Abstract: Methods and systems for improved simultaneous localization and mapping based on 3-D LIDAR image data are presented herein. In one aspect, LIDAR image frames are segmented and clustered before feature detection to improve computational efficiency while maintaining both mapping and localization accuracy. Segmentation involves removing redundant data before feature extraction. Clustering involves grouping pixels associated with similar objects together before feature extraction. In another aspect, features are extracted from LIDAR image frames based on a measured optical property associated with each measured point. The pools of feature points comprise a low resolution feature map associated with each image frame. Low resolution feature maps are aggregated over time to generate high resolution feature maps.

Abstract: Techniques for determining error models for use in simulations are discussed herein. Ground truth perception data and vehicle perception data can be determined from vehicle log data. Further, objects in the log data can be identified as relevant objects by signals output by a planner system or based on the object being located in a driving corridor. Differences between the ground truth perception data and the vehicle perception data can be determined and used to generate error models for the relevant objects. The error models can be applied to objects during simulation to increase realism and test vehicle components.

Abstract: In various examples, systems and methods are disclosed that preserve rich, detail-centric information from a real-world image by augmenting the real-world image with simulated objects to train a machine learning model to detect objects in an input image. The machine learning model may be trained, in deployment, to detect objects and determine bounding shapes to encapsulate detected objects. The machine learning model may further be trained to determine the type of road object encountered, calculate hazard ratings, and calculate confidence percentages. In deployment, detection of a road object, determination of a corresponding bounding shape, identification of road object type, and/or calculation of a hazard rating by the machine learning model may be used as an aid for determining next steps regarding the surrounding environment—e.g., navigating around the road debris, driving over the road debris, or coming to a complete stop—in a variety of autonomous machine applications.

Abstract: A method determines safety-critical traffic scenarios for driver assistance systems and highly automated driving functions for a motor vehicle. A safety-critical traffic scenario has a scenario type, a location determined geographic coordinates, and a safety value. The method includes: recording first data of a vehicle while driving along a route, assigning geographic coordinates to the first data in each case; recording second data for capturing physiological and physical reactions of a driver of a vehicle while driving along the route, assigning geographic coordinates to the second data in each case; transmitting the first and second data to a data evaluation unit; combining the first data and the second data having the same geographic coordinates so that they represent data at a specific geographic location; identifying a scenario for the specific geographic location based on the first and second data; classifying the identified scenario with a difficulty value.

Abstract: An autonomous driving system configured to perform an autonomous driving of a vehicle includes a trigger input request unit configured to perform a trigger input request for requesting a driver of the vehicle to perform a trigger input for causing the vehicle to pass through a target point if the autonomously driving vehicle approaches the target point set in advance and positioned on a traveling route of the vehicle, a trigger input detection unit configured to detect the driver's trigger input, and a vehicle control unit configured to cause the vehicle to pass through the target point if the trigger input is detected, and causes the vehicle to decelerate and stop without passing through the target point if the trigger input is not detected.

Abstract: An on-board sensor system includes: a first sensor configured to detect a situation around a vehicle; a second sensor having a higher angular resolution than the first sensor; an acquisition unit configured to acquire a detection result of the first sensor; and a range decision unit configured to decide, based on the detection result, an observation range to be observed by the second sensor around the vehicle.

Abstract: A vehicle includes a driving device configured to control a speed of the vehicle, a camera configured to detect a surrounding vehicle, and a controller configured to determine the speed of the vehicle. The controller also calculates an image vector variation amount of the surrounding vehicle when the speed of the vehicle is lower than a predetermined speed and calculates a safety distance between the vehicle and a preceding vehicle based on the image vector variation amount of the surrounding vehicle when the image vector variation amount of the surrounding vehicle satisfies a predetermined condition. The controller also controls the driving device to control the speed of the vehicle depending on the calculated safety distance.

Abstract: Systems and methods for controlling the operation of an autonomous vehicle are disclosed herein.

Abstract: An autonomous driving system configured to perform an autonomous driving of a vehicle includes a trigger input request unit configured to perform a trigger input request for requesting a driver of the vehicle to perform a trigger input for causing the vehicle to pass through a target point if the autonomously driving vehicle approaches the target point set in advance and positioned on a traveling route of the vehicle, a trigger input detection unit configured to detect the driver's trigger input, and a vehicle control unit configured to cause the vehicle to pass through the target point if the trigger input is detected, and causes the vehicle to decelerate and stop without passing through the target point if the trigger input is not detected.

Abstract: An Autonomous Vehicle (AV) system, including: a tracking subsystem configured to detect and track relative positioning of another vehicle that is behind or lateral to an AV configured to comply with a safety driving model, and to check a safety driving model compliance status of the other vehicle; and a risk reduction subsystem configured to plan, based on the safety driving model compliance status of the other vehicle, an AV action, wherein if the safety driving model compliance status of the other vehicle is unknown or is known to be non-compliant, the AV action is administration of a safety driving model compliance test to the other vehicle, or is a maneuver by the AV to reduce risk of collision with a leading vehicle positioned in front of the AV.

Abstract: Autonomous vehicle operation with explicit occlusion reasoning may include traversing, by a vehicle, a vehicle transporation network. Traversing the vehicle transportation network can include receiving, from a sensor of the vehicle, sensor data for a portion of a vehicle operational environment, determining, using the sensor data, a visibility grid comprising coordinates forming an unobserved region within a defined distance from the vehicle, computing a probability of a presence of an external object within the unobserved region by comparing the visibility grid to a map (e.g., a high-definition map), and traversing a portion of the vehicle transportation network using the probability. An apparatus and a vehicle are also described.

Abstract: A vehicle sideslip estimation system includes sensors mounted on a vehicle and a kinematic model receiving signals from the sensors to estimate a lateral velocity of the vehicle. A compensated acceleration calculator calculates a compensated lateral acceleration as a measure of conditions that result in a deviation of a measured lateral acceleration. A lateral acceleration calculator determines, based on the compensated lateral acceleration and the measured lateral acceleration, if a lateral acceleration error is larger than a predefined threshold. A filter corrects the estimated lateral velocity of the vehicle when the lateral acceleration error is larger than the predefined threshold.

Abstract: Techniques and methods for performing collision monitoring using error models. For instance, a vehicle may generate sensor data using one or more sensors. The vehicle may then analyze the sensor data using systems in order to determine parameters associated with the vehicle and parameters associated with another object. Additionally, the vehicle may process the parameters associated with the vehicle using error models associated with the systems in order to determine a distribution of estimated locations associated with the vehicle. The vehicle may also process the parameters associated with the object using the error models in order to determine a distribution of estimated locations associated with the object. Using the distributions of estimated locations, the vehicle may determine the probability of collision between the vehicle and the object.

Abstract: A vehicle control device includes a recognizer configured to recognize a surrounding environment including a structure of a road near a vehicle and another vehicle, a deriver configured to derive a predicted probability that the other vehicle will travel in the future along each of routes which are assumed when a plurality of routes along which the other vehicle is able to travel are assumed on a road on which the other vehicle recognized by the recognizer travels, and a travel controller configured to control behavior of the vehicle based on the predicted probability derived by the deriver.

Abstract: Techniques and methods for performing collision monitoring using system data. For instance, a vehicle may generate sensor data using one or more sensors. The vehicle may then analyze the sensor data using systems in order to determine parameters associated with the vehicle and parameters associated with another object. Additionally, the vehicle may determine uncertainties associated with the parameters and then process the parameters using the uncertainties. Based at least in part on the processing, the vehicle may determine a distribution of estimated locations associated with the vehicle and a distribution of estimated locations associated with the object. Using the distributions of estimated locations, the vehicle may determine the probability of collision between the vehicle and the object.

Abstract: A vehicle control system that acquires position information of a vehicle in a driving state of a manually driven state or a remotely operated driven state; that stores a pre-traveled travel route of a vehicle in the manually driven state or the remotely operated driven state based on the acquired position information; and that creates a travel route on which a vehicle is caused to travel in an autonomously driven state using the stored travel route.

Abstract: In one embodiment, a method includes determining an initial cost volume associated with a plurality of potential trajectories of a vehicle in an environment based on a set of movement restrictions of the vehicle, generating a delta cost volume using the initial cost volume and environment data associated with the environment, wherein the delta cost volume is generated by determining adjustments to the initial cost volume that incorporate observed driving behavior, and scoring a trajectory of the plurality of potential trajectories for the vehicle based on the initial cost volume and the delta cost volume.

Abstract: A method for controlling the movements of a controllable door of a motor vehicle that has two or more doors with movable door wings. One door is a main door and at least one other door is a secondary door. A control device and a sensor arrangement are associated to the doors. The secondary door includes a controllable motion influencing device, wherein a motion of the door wing of the secondary door can be at least partially controlled and influenced by way of the motion influencing device between a closed position and an open position. The motion influencing device brakes or arrests a door wing of the secondary door in the closed position for a predetermined time period after the main door has been opened, and/or in dependence on an identified situation.

Abstract: A computer-implemented method for controlling an unmanned aerial vehicle (UAV) includes obtaining a first image captured by an imaging device carried by the UAV during a takeoff of the UAV from a target location, obtaining a second image from the imaging device in response to an indication to return to the target location, determining a spatial relationship between the UAV and the target location by comparing the first image and the second image, and controlling the UAV to approach the target location based at least in part on the spatial relationship.

Abstract: A driving control method is provided in which a processor configured to control driving of a vehicle acquires detection information around a vehicle on the basis of a detection condition that can be set for each point; extracts events which the vehicle encounters, on the basis of the detection information; creates a driving plan in which a driving action is defined for each of the events on the basis of the detection information acquired in the events; executes a driving control instruction for the vehicle in accordance with the driving plan; and determines the detection condition on the basis of the content of the driving action defined for each of the events.