time period from a second sensor, the computing device may estimate parameters of objects in the vehicle's environment. The computing device may modify the parameters in response to receiving subsequent frames or subsequent portions of frame of sensor data from the sensors even if the frames arrive at the computing device out of order. The computing device may provide the parameters of the objects to systems of the vehicle for object detection and obstacle avoidance.

Abstract: A computing device may identify an object in an environment of a vehicle and receive a first three-dimensional (3D) point cloud depicting a first view of the object. The computing device may determine a reference point on the object in the first 3D point cloud, and receive a second 3D point cloud depicting a second view of the object. The computing device may determine a transformation between the first view and the second view, and estimate a projection of the reference point from the first view relative to the second view based on the transformation so as to trace the reference point from the first view to the second view. The computing device may determine one or more motion characteristics of the object based on the projection of the reference point.

Abstract: Methods and systems for object detection using multiple sensors are described herein. In an example embodiment, a vehicle's computing device may receive sensor data frames indicative of an environment at different rates from multiple sensors. Based on a first frame from a first sensor indicative of the environment at a first time period and a portion of a first frame that corresponds to the first time period from a second sensor, the computing device may estimate parameters of objects in the vehicle's environment. The computing device may modify the parameters in response to receiving subsequent frames or subsequent portions of frame of sensor data from the sensors even if the frames arrive at the computing device out of order. The computing device may provide the parameters of the objects to systems of the vehicle for object detection and obstacle avoidance.

Abstract: Methods and systems for object detection using multiple sensors are described herein. In an example embodiment, a vehicle's computing device may receive sensor data frames indicative of an environment at different rates from multiple sensors. Based on a first frame from a first sensor indicative of the environment at a first time period and a portion of a first frame that corresponds to the first time period from a second sensor, the computing device may estimate parameters of objects in the vehicle's environment. The computing device may modify the parameters in response to receiving subsequent frames or subsequent portions of frame of sensor data from the sensors even if the frames arrive at the computing device out of order. The computing device may provide the parameters of the objects to systems of the vehicle for object detection and obstacle avoidance.

Abstract: An example method may include receiving a first set of points based on detection of an environment of an autonomous vehicle during a first time period, selecting a plurality of points from the first set of points that form a first point cloud representing an object in the environment, receiving a second set of points based on detection of the environment during a second time period which is after the first period, selecting a plurality of points from the second set of points that form a second point cloud representing the object in the environment, determining a transformation between the selected points from the first set of points and the selected points from the second set of points, using the transformation to determine a velocity of the object, and providing instructions to control the autonomous vehicle based at least in part on the velocity of the object.

Abstract: A computing device may identify an object in an environment of a vehicle and receive a first three-dimensional (3D) point cloud depicting a first view of the object. The computing device may determine a reference point on the object in the first 3D point cloud, and receive a second 3D point cloud depicting a second view of the object. The computing device may determine a transformation between the first view and the second view, and estimate a projection of the reference point from the first view relative to the second view based on the transformation so as to trace the reference point from the first view to the second view. The computing device may determine one or more motion characteristics of the object based on the projection of the reference point.