Provided are systems and methods for a deep learning based beam control. Sensor data associated with the environment and the corresponding detected objects from a perception system are obtained. Object features and image features are extracted. The extracted object features and image features are fused into fused features. A beam control status is predicted according to the fused features, wherein the beam control status indicates a high beam illumination intensity or a low beam illumination intensity of a light emitting device.

The disclosure generally pertains to systems and methods for assisting a customer retrieve a package from an autonomous vehicle. In an example procedure, the autonomous vehicle may detect the customer waiting at a first spot and may determine that the first spot is unsuitable/unsafe for the customer to retrieve a package from a locked compartment in the autonomous vehicle. The autonomous vehicle may therefore instruct the customer to move to a second spot that is safer and closer to the compartment and may then execute an authentication procedure to authenticate the customer and unlock a door of the compartment. In an alternative approach, the autonomous vehicle may travel to a parking spot that is safer and closer to where the customer is waiting (rather than instructing the customer to move) before authenticating and unlocking the door of the compartment to allow the customer to retrieve the package.

A control method according to the present disclosure includes: obtaining (receiving) position information (a danger warning signal) indicating a target position where a target object is present; determining whether the vehicle is driving autonomously or is being driven manually; when the vehicle is determined to be being driven manually, inspecting whether the target position is located within a predetermined region of a travel route of the vehicle based on the position information; when the target position is located within the predetermined region, changing the light transmission state of the headlight from a first state to a second state; and when the vehicle is determined to be driving autonomously and/or the target position is not located within the predetermined region, maintaining the light transmission state of the headlight.

A delivery robot that delivers a delivery item in a building comprises: a first acquisition unit configured to acquire external environment information; a travel control unit configured to control traveling of the delivery robot to a delivery destination in the building on the basis of the environment information acquired by the first acquisition unit; and a notification unit configured to perform notification in a case where an opening operation of a door existing in a traveling direction of the delivery robot is detected during the traveling of the delivery robot on the basis of the environment information acquired by the first acquisition unit. The notification unit performs notification by at least one of light and sound toward the door.

An autonomous travel controller detects whether a host vehicle is carrying out a first course change for changing a course in a direction indicated by a turn indicator. Upon detecting that the host vehicle is carrying out the first course change, detecting whether there is a road that enables a second course change for changing the course of the host vehicle that branches from the road after the first course change. When a road that enables the second course change is detected, the autonomous travel controller turns the turn indicator off.

A vehicle system is provided in a vehicle that is capable of running in an autonomous driving mode. The vehicle system includes: a sensor configured to acquire detection data indicating a surrounding environment of the vehicle; a generator configured to generate surrounding environment information indicating a surrounding environment of the vehicle, based on the detection data; and a use frequency setting module configured to set a use frequency for the sensor, based on predetermined information related to the vehicle or surrounding environment of the vehicle.

Headlight and taillight assemblies may include cameras for providing video information. A barrier positioned between the cameras and the lamps of a headlight or taillight assembly reduces or eliminates light reflected from the lamps into the camera from an outer interface of the lens. The barriers enable the cameras to be positioned in close proximity to the lamps. Headlight and taillight assemblies may further include heaters to warm the lenses to melt ice or snow. Various methods may be used to install the headlight and taillight assemblies on the vehicle so the position of each headlight and taillight is known to a processing circuit.

The disclosure provides systems and methods for detecting and responding to a power outage. The methods use sensors of vehicles to detect an indication of a power outage. Once the power outage is validated, the lighting systems of the vehicles are used to illuminate locations so that pedestrians can walk along sidewalks or through parking garages. For example, the vehicles can be arranged to provide lighting at selected locations.

Disclosed is an electronic device for a vehicle, including a processor acquiring image data acquired by a camera mounted in a vehicle, determining a riding intention of an outside person based on the location, posture, and gesture of the outside person detected from the image data, and generating a control signal to stop the vehicle based on the riding intention.

A user can request, via an electronic communication, an autonomous vehicle, such as a taxi, using a mobile device. Once the autonomous vehicle arrives at a pickup location, a wireless electronic communication connection is established between the autonomous vehicle and the mobile device. The autonomous vehicle then generates an audible or visual cue to the user. The mobile direct generates a corresponding audible, visual, or tactile cue as directed via the established wireless electronic communication connection. In this way, the user is able to readily identify which autonomous vehicle is the one requested. In further embodiments the mobile device cue duplicates a pattern of the autonomous vehicle cue or the autonomous vehicle cue and the mobile device cue operate in a call and response fashion.