Abstract: Categorizing driving behaviors of other road users includes maintaining a first history of first lateral-offset values of a road user with respect to a center line of a lane of a road; determining a first pattern based on the first history of the first lateral-offset values; determining a driving behavior of the road user based on the first pattern; and autonomously performing, by a host vehicle, a driving maneuver based on the driving behavior of the road user. The first history can be maintained for a predetermined period of time. An apparatus includes a processor that is configured to track a trajectory history of a road user; determine, based on the trajectory history, a driving behavior of the road user; and transmit a notification of the driving behavior.

Abstract: Detecting prediction errors includes detecting a road user; determining respective predicted data for the road user; storing, in a data structure, the respective predicted data; storing, in the data structure, actual data of the road user; obtaining an average prediction displacement error using at least one of the actual data and at least two corresponding respective predicted data; and determining a prediction accuracy based on the average prediction displacement error. Detecting map errors includes detecting a road user; storing, in a data structure, actual data of the road user; storing, in the data structure, map data corresponding to the actual data; obtaining an average map displacement error based on a comparison of at least some of the actual data and corresponding at least some map data; and determining a map accuracy based on the average map displacement error.

Abstract: A proactive pedal algorithm is used to modify an accelerator pedal map to ensure the deceleration when the accelerator pedal is released matches driver expectation. Modifying the accelerator pedal map provides the driver of a vehicle the sensation that the vehicle resists moving when travelling in dense scenes with potentially high deceleration requirements and coasts easily in scenes with low deceleration requirements. The accelerator pedal map is modified based on a scene determination to classify other remote vehicles as in-lane, neighbor-lane, or on-coming.

Abstract: A reactive pedal algorithm is used to modify an accelerator pedal output (APO)-to-torque conversion to produce more deceleration for the same accelerator pedal position. Modifying the APO-to-torque conversion provides the driver of a vehicle the sensation that the vehicle is resisting approaching closer to a lead vehicle. The APO-to-torque conversion is modified based on a scene determination to classify vehicles as in-lane, neighbor-lane, or on-coming. Lane change assist methods and systems are used to modify the APO-to-torque conversion range based on a lead vehicle, a neighbor vehicle, or both.

Abstract: Route planning for a hybrid electric vehicle (HEV) includes obtaining a route between an origin and a destination, where the route is optimized for at least one of a noise level or energy consumption of an engine of the HEV that is used to charge a battery of the HEV, and where the route comprises respective engine activation actions for at least some segments of the route; and controlling the HEV to follow the segments of the route and to activate the engine according to the respective engine activation actions.

Abstract: Activating an engine of a HEV to charge a battery includes obtaining a first GPS trace from a first trip of the HEV along a first route, where the first GPS trace includes first trace metadata; obtaining a second GPS trace from a second trip, where the second GPS trace includes second trace metadata; adding, to a navigation map, an aggregation of the first trace metadata and the second trace metadata for edges of the navigation map; using the navigation map to obtain an activation action of the engine, where the activation action is selected from a set that includes a first activation action of turning the engine on and a second activation action of turning the engine off; and activating the engine according to the activation action, where activating the engine using the first activation action causes the engine to turn on to charge the battery of the HEV.

Abstract: A system includes a battery, an engine, and a processor. The processor is configured to plan, according to a model, an activation action of the engine of a vehicle for a next road segment subsequent to a current road segment; and activate, for the next road segment, the engine according to the activation action. The model includes a state space that includes a navigation map, which includes the current road segment of the vehicle, a current charge level of the battery, and whether the engine is currently on or off. The activation action is selected from a set comprising a first action to turn on the engine to charge the battery and a second action to turn off the engine.

Abstract: An apparatus for traveling through a transportation network performs a method including generating a display that includes a geographical area about a starting location for route assistance through the transportation network and a virtual vehicle at the starting location, and forming a virtual path for the route assistance using the virtual vehicle. The virtual path includes a first portion obtained from advancing the virtual vehicle from the starting location while an autonomous vehicle (AV) is at the starting location and a second portion obtained from, after the virtual vehicle departs from the starting location, extrapolating from the virtual vehicle through the geographical area to a stopping location or an ending location of the route assistance. Points along the virtual path are continually transmitted to a trajectory planner of the AV while the virtual vehicle advances through the geographical area, and the trajectory planner generates a route for the AV conforming to the virtual path.

Abstract: Systems and methods for optimizing traffic flow through an intersection are disclosed. In an embodiment, the method includes receiving positional data indicating a current location of a first vehicle intending to pass through the intersection, receiving directional data indicating an intended direction of the first vehicle through the intersection from the current location, determining, based on the positional data and the directional data, whether an intended path of the first vehicle through the intersection interferes with an alternative path through the intersection, and adjusting a traffic signal at the intersection to decrease an amount of time to pass through the intersection via the alternative path.

Abstract: Resolving an exception situation in autonomous driving includes receiving an assistance request to resolve the exception situation from an autonomous vehicle (AV); identifying a solution to the exception situation; forwarding the solution to a tele-operator; receiving a request for playback data from the tele-operator; receiving, from the AV, the playback data; and obtaining, from the tele-operator, a validated solution based on the tele-operator using the playback data. The playback data includes snapshots ni of data related to autonomous driving stored at the AV at respective consecutive times ti, for i=1, . . . , N.

Abstract: A method for performing a pickup/drop-off at a location includes providing, to an autonomous vehicle (AV), a parameter value of a parameter associated with the pickup/drop-off. The AV executes the pickup/drop-off according to the parameter value. After the pickup/drop-off is executed, feedback related to the parameter is received from a customer and from a tele-operator. The method also includes identifying other world objects present at the location during the pickup/drop-off and generating an optimized parameter value for executing the pickup/drop-off using the parameter value, the customer feedback, the tele-operator feedback, and other world objects.

Abstract: A first method includes identifying an occlusion in the vehicle transportation network; identifying, for a first world object that is on a first side of the occlusion, a visibility grid on a second side of the occlusion; and altering a driving behavior of the first vehicle based on the visibility grid. The visibility grid is used in determining whether other world objects exist on the second side of the occlusion. A second includes identifying a first trajectory of a first world object in the vehicle transportation network; identifying a visibility grid of the first world object; identifying, using the visibility grid, a second world object that is invisible to the first world object; and, in response to determining that the first world object is predicted to collide with the second world object, alerting at least one of the first world object or the second world object.

Abstract: Object avoidance by an autonomous vehicle (AV) is disclosed. A method includes detecting a first object along a coarse driveline of a drivable area of the AV; receiving a predicted path of the first object; determining, based on the predicted path of the first object, an adjusted drivable area; and determining a trajectory of the AV through the adjusted drivable area. A system includes a trajectory planner configured to detect a first object along a coarse driveline of a drivable area of the AV; receive a predicted path of the first object; determine, based on the predicted path of the first object, an adjusted drivable area; and determine a trajectory of the AV through the adjusted drivable area.

Abstract: A method for world objects tracking and prediction by an autonomous vehicle includes receiving, from sensors of the AV, a first observation data; associating the first observation data with a first world object; determining hypotheses for the first world object; determining a respective hypothesis likelihood of each of the hypotheses indicating a likelihood that the first world object follows the intention; determining, for at least one hypothesis of the hypotheses, a respective state; and in response to a query, providing a hypothesis of the hypotheses based on the respective hypothesis likelihood of each of the hypotheses. A hypothesis corresponds to an intention of the first world object and the respective state includes predicted positions of the first world object.

Abstract: Exception handing, such as of obstruction situations, by an autonomous vehicle (AV) is disclosed. A method includes identifying an exception situation; identifying a risk associated with autonomously resolving the exception situation; and in response to the risk exceeding a risk threshold, initiating a request for assistance from a tele-operator, and halting for the tele-operator to respond to the request; and receiving a response from the tele-operator.

Abstract: An apparatus for traveling through a transportation network performs a method including generating a display that includes a geographical area about a starting location for route assistance through the transportation network and a virtual vehicle at the starting location, and forming a virtual path for the route assistance using the virtual vehicle. The virtual path includes a first portion obtained from advancing the virtual vehicle from the starting location while an autonomous vehicle (AV) is at the starting location and a second portion obtained from, after the virtual vehicle departs from the starting location, extrapolating from the virtual vehicle through the geographical area to a stopping location or an ending location of the route assistance. Points along the virtual path are continually transmitted to a trajectory planner of the AV while the virtual vehicle advances through the geographical area, and the trajectory planner generates a route for the AV conforming to the virtual path.

Abstract: World objects tracking and prediction by an autonomous vehicle is disclosed. A method includes receiving, from sensors of the AV, a first observation data; associating the first observation data with a first world object; determining hypotheses for the first world object, wherein a hypothesis corresponds to an intention of the first world object; determining a respective hypothesis likelihood of each of the hypotheses indicating a likelihood that the first world object follows the intention; determining, for at least one hypothesis of the hypotheses, a respective state, wherein the respective state comprises predicted positions of the first world object; and in response to a query, providing a hypothesis of the hypotheses based on the respective hypothesis likelihood of each of the hypotheses.

Abstract: A method for responding to a public safety alert includes receiving an indication of the public safety alert, wherein the public safety alert comprising a description of a wanted road user; identifying, using sensors of an autonomous vehicle (AV) and in response to the public safety alert, road users; and, in response to determining that an identified road user matches the wanted road user, notifying an authority of the match. A method for road incident reporting by an AV includes identifying road users based on sensor data of the AV; associating respective hypotheses with each of the road users; and, in response to determining that a threshold number of the road users are not proceeding according to at least one of the respective hypotheses, sending a notification indicating a potential traffic issue at a zone of the road users.

Abstract: A method for contingency planning for an autonomous vehicle (AV) includes determining a nominal trajectory for the AV; detecting a hazard object that does not intrude into a path of the AV at a time of the detecting the hazard object; determining a hazard zone for the hazard object; determining a time of arrival of the AV at the hazard zone; determining a contingency trajectory for the AV; controlling the AV according to the contingency trajectory; and, in response to the hazard object intruding into the path of the AV, controlling the AV to perform a maneuver to avoid the hazard object. The contingency trajectory includes at least one of a lateral contingency or a longitudinal contingency. The contingency trajectory is determined using the time of arrival of the AV at the hazard zone.

Abstract: A method for pickup/drop-off at a location includes providing, to a first autonomous vehicle (AV), a parameter value of a parameter associated with the pickup/drop-off; executing, by the first autonomous vehicle (AV), the pickup/drop-off according to the parameter value; receiving a customer feedback related to the parameter; receiving a tele-operator feedback related to the parameter; identifying other world objects at the location; and generating an optimized parameter value for executing the pickup/drop-off. Generating the optimized parameter value uses the parameter value, the customer feedback, the tele-operator feedback, and other world objects.