An agricultural method includes providing a positive air pressure chamber to prevent outside contaminants from entering the chamber; growing crops in a plurality of cells in the chamber, each cell having multi-grow benches or levels, each cell further having connectors to vertical hoists for vertical movements in the chamber; maintaining pre-set temperature, humidity, carbon dioxide, watering and lighting levels to achieve predetermined plant growth; using motorized transport rails to deliver benches for operations including seeding, harvesting, grow media recovery, and bench wash; dispensing seeds in the cell with a mechanical seeder coupled to the transport rails; growing the crops with computer controlled nutrients, light and air level; and harvesting the crops and delivering the harvested crop at a selected outlet of the chamber.

Techniques for determining and/or predicting a trajectory of an object by using the appearance of the object, as captured in an image, are discussed herein. Image data, sensor data, and/or a predicted trajectory of the object (e.g., a pedestrian, animal, and the like) may be used to train a machine learning model that can subsequently be provided to, and used by, an autonomous vehicle for operation and navigation. In some implementations, predicted trajectories may be compared to actual trajectories and such comparisons are used as training data for machine learning.

An image processing system includes: a possibility determination unit that determines whether there is a possibility that an obstacle is shown in an image acquired by an image acquisition device of a vehicle; a transmitting unit that transmits, from the vehicle, image information of the acquired image if it has been determined that there is a possibility that an obstacle is shown therein; a receiving unit that receives the image information from vehicles; a processing unit that performs image processing to identify an obstacle shown in the acquired image; and a duplication determination unit that determines whether or not an identified obstacle, which has been identified in a previous acquired image, is shown in a subsequent acquired image received by the receiving unit, wherein the processing unit performs the image processing on the subsequent acquired image if the subsequent acquired image has been determined to not show the identified obstacle.

Planar regions in three-dimensional scenes offer important geometric cues in a variety of three-dimensional perception tasks such as scene understanding, scene reconstruction, and robot navigation. Image analysis to detect planar regions can be performed by a deep learning architecture that includes a number of neural networks configured to estimate parameters for the planar regions. The neural networks process an image to detect an arbitrary number of plane objects in the image. Each plane object is associated with a number of estimated parameters including bounding box parameters, plane normal parameters, and a segmentation mask. Global parameters for the image, including a depth map, can also be estimated by one of the neural networks. Then, a segmentation refinement network jointly optimizes (i.e., refines) the segmentation masks for each instance of the plane objects and combines the refined segmentation masks to generate an aggregate segmentation mask for the image.

This disclosure relates in general to systems and methods for optically tracking objects proximate an autonomous vehicle. In particular, an object tracking system capable of refining position data for objects being tracked by determining a location of the objects surrounding the autonomous vehicle at least on part on previously determined locations of the objects. In certain instances, the predicted and detected locations used to arrive at a refined location for the objects can be weighted in different ways depending on conditions of the sensor data and quality of the historical data.

A method and an electronic device for determining a presence of an obstacle in a surrounding area of a self-driving car (SDC) are provided. The method comprises receiving sensor data representative of the surrounding area of the SDC in a form of 3D point cloud data; generating, by an MLA, based on the 3D point cloud data, a set of feature vectors representative of the surrounding area; generating, by the MLA, a grid representation of the surrounding area, each given cell of the grid representation including a predicted distance parameter indicative of a distance from the given cell to a closest cell with the obstacle; and using, by the electronic device, the distance parameter to determine presence of the obstacle in the surrounding area of the SDC.

Systems, methods, and non-transitory computer-readable media can receive a geometric map and a semantic map associated with a geographic area, the semantic map comprising semantic data associated with vehicle navigation. A first semantic position estimate associated with a first piece of semantic data contained in the semantic map is generated based on semantic data location information associated with the first piece of semantic data. A final position for the first semantic position estimate is received. One or more three-dimensional semantic labels are applied to the geometric map based on the final position of the first semantic position estimate. A warped semantic map is generated. Generating the warped semantic map comprises warping the semantic map based on the one or more three-dimensional semantic labels.

The present teaching relates to method, system, medium, and implementations for sensor calibration. A request is received from an ego vehicle in motion on a route for assistance in collaborative calibration of a sensor deployed on the ego vehicle. The request specifies a position of the ego vehicle and a configuration of the sensor with respect to the ego vehicle. A collaborative means along the route is identified based on the ego vehicle's position, the configuration of the sensor, the route, and the position associated with the collaborative means. A calibration assistance package is generated in response to the request and sent to the ego vehicle. The calibration assistance package includes information about the collaborative means that can be used to identify the collaborative means while in motion along the route for calibrating the sensor while the ego vehicle is in the vicinity of the collaborative means.

A machine-learning (ML) architecture for determining three or more outputs, such as a two and/or three-dimensional region of interest, semantic segmentation, direction logits, depth data, and/or instance segmentation associated with an object in an image. The ML architecture may output these outputs at a rate of 30 or more frames per second on consumer grade hardware.

Tracking a current and/or previous position, velocity, acceleration, and/or heading of an object using sensor data may comprise determining whether to associate a current object detection generated from recently received (e.g., current) sensor data with a previous object detection generated from formerly received sensor data. In other words, a track may identify that an object detected in former sensor data is the same object detected in current sensor data. However, multiple types of sensor data may be used to detect objects and some objects may not be detected by different sensor types or may be detected differently, which may confound attempts to track an object. An ML model may be trained to receive outputs associated with different sensor types and/or a track associated with an object, and determine a data structure comprising a region of interest, object classification, and/or a pose associated with the object.