Abstract: Trajectory generation for controlling motion or other behavior of an autonomous vehicle may include alternately determining a candidate action and predicting a future state based on that candidate action. The technique may include determining a cost associated with the candidate action that may include an estimation of a transition cost from a current or former state to a next state of the vehicle. This cost estimate may be a lower bound cost or an upper bound cost and the tree search may alternately apply the lower bound cost or upper bound cost exclusively or according to a ratio or changing ratio. The prediction of the future state may be based at least in part on a machine-learned model's classification of a dynamic object as being a reactive object or a passive object, which may change how the dynamic object is modeled for the prediction.

Abstract: Techniques for accurately predicting and avoiding collisions with objects detected in an environment of a vehicle are discussed herein. A vehicle computing device can implement a model to output data indicating costs for potential intersection points between the object and the vehicle in the future. The model may employ a control policy and a time-step integrator to determine whether an object may intersect with the vehicle, in which case the techniques may include predicting vehicle actions by the vehicle computing device to control the vehicle.

Abstract: Techniques for accurately predicting and avoiding collisions with objects detected in an environment of a vehicle are discussed herein. A vehicle computing device can implement a model to output data indicating costs for potential intersection points between the object and the vehicle in the future. The model may employ a control policy and a time-step integrator to determine whether an object may intersect with the vehicle, in which case the techniques may include predicting vehicle actions by the vehicle computing device to control the vehicle.

Abstract: A vehicle computing system may implement techniques to determine relevance of objects detected in an environment to a vehicle operating in the environment (e.g., whether an object could potentially impact the vehicle's ability to safely travel). The techniques may include determining an initial location and trajectory associated with a detected object and determining whether the detected object may intersect a path polygon (e.g., planned path with a safety buffer) of the vehicle. A path intersection may include the detected object intersecting the path polygon or sharing a road segment with the vehicle at a substantially similar height as the vehicle (e.g., on a similar plane). Based on a determination that the detected object does not intersect the planned path of the vehicle, the vehicle computing system may determine that the detected object is irrelevant to the vehicle and may disregard the detected object in vehicle control planning considerations.

Abstract: Trajectory generation for controlling motion or other behavior of an autonomous vehicle may include alternately determining a candidate action and predicting a future state based on that candidate action. The technique may include determining a cost associated with the candidate action that may include an estimation of a transition cost from a current or former state to a next state of the vehicle. This cost estimate may be a lower bound cost or an upper bound cost and the tree search may alternately apply the lower bound cost or upper bound cost exclusively or according to a ratio or changing ratio. The prediction of the future state may be based at least in part on a machine-learned model's classification of a dynamic object as being a reactive object or a passive object, which may change how the dynamic object is modeled for the prediction.

Abstract: Controlling autonomous vehicles requires accurate information about how entities behave in an environment with respect to one another. In an example, a data structure is used to associate entities in an environment of the vehicle with the vehicle and/or with each other. For example, associations between entities can be based on locations of the entities relative to each other and/or relative to segments of a drivable surface. Information about associations between the vehicle and/or entities in the environment may be used to identify entities that may influence travel of the vehicle and/or other entities and, in some implementations, vehicle controls can be generated based on these relevant entities.

Abstract: Techniques for accurately predicting and avoiding collisions with objects detected in an environment of a vehicle are discussed herein. A vehicle computing device can implement a model to output data indicating costs for potential intersection points between the object and the vehicle in the future. The model may employ a control policy and a time-step integrator to determine whether an object may intersect with the vehicle, in which case the techniques may include predicting vehicle actions by the vehicle computing device to control the vehicle.

Abstract: Controlling autonomous vehicles requires accurate information about how entities behave in an environment with respect to one another. In an example, a data structure is used to associate entities in an environment of the vehicle with the vehicle and/or with each other. For example, associations between entities can be based on locations of the entities relative to each other and/or relative to segments of a drivable surface. Information about associations between the vehicle and/or entities in the environment may be used to identify entities that may influence travel of the vehicle and/or other entities and, in some implementations, vehicle controls can be generated based on these relevant entities.

Abstract: Techniques for determining gaps for performing lane change operations are described. A first region in an environment of a vehicle can be determined. The first region can be associated with a first time period through which the vehicle is unable to travel and can correspond to a constraint space. A second region of the environment can be determined. The second region can be associated with a second time period and can correspond to a configuration space. A gap in the environment can be determined based on a portion of the configuration space that is exclusive of the constraint space. A trajectory can be determined based on the gap. The trajectory can be associated with performing a lane change operation and can be associated with a cost. The vehicle can be controlled to perform the lane change operation based at least in part on the trajectory and the cost.

Abstract: Techniques are discussed for controlling a vehicle, such as an autonomous vehicle, to navigate a junction in an environment. In some cases, the techniques can be used to navigate a turn at the junction or traverse through the junction. Operations include the vehicle detecting a stop signal and preparing the vehicle to stop at a location associated with the junction. The vehicle can determine a time to execute a maneuver and a visibility distance that a sensor can observe in the environment. A speed of the vehicle to execute the maneuver can be determined based on the time to execute the maneuver and the visibility distance.

Abstract: According to one aspect, an autonomous all-terrain vehicle (ATV) may include a controller receiving a command associated with autonomous driving and monitoring components of the autonomous ATV, a location unit determining a current location associated with the autonomous ATV and a destination location associated with the command, a navigation module determining one or more driving parameters based on map data associated with a path from the current location to the destination location, and a safety logic implementing an emergency stop based on an error determined by the controller. The controller may monitor the location unit and the navigation module for the error.

Abstract: This application describes locating objects in an environment, such as a mapped region. In an example, a location of an entity on a drivable surface can include querying an axis-aligned bounding box (AABB) tree to determine a segment of the drivable surface including the location. In some examples, the location can be further determined within the segment of the drivable surface. For instance, the segment of the drivable surface may be partitioned into a plurality of polygons, and the polygons can be searched to determine a lane segment in the road segment associated with the entity.

Abstract: Techniques are discussed for controlling a vehicle, such as an autonomous vehicle, to navigate a junction in an environment. In some cases, the techniques can be used to navigate a turn at the junction or traverse through the junction. Operations include the vehicle detecting a stop signal and preparing the vehicle to stop at a location associated with the junction. The vehicle can determine a time to execute a maneuver and a visibility distance that a sensor can observe in the environment. A speed of the vehicle to execute the maneuver can be determined based on the time to execute the maneuver and the visibility distance.

Abstract: According to one aspect, an autonomous all-terrain vehicle (ATV) may include a controller receiving a command associated with autonomous driving and monitoring components of the autonomous ATV, a location unit determining a current location associated with the autonomous ATV and a destination location associated with the command, a navigation module determining one or more driving parameters based on map data associated with a path from the current location to the destination location, and a safety logic implementing an emergency stop based on an error determined by the controller. The controller may monitor the location unit and the navigation module for the error.