A method for automatically training a neural network includes at a trainer having a first communication device and a perception recorder, continuously recording the surroundings in the vicinity of the first object; receiving, at the trainer, a message from a communication device associated with an object in the vicinity of the trainer, the message including information about the position and the type of the object; identifying a recording corresponding to the time at which the message is received from the object; correlating the received positional information about the second object with a corresponding location in the recording to identify the object in the recording; classifying the identified object based on the type of information received in the message from the object; and using the classified recording to train the neural network.

A vehicle detects a rotation angle of a seat, controls activation of a first type of roof airbag module provided in a central portion of a headlining and located at a side of the seat when the detected rotation angle of the seat is greater than a first reference angle and less than or equal to a second reference angle, controls activation of the first type of roof airbag module and a second type of roof airbag module provided in the central portion of the headlining and provided at a rear of the seat when the detected rotation angle of the seat is greater than the second reference angle and less than or equal to a third reference angle, determines whether a collision with an obstacle has occurred during traveling, and deploys and expands the activated airbag module when determining that the collision with the obstacle has occurred.

Disclosed embodiments include techniques for providing alerts to a driver of a vehicle. The techniques include detecting a condition that exceeds a threshold hazard potential; detecting a predetermined gesture of a driver, the predetermined gesture indicating that the driver has acknowledged the detected condition; in response to detecting the predetermined gesture, reducing an urgency level for alerting the driver of the detected condition; and determining whether to issue an alert to the driver based on the reduced urgency level.

A method for providing a coast recommendation for an operator of a vehicle, including receiving vehicle position data; determining a projected route; determining a first speed change position and a first speed change target speed; determining a first residual speed and a first residual speed position based at least in part on the first speed change position and the first speed change target speed; determining a first lower speed envelope; determining an overall lower speed envelope based at least in part on the first residual speed; determining an upper speed envelope; determining a target speed profile based at least in part on the first residual speed, the first residual speed position, the first lower speed envelope, and the upper speed envelope; determining a coast start point based at least in part on the target speed profile; and communicating the coast start point to the operator of the vehicle.

A method and activity recognition system for recognising activities in surrounding environment for controlling navigation of an autonomous vehicle is disclosed. The activity recognition system receives first data feed from neuromorphic event-based camera and second data feed from frame-based RGB video camera. The first data feed comprises high-speed temporal information encoding motion associated with change in surrounding environment at each spatial location, and second data feed comprises spatio-temporal data providing scene-level contextual information associated with surrounding environment. An adaptive sampling of second data feed is performed with respect to foreground activity rate based on amount of foreground motion encoded in first data feed. Further, the activity recognition system recognizes activities associated with at least one object in surrounding environment by identifying correlation between both data feed by using two-stream neural network model. Thereafter, based on the determined activities, the activity recognition system controls the navigation of the autonomous vehicle.

A materials handling vehicle comprises an operator compartment, a compartment tower, a multi-field scanning tool, and mechanisms that facilitate movement along a travel plane in a warehouse. The tool establishes a scan field, and, within scan field bounds, an occupancy detection field and an obstacle detection field. Tool scanning hardware is configured to generate the scan field from a point of origin that is elevated relative to the operator compartment and to expand the scan field such that it intersects the operator compartment and extends laterally beyond lateral edges of the operator compartment such that the occupancy detection field falls within the operator compartment, the obstacle detection field falls outside of the operator compartment, and the multi-field scanning tool is configured to indicate the presence of an occupant in the occupancy detection field and obstacles in the obstacle detection field.

A trajectory setting device that sets a trajectory of a host vehicle includes a first path generation unit configured to generate a first path by assuming all obstacles around the host vehicle to be stationary obstacles, a second path generation unit configured to generate a second path when the moving obstacle is assumed to move independently, a third path generation unit configured to generate a third path when the moving obstacle is assumed to move while interacting with at least one of the other obstacles or the host vehicle, a reliability calculation unit configured to calculate reliability of the second path and reliability of the third path, and a trajectory setting unit configured to set the trajectory for traveling from the first path, the second path, and the third path based on the reliability of the second path and the reliability of the third path.

The control device for forward collision avoidance in a vehicle includes a forward object determination unit configured to recognize an object in front of the vehicle and to determine an attribute of the recognized object, a gear position detection unit configured to detect a gear position of the vehicle, and a forward collision-avoidance assist (FCA) control unit configured to finally determine the attribute of the object determined by the forward object determination unit according to the gear position input from the gear position detection unit and to set an FCA control range based on the finally determined object attribute.

The disclosure relates to an improved way to avoid or clear a traffic jam. In particular, the disclosure relates to a method for the operation of a vehicle in which at least partial intersection by a dynamic object with a first section of the traffic area occupied by the vehicle is predicted, wherein the vehicle is in a waiting situation waiting for a release for onward travel. Then a trajectory of the vehicle is determined, which at least clears or avoids the intersection by the dynamic object with the first section of the traffic area. Further, the disclosure relates to a device for the operation of a vehicle, a program element and a computer-readable medium with such a program element.

A vehicle is provided to avoid a collision with a target object located in front of the vehicle by predicting an expected traveling path of the target object. The vehicle also predicts the possibility of a collision with the target object.