A vehicle exterior environment recognition apparatus includes a travel path derivation unit, a speed derivation unit, and a follow-up controller. The travel path derivation unit estimates an own-vehicle travel path and derives a target-vehicle travel path that contains a point on a target vehicle and forms a parallel curve to the own-vehicle travel path. The speed derivation unit derives a target-vehicle speed vector. The follow-up controller makes a follow-up control based on the target-vehicle speed vector on the condition that an angle formed by the target-vehicle speed vector and a tangential line to the target-vehicle travel path at the point on the target vehicle falls within a predetermined angular range, and makes the follow-up control based on a tangential speed component of the target-vehicle speed vector on the condition that the angle falls out of the angular range.

A system includes a controller circuit configured to monitor, while a host vehicle is operated in a manual driving mode, a speed change response of an operator of the host vehicle based on a movement of a first vehicle traveling on a roadway, identify at least one speed parameter based on the speed change response, and apply, when the host vehicle is controlled in an autonomous driving mode, the at least one speed parameter based on the movement of a second vehicle traveling on the roadway.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting actions for an agent at a specific real-world location using historical data generated at the same real-world location. One of the methods includes determining a current geolocation of an agent within an environment; obtaining historical data for geolocations in a vicinity of the current geolocation of the agent from a database that maintains historical data for a plurality of geolocations within the environment, the historical data for each geolocation comprising observations generated at least in part from sensor readings of the geolocation captured by vehicles navigating through the environment; generating an embedding of the obtained historical data; and providing the embedding as an input to a policy decision-making system that selects actions to be performed by the agent.

Systems and methods use cameras to provide autonomous navigation features. In one implementation, a method for navigating a user vehicle may include acquiring, using at least one image capture device, a plurality of images of an area in a vicinity of the user vehicle; determining from the plurality of images a first lane constraint on a first side of the user vehicle and a second lane constraint on a second side of the user vehicle opposite to the first side of the user vehicle; enabling the user vehicle to pass a target vehicle if the target vehicle is determined to be in a lane different from the lane in which the user vehicle is traveling; and causing the user vehicle to abort the pass before completion of the pass, if the target vehicle is determined to be entering the lane in which the user vehicle is traveling.

A method for navigating a vehicle automatically from a current location to a destination location without a human operator is disclosed. The method includes identifying a vehicle location using global positioning system (GPS) data regarding the vehicle. Also included is identifying that the vehicle location is near or at a parking location. Then, using mapping data defined for the parking location. The mapping data at least in part is used to find a path at the parking location to avoid a collision of the vehicle with at least one physical structure when the vehicle is automatically moved at the parking location. The method includes instructing the electronics of the vehicle to proceed with controlling the vehicle to automatically move from the current location to the destination location at the parking location. The electronics use as input at least part of the mapping data and sensor data collected from around the vehicle by at least two vehicle sensors. The path is configured to be updatable dynamically based on changes in the destination location or changes along the path. The destination location is a parking spot for the vehicle at the parking location.

Provided are a path planning method and device for an unmanned vehicle, road segments of an origin and destination of a path are acquired; path search is performed to generate an initial path according to an exit endpoint of the road segment where the origin is located, an entrance endpoint of the road segment where the destination is located, and entrance endpoints and exit endpoints of the road segments for connecting the exit endpoint of the road, segment where the origin is located to the entrance endpoint of the road segment where the destination is located; an exit endpoint of a previous road section of the connecting passages in a passable direction is updated according to entrance endpoints of the connecting passages in the initial path; and a final planed path is generated according to different endpoints in the updated initial path.

A control system for preventing vehicle collisions may include a vehicle location determination module, a terrain determination module, a terrain surface coefficient of friction estimation module, and a sensing system configured to generate signals indicative of vehicle speed, vehicle pose, vehicle size, vehicle weight, vehicle tire type, vehicle load, vehicle gear ratio, weather characteristics, and road conditions for a vehicle operating at a job site. A manned vehicle trajectory determination module may receive location information and plot a first travel path for a manned vehicle based at least in part on a location, heading, and speed of the manned vehicle and a desired destination for the manned vehicle. An autonomous vehicle trajectory determination module may receive location information, terrain information, and terrain surface coefficient of friction information, plot a second travel path for an autonomous vehicle, and determine projected slide trajectories for the autonomous vehicle at successive positions along the second travel path where the autonomous vehicle is predicted to lose traction based at least in part on signals received from the sensing system.

Disclosed are a vehicle anti-collision forewarning method, an in-vehicle computer device and a vehicle anti-collision forewarning system.

Systems and methods use cameras to provide autonomous navigation features. In one implementation, a method for navigating a user vehicle may include acquiring, using at least one image capture device, a plurality of images of an area in a vicinity of the user vehicle; determining from the plurality of images a first lane constraint on a first side of the user vehicle and a second lane constraint on a second side of the user vehicle opposite to the first side of the user vehicle; enabling the user vehicle to pass a target vehicle if the target vehicle is determined to be in a lane different from the lane in which the user vehicle is traveling; and causing the user vehicle to abort the pass before completion of the pass, if the target vehicle is determined to be entering the lane in which the user vehicle is traveling.

System, methods, and other embodiments described herein relate to transitioning a vehicle from an autonomous to a manual driving mode. One embodiment analyzes data from one or more vehicle sensors to detect, at a current vehicle position, features in a first detection region and a second detection region ahead of the vehicle; determines, for each of one or more hypothetical vehicle positions, which features detected at the current position, if any, lie within the first detection region at that hypothetical position; identifies, among the one or more hypothetical positions, at least one localization-failure position at which localization of the vehicle will fail due to insufficient features being detected within the first detection region at the at least one localization-failure position; and initiates a transition from the autonomous driving mode to the manual driving mode based, at least in part, on the at least one localization-failure position.