The subject disclosure relates to features that improve safety for autonomous vehicle (AV) maneuvers and in particular, that improve safety for parallel parking. A process of the disclosed technology includes steps for initiating a parking maneuver, navigating the AV into a parking location, and detecting a roadway grade with respect to a direction of the AV. In some aspects, the process can further include steps for automatically adjusting a wheel angle of the AV based on the roadway grade with respect to the direction of the AV. Systems and machine-readable media are also provided.

The vehicle control program is executed in a VCIB connected between DS and VP that performs autonomous driving in accordance with a command from DS. VCIB includes a memory in which a program including a predetermined API defined for each signal is stored, and a processor that controls VP in response to an instruction from DS by executing the program. VCIB has a manual/automatic mode. VP can accept a manual driving operation in the manual mode, and can accept a command from DS in the automated mode. The vehicle control program causes the processor to execute a step of executing a process for starting the limp-home travel by ICM that differs from VCIB on the condition that communication between DS and VCIB is impossible, and a step of switching from the automated mode to the manual mode on the condition that the limp-home travel by ICM is started.

Embodiments herein relate to robust methodologies for autonomous parking. In one or more embodiments, an autonomous vehicle may determine the slope of a road based upon one or more inputs and a pre-defined slope definition and may also determine curb/no curb status of a parking location. Given the determined road conditions, such as slope and no curb/curb, embodiments determine wheel direction and angle that the vehicle should achieve to properly park. Embodiments also include countermeasures if one or more issues prohibit the vehicle from achieving a desired parking condition.

Generating a lane reference from a roadway shape and/or generating a trajectory for controlling an autonomous vehicle may include determining a predicted state of the lane reference and/or a candidate trajectory by an integrator. The disclosed integrator is implemented as a numerical integrator in predominantly closed-form that is able to avoid singularities while maintaining no approximation error. The disclosed integrator is also more robust to poor initial estimations, high curvature roadways, and zero-velocity conditions.

The present invention provides a lane following system and method considering a driving assistance lane that can flexibly cope with complex roadway situations and enable lane following to improve the reliability of an LCA system, and furthermore, expand a range of a road to which an autonomous driving system is applied.

Disclosed are techniques for operating a driver-in-the-loop (DIL) component of a vehicle. In an aspect, the DIL component receives a first input signal generated based on a first interaction of a driver with a component of the vehicle operating in an autonomous driving mode, applies an attack-sustain-release (ASR) envelope to an amplitude of the first input signal to generate a first output signal representing at least a ramp-in of driver control over the component from no driver control to full driver control, and wherein the ramp-in of the driver control is limited by application of the ASR envelope to the amplitude of the first input signal, and transmits the first output signal to a controller module for the component of the vehicle to enable the controller module to reduce control over the component of the vehicle based on the ramp-in of the driver control represented by the first output signal.

A vehicle control system includes a controller configured to, when a collision of a host vehicle with another vehicle traveling in a direction that intersects with a front-rear direction of the host vehicle is predicted (Yes in S20), when the collision with the other vehicle is unavoidable (No in S70) and when the other vehicle comes into collision with the host vehicle in the intersecting direction, automatically turn a steered wheel of the host vehicle before the host vehicle collides with the other vehicle. The controller is configured to vary a direction of the steered wheel that is turned by the controller (S100 or S110) in response to whether there is a target, other than the other vehicle, around the host vehicle (Yes or No in S90).

Systems and methods use cameras to provide autonomous navigation features. In one implementation, a traffic light detection system is provided for a vehicle. One or more processing devices associated with the system receive at least one image of an area forward of the vehicle via a data interface, with the area including at least one traffic lamp fixture having at least one traffic light. The processing device(s) determine, based on at least one indicator of vehicle position, whether the vehicle is in a turn lane. Also, the processing device(s) process the received image(s) to determine the status of the traffic light, including whether the traffic light includes an arrow. Further, the system may cause a system response based on the determination of the status of the traffic light, whether the traffic light includes an arrow, and whether the vehicle is in a turn lane.

A method and a device for avoiding a collision of a motor vehicle with at least one other object which approaches the motor vehicle in such a way that a collision between the motor vehicle and the approaching object is imminent, a friction coefficient variable being ascertained which represents the friction coefficient potential of the motor vehicle, and at least one action for avoiding and/or reducing the consequences of a collision between the motor vehicle and the approaching object being carried out as a function of the friction coefficient variable.

A method for adjusting a vehicle's position in a roadway lane. A camera mounted on the vehicle generates a current image of the lane and the method identifies a current lane-center line in the current image. A reference image is generated and the method identifies a reference lane-center line in the reference image. The method then calculates an error between the current lane-center line and the reference lane-center line and provide steering commands to adjust the position of the vehicle so that the error is reduced.