An apparatus for warning the collision of a vehicle includes an information acquirer configured to acquire information on a surrounding object and information on a vehicle, and a controller configured to generate collision predicting information for the surrounding object, based on the information on the surrounding object and the information on the vehicle, and generate control information to control braking of the vehicle and to provide, based on the collision predicting information, a buffer element to an outside of the vehicle while controlling the braking of the vehicle.

A system and method for reducing the risk of road accidents on account of blind spot errors and a vehicle using the system and method includes a visual sensing unit, the visual sensing unit comprising a first camera and a second camera, wherein the first camera looks left and obtains a first image information, the second camera looks to the right and obtains a second image information; a pre-processing unit, the pre-processing unit being coupled with the visual sensing unit, wherein the pre-processing unit processes the first image information and the second image information to generate a single image. An image processing unit generates an obstacle recognition information according to the processed image.

A method of generating an output trajectory of an ego vehicle includes recording trajectory data of the ego vehicle and pedestrian agents from a scene of a training environment of the ego vehicle. The method includes identifying at least one pedestrian agent from the pedestrian agents within the scene of the training environment of the ego vehicle causing a prediction-discrepancy by the ego vehicle greater than the pedestrian agents within the scene. The method includes updating parameters of a motion prediction model of the ego vehicle based on a magnitude of the prediction-discrepancy caused by the at least one pedestrian agent on the ego vehicle to form a trained, control-aware prediction objective model. The method includes selecting a vehicle control action of the ego vehicle in response to a predicted motion from the trained, control-aware prediction objective model regarding detected pedestrian agents within a traffic environment of the ego vehicle.

Postal, package, and grocery deliveries are performed routinely everywhere around the world. Currently, the delivery truck drives slowly, and the postman or delivery man goes from one house to another. The postman already has a box that he carries with the sorted letters for a few of the contiguous houses, stops the truck, and walks to the different houses in the bunch, and then moves the truck and goes to the next bunch of houses. In this invention, the package delivery truck will automatically follow the mailman while still staying close to the curb to minimize traffic issues. Here, the autonomous package or delivery truck could actually go in front of the mailman to look for a good spot for the next cluster, or can wait for the mailman that is close to the last house of the current cluster, pick him up, and drop off at the center of the next cluster, or at the first house of the next cluster. In addition, there are robots that replace the function of the human (mailman or grocery delivery man).

A forklift truck includes a main controller, a driving motor, a drive controller, and an object detector. The drive controller controls the driving motor. The object detector detects the position of an object being present in the backward direction of the forklift truck. The main controller derives an expected trajectory of the forklift truck. The main controller imposes a speed limit on the forklift truck by setting a vehicle speed upper limit when the object detected by the object detector is located within the expected trajectory and the forklift truck is traveling in the direction of approaching the object. The main controller gives commands to the drive controller to prevent the vehicle speed of the forklift truck from exceeding the vehicle speed upper limit.

Embodiments described herein disclose systems and methods for a dual buffer zone system to ensure a stable nudge for autonomous driving vehicles. In one embodiment, a system perceives a driving environment surrounding an autonomous driving vehicle (ADV), including perceiving one or more obstacles within a view of the ADV. For each of the one or more obstacles, if a previous planning decision for the obstacle is not a nudge, the system associates a first buffer zone with the obstacle. Otherwise, the system associates a second buffer zone with the obstacle. Based on the associated buffer zone for the obstacle, the system determines a planning decision to nudge the obstacle to ensure a buffer distance between the ADV and the obstacle. The system generates a trajectory for the ADV based on the planning decisions for the one or more obstacles.

A system for providing an alert to an occupant of a vehicle may include one or more processors and a memory. The memory may store a free space detection module, a target detection module, a path prediction module, an activation threshold module, and an alert module. The modules include instructions that cause the one or more processors to determine one or more dimensions of a free space located adjacent to a side of the vehicle, determine one or more dimensions of one or more targets, determine one or more predicted paths of one or more targets, selectively adjust an activation threshold for providing an alert according to the one or more predicted paths, and activate the alert to inform the occupant of a hazard associated with the one or more targets according to whether the one or more predicted paths satisfies the activation threshold.

A vehicle control method implemented by a first vehicle configured with at least one driver assistance system. The method includes activating a driver assistance system to an active state, applying a vehicle speed range to the first vehicle in response to the driver assistance system being in the active state, obtaining first information of a moving object near the first vehicle, determining a first parameter based on the first information, and further terminating, based on the first parameter, the active state, and setting, based on the first parameter, the first vehicle to run at a first vehicle speed beyond the vehicle speed range.

A system includes a memory device, and a processing device, operatively coupled to the memory device, to receive a set of input data including a roadgraph, the roadgraph including an autonomous vehicle driving path, modify the roadgraph to obtain a modified roadgraph by adjusting a trajectory of the autonomous vehicle driving path, place a set of artifacts along one or more lane boundaries of the modified roadgraph to generate a synthetic scene, and train a machine learning model used to navigate an autonomous vehicle based on the synthetic scene.

A control apparatus includes a risk area identification unit for identifying a risk area outside a movable object with respect to a movement of the movable object based on an image captured by an image capturing apparatus mounted on the movable object, and a transmission control unit for performing control to transmit risk area information including position information of the risk area, and precision information related to a calculation precision of the position information to an outside of the movable object without designating a destination, wherein the transmission control unit transmits the position information and the precision information to cause a terminal having received the position information and the precision information to determine whether a position thereof corresponds to an inside of the risk area, and cause an alert unit included in the terminal to output an alert when it is determined that the terminal is inside the risk area.