The present disclosure belongs to a field of UAVs exploration technology, discloses a high-efficient autonomous exploration method, system, and terminal for UAVs, comprising: S1, heuristic waypoint generation: setting an exploration scope and waypoint spacing, and generating waypoints through waypoint generation algorithms; S2, global path planning: after generating heuristic waypoints, an A * algorithm is used to generate the global planning path; S3, real-time positioning and mapping: using point clouds for real-time positioning and mapping; S4, local B-spline trajectory generation: using B-spline parameterization method to generate local trajectories; S5, real-time obstacle avoidance and dynamic feasibility constraints: optimizing the trajectories to achieve fast convergence, generating smooth, collision-free, and dynamically feasible trajectories; S6, local real-time replanning: using a time sliding window for local replanning; S7, flight control: Using UAV control algorithms for controlling of UAVs robustly.

An optimized coverage-path planning method for a single unmanned surface mapping vessel (USMV) is implemented with a system including a computer processor executing a computer program loaded in a storage device and implanting the method. The method includes rasterizing and initializing an environmental map, and an unmanned vessel outputting position data and obstacle data according to the environmental map so that path planning is started to provide a target point to the unmanned vessel. In case of tripping in a local optimum at a current-level map for the target point, the map level is updated in an ascending order until the highest level, in order to identify a map level in which the target point is found.

Systems and methods for autonomous vehicle path planning are described herein. An example vehicle includes an image sensor to obtain an image of a scene of an area surrounding the vehicle. The vehicle also includes navigation system circuitry to: analyze the image and generate a semantically segmented image that identifies one or more types of features in the image; project the semantically segmented image to a two-dimensional (2D) map projection; convert the 2D map projection into a cost map; and determine a path for the vehicle based on the cost map.

A method and system for exploring a real-world environment using a mobile robot platform comprising mapping the environment at a first time, to generate a first representation of the environment and identifying an initial location of an object in the first representation of the environment. The environment is mapped at a second time, to generate a second representation of the environment. The mappings are generated based on data obtained from a sensor associated with the mobile robot platform. Based on data obtained from the sensor, a new location of the object is identified in the second representation of the environment, and a difference between the initial location of the object and the new location of the object is determined. Using a manipulator the object is moved to the initial location when it is determined that the initial location of the object differs from the new location.

A latency-based robot driving map generation apparatus includes a network map generator configured to divide a space into grids and measure network latency for each grid to generate a network map with assigned latency levels. The apparatus further includes a success rate calculator configured to calculate success rates by repeated driving operations on paths within grids assigned specific latency levels in the network map. Additionally, a driving path determiner determines a driving path on the network map based on the assigned latency levels and the calculated success rates.

Systems and methods for geophysical exploration of underwater environments are provided. In some embodiments, a geophysical measurement system includes at least one cable having a cable distributed array of electrodes. In some embodiments, the geophysical measurement system further includes at least first and second unmanned vehicles submersible below water for coupling at respective points along the cable so as to maneuver a segment of the cable that includes at least some of the cable distributed array of electrodes through a series of positions and orientations relative to subsurface geologic features below the water, where respective ones of the electrodes along the maneuvered segment participate as transmitters or receivers in electrical resistivity imaging of the subsurface geologic features from at least first and second maneuvered-to positions or orientations that differ from one another.

A method of determining a crop yield of a field worked by an agricultural vehicle includes receiving, from a sensor of the agricultural vehicle, sensor data associated with at least one parameter of a swath of a plant material formed by the agricultural vehicle in the field. The method further includes receiving, from a location sensor, location data indicative of a location of the swath of the plant material. The method further includes generating, based on the sensor data and the location data, the swath parameter map indicating the at least one parameter of the swath of the plant material at the location of the swath of the plant material.

A fruit quantity measurement system includes an unmanned aerial vehicle configured to receive GPS information about a fruit tree region of a predetermined area and an RF signal transmitted from an RF transmitter installed for each fruit tree and provide fruit tree images captured using at least one image sensor while flying based on a predetermined flight plan over the fruit tree region, and a monitoring server configured to be connected to the unmanned aerial vehicle through a communication network to receive GPS information and an RF signal from the unmanned aerial vehicle, match and store location data for each fruit tree, analyze the fruit tree image, measure the number of fruits for each fruit tree, store fruit counting information, and provide the stored location data or fruit counting information for each fruit tree according to a request from a user terminal authorized in advance.

Approaches are disclosed for mapping surroundings of a marine vessel. These involve obtaining, at a first location, first distance data from distance sensors including a bow-mounted sensor arranged to monitor a first area involving surroundings adjacent to the bow and a first side of the marine vessel, and a stern-mounted sensor arranged to monitor a second area involving surroundings adjacent to the stern and a second side, opposite the first side, of the marine vessel. The approaches further includes generating a surroundings map comprising at least two unmapped areas indicating blind spots of at least partially incomplete surroundings representations; obtaining, at a second location, second distance data from the set of distance sensors; and causing updates to the unmapped areas based on the second distance data.

A method of validating detected anomalies in an agricultural field includes gathering sensor data with one or more cameras, LiDAR units, and radar units and generating predicted anomalies based on the sensor data by applying an anomaly detection deep neural network to the sensor data. Sensor data is gathered at a second time and predicted anomalies are determined by applying the anomaly detection deep neural network to the sensor data acquired at the second time. The predicted anomalies at the second time is compared to the predicted anomalies at the first time to validate the predicted anomalies and generated a validated anomaly map. Related agricultural machines and systems are also disclosed.