A self-propelled harvesting machine includes a front harvesting attachment, a ground drive with first and second drive shafts offset relative to the front harvesting attachment, first and second track roller units to which first and second drive shafts are drivably connected and which extend on both sides of the harvesting machine and a rear axle having rear wheels that are steered via a steering mechanism provided in a rear region of the harvesting machine. The first and second drive shafts are driven by separate first and second hydraulic motors of a hydrostatic transmission. A displacement volume of each of the first and second hydraulic motors is changed depending on a steering movement transferred from the steering mechanism to the rear wheels, realizing an additional moment about a vertical axis of the harvesting machine simultaneously with the steering of the rear wheels.

An implement includes a global positioning system (GPS) receiver and an implement control system. The global positioning system receiver is configured to obtain position information for the implement. The implement control system is configured to determine a lateral error for the implement based on the position information, estimate a lateral error for a vehicle relative to the implement, the vehicle being attached to the implement, and steer the vehicle to guide the implement based on at least the lateral error for the implement and the lateral error for the vehicle.

A vegetative health mapping system which creates two- or three-dimensional maps and associates moisture content, soil density, ambient light, surface temperature, and/or additional indications of vegetative health with the map. Moisture content is inferred using radar return signals of near-field and/or far-field radar. By tuning various parameters of the one or more radar (e.g. frequency, focus, power), additional data may be associated with the map from subterranean features (such as rocks, soil density, sprinklers, etc.). Additional sensors (camera(s), lidar, IMU, GPS, etc.) may be fused with radar returns to generate maps having associated moisture content, surface temperature, ambient light levels, additional indications of vegetative health (as may be determined by machine learned algorithms), etc. Such vegetative health maps may be provided to a user who, in turn, may indicate additional areas for the vegetative health device to scan or otherwise used to recommend and/or perform treatments.

A method includes obtaining, by the treatment system configured to implement a machine learning (ML) algorithm, one or more images of a region of an agricultural environment near the treatment system, wherein the one or more images are captured from the region of a real-world where agricultural target objects are expected to be present, determining one or more parameters for use with the ML algorithm, wherein at least one of the one or more parameters is based on one or more ML models related to identification of an agricultural object, determining a real-world target in the one or more images using the ML algorithm, wherein the ML algorithm is at least partly implemented using the one or more processors of the treatment system, and applying a treatment to the target by selectively activating the treatment mechanism based on a result of the determining the target.

A vehicle is provided. The vehicle includes a camera configured to detect a target object in a parking space and a controller programmed to advance the vehicle into the parking space based on a yaw angle of the vehicle and a distance to the target object in response to the camera detecting the presence of the target object. The distance to the target object is based on a vector representing a boundary of the target object.

A system and method is provided for early detection of objects by a perception system of a vehicle, and triggering a precautionary action by the vehicle in response without waiting for a more precise detection. The vehicle has a multi-level sensor range, wherein a first level of the sensor range is adjacent an outer bounds of the sensor range and has a first confidence value, and a second level of the sensor range is within the first range and has a second higher confidence value. In situations when oncoming traffic is traveling at a high rate of speed, the vehicle responds to noisier detections, or objects perceived with a lower degree of confidence, rather than waiting for verification which may come too late.

Provided are a work region setting portion which sets, within a traveling region, a work region for a working vehicle to perform predetermined work; and a traveling route setting portion which sets, within the traveling region, a target traveling route to make the working vehicle travel automatically. The traveling route setting portion includes: an initial route generation portion which generates an initial route based on a trajectory formed by the working vehicle traveling in the traveling region; a work route generation portion which generates work routes arranged in a parallel arrangement direction orthogonal to an extension direction; and a connection route generation portion which generates connection routes connecting, at either side of the work region, routes adjacent in the parallel arrangement direction among the initial route and the work routes. The target traveling route including the initial route, the work routes, and the connection routes is thereby set.

Provided are a work region setting portion which sets, within a traveling region, a work region for a working vehicle to perform predetermined work; and a traveling route setting portion which sets, within the traveling region, a target traveling route to make the working vehicle travel automatically. The traveling route setting portion includes: an initial route generation portion which generates an initial route based on a trajectory formed by the working vehicle traveling in the traveling region; a work route generation portion which generates work routes arranged in a parallel arrangement direction orthogonal to an extension direction; and a connection route generation portion which generates connection routes connecting, at either side of the work region, routes adjacent in the parallel arrangement direction among the initial route and the work routes. The target traveling route including the initial route, the work routes, and the connection routes is thereby set.

A control system for a mobile machine includes one or more sensors for generating machine state data and one or more computing devices. The one or more computing devices are configured to determine a first segment and a second segment of an operating path of the machine and to use the machine state data to determine an optimal speed for a turn maneuver between the first segment and the second segment of the operating path. The one or more computing devices may further be configured to determine a first optimal speed for a first portion of the turn maneuver and a second optimal speed for a second portion of the turn maneuver.

A vehicle control system and a method for self-control driving thereof are provided. The method includes: adjusting, by a controller, steering based on lane information and sensing a driving situation of the vehicle based on the steering adjustment. In addition, the controller is configured to determine an intervention in an attitude control based on the driving situation and in response to determining the intervention, operate a braking system to adjust the attitude of the vehicle.