A method for training a trajectory planning model, an apparatus, and computer storage medium are provided. The method may include: obtaining an image of a physical environment in which a vehicle is located via at least one sensor of the vehicle, the image including multiple objects surrounding the vehicle; obtaining a feature chart indicating multiple initial trajectory points of the vehicle in the image from a trajectory planning model based on the image; identifying the image to determine in the image a first area associated with a road object in multiple objects and a second area associated with a non-road object in the multiple objects; determining a planning trajectory point based on positional relationship of the multiple initial trajectory points with respect to the first area and the second area; and training a trajectory planning model based on the planning track point and the actual trajectory point of the vehicle.

Methods and systems for identifying autonomous vehicle users are described herein. An autonomous vehicle may receive a request to transport a first user to a first destination location. While travelling along a route to the first destination location, the autonomous vehicle may receive a request to pick up a second user at a second starting location and transport the second user to a second destination location. The autonomous vehicle may travel to the second starting location when the second user is within the threshold distance of the autonomous vehicle. Upon arriving at the second starting location, the autonomous vehicle may detect whether a person approaching the vehicle is the second user by detecting a biometric identifier for the person. As a result, the second user may be allowed to enter the autonomous vehicle and/or the autonomous vehicle may begin travelling to the second destination location.

An information presentation apparatus includes an acquisition unit, an asymmetric acceleration generating unit, and a signal generating unit. The acquisition unit acquires at least one of information inside a vehicle or information outside the vehicle. The asymmetric acceleration generating unit presents haptic feedback information to a user via a steering unit provided in the vehicle by generating asymmetric acceleration. The signal generating unit generates a driving signal on the basis of information acquired by the acquisition unit and send the driving signal to the asymmetric acceleration generating unit.

A controller for use with autonomous vehicle functions comprises an input for receiving data regarding a set of vehicle factors, an output for controlling autonomous vehicle functions and a processor having control logic. The control logic receives data regarding the set of vehicle factors, sets the autonomous vehicle functions in a first mode when at least two of the vehicle factors meet a respective first condition and sets the autonomous vehicle functions in second mode when at least one of the vehicle factors meets a respective second condition.

An apparatus for assisting driving of a vehicle includes a camera mounted to the vehicle for viewing an area in front of the vehicle, a radar sensor mounted to the vehicle to sense around the vehicle, and a controller connected to the camera and/or the radar sensor to detect obstacles and perform collision avoidance control. The controller is further configured to recognize a first obstacle approaching in a lateral direction from an outside of a driving lane of the vehicle, generate and store a collision avoidance path for avoiding collision with the first obstacle, recognize a third obstacle passing behind a second obstacle in the lateral direction after the recognition of the first obstacle is interrupted by the second obstacle, and perform collision avoidance control of the vehicle based on a similarity between the first obstacle and the third obstacle and based on the stored collision avoidance path.

The invention relates to a driver-assistance device for assisting with driving a motor vehicle (1) following a road (2), this device comprising: a sensor suitable for acquiring a signal representative of the presence of an obstacle in the interior of a detection field (110) of this sensor, and a control module that is programmed to control a driver-assistance function for assisting with driving the motor vehicle, depending on the signal acquired by said sensor, and: a) to detect, on the basis of a position of the motor vehicle and of characteristics of said road, a section (20) of this road located outside of the detection field of said sensor, and b) in case of detection of this road section, to control said driver-assistance function while taking into account the potential presence of an obstacle on said road section. An associated driver-assistance method is also described.

Systems and methods for navigating a host vehicle are disclosed. In one implementation, a system includes a processor configured to receive a first image acquired by a first camera and a second image acquired by a second camera onboard the host vehicle; identify a first representation of an object in the first image and a second representation of the object in the second image; input to a first trained model at least a portion of the first image; input to a second trained model at least a portion of the second image; receive the first signature encoding determined by the first trained model and the second signature encoding determined by the second trained model; input to a third trained model the first signature encoding and the second signature encoding; and receive an indicator of a location of the object determined by the third trained model.

Waste collection is performed at regular intervals around the world. The process currently is performed by a team consisting of a waste collection truck that carries the refuse that is driven around urban areas at slow speeds. This waste collection truck usually contains a large opening in the back. A team of humans controls this truck and collects the bins dumping the refuse on the back of the truck and returning the bins to the curb. Usually, the driver (human) of the truck positions the truck so as to minimize the distance that the human garbage collectors need to walk with the loaded bins, and slowly drives a route that take the truck to the collections sites. Because currently most residential neighborhoods and some commercial neighborhoods do not use bins and pick up locations that are easy to automatically lift, it is likely that the process of picking up the bins, depositing the refuse on the truck, and returning the bins to the curb will be performed by humans for some time to come. However, the driver of the truck and the control mechanism to make sure that the truck minimizes the work performed by the humans picking up the bins, can be readily and economically performed using current technology. The invention being presented here automates the functions of the driver of the garbage truck. It involves a waste collection truck designed to follow routes to collect waste using a human to pick up the bins with refuse or other material comprising a truck that includes a drive-by-wire kit, a database storing the collection routes, a mechanism for detecting the position of the human which collects the waste bins and empties them on the back of the truck and a control mechanism that follows the assigned route and speeds or slows down the truck as to minimize the distance that the human will need to walk to empty the trash in the back of the waste collection truck. In addition, robots will replace the human workers who empty the bins.

A driving assistance device includes processing circuitry to acquire host vehicle information, receive mobile object information from a mobile object outside the host vehicle using wireless communication, determinate a right or left turn of the host vehicle based on the host vehicle information, obtain a prediction point by calculating a right or left turn point of the host vehicle based on the host vehicle information, determine whether or not the host vehicle collides with the mobile object using the host vehicle information, the mobile object information, and the prediction point, and perform driving assistance of the host vehicle based on a result of the collision determination. The processing circuitry obtains the prediction point by calculating, on a basis of a preset deceleration, a distance required for the speed of the host vehicle HV included in the host vehicle information to reach a target speed set in advance.

An environmental safety system may comprise a plurality of first sensors each located at a predetermined physical location of a physical location and with a predetermined orientation. The system may receive first sensor data captured by the plurality of first sensors. The system may also determine values of one or more parameters of an object within a threshold distance of the physical location using the first sensor data. The values of the one or more parameters of the object may be transmitted to a vehicle approaching the physical location. The vehicle may receive second sensor data captured by a plurality of second sensors in the vehicle. An optimized navigation of the vehicle approaching the physical location may be determined based on the values of the one or more parameters of the object and the second sensor data. A driving action may be provided to the vehicle based on the optimized navigation of the vehicle. The driving action may be characterize one or more maneuvers to be performed by the vehicle to execute the optimized navigation nearby the physical location.