Abstract: Systems and techniques are described that provide for generalizable approach policy learning and implementation for robotic object approaching. Described techniques provide fast and accurate approaching of a specified object, or type of object, in many different environments. The described techniques enable a robot to receive an identification of an object or type of object from a user, and then navigate to the desired object, without further control from the user. Moreover, the approach of the robot to the desired object is performed efficiently, e.g., with a minimum number of movements. Further, the approach techniques may be used even when the robot is placed in a new environment, such as when the same type of object must be approached in multiple settings.

Abstract: A robot for providing a guidance service using artificial intelligence. The robot measures distances between external robots and the robot and, based on the measured distances, determines that robots are concentrated in a specific area. Based on the determination that robots are concentrated in the specific area, the robot moves some of the external robots to the specific area.

Abstract: A proximity sensor system on a marine vessel includes one or more proximity sensors, each at a sensor location on the marine vessel and configured to measure proximity of objects and generate proximity measurements. A processor is configured to store a two-dimensional vessel outline of the marine vessel with respect to a point of navigation for the marine vessel, receive the proximity measurements measured by one or more proximity sensors on the marine vessel, and identify four linearly-closest proximity measurements to the two-dimensional vessel outline, including one closest proximity measurement in each of a positive X direction, a negative X direction, a positive Y direction, and a negative Y direction. The processor then generates a most important object (MIO) dataset identifying the four linearly-closest proximity measurements.

Abstract: A system for proximity sensing on a marine vessel includes a main inertial measurement unit (IMU) positioned at a main installation attitude and a main location, a first proximity sensor configured to measure proximity of objects from a first sensor location, and a first sensor IMU positioned at the first sensor location and at a first installation attitude. A sensor processor is configured to receive main IMU data from the main IMU and first IMU data from the first sensor IMU, and then determine a relative orientation transform between the main installation attitude and the first installation attitude by comparing the main IMU data and the first IMU data, and then determine a relative position transform between the main location and the first sensor location based on the relative orientation transform, the main IMU data, and the first IMU data.

Abstract: Disclosed are systems and methods of sensor fusion for exemplary use with robotic navigation control. Systems and methods include providing local estimates of a target location from a plurality of expert modules that process sensor data. The local estimates are weighted based upon a Mahalanobis distance from an expected estimated value and based upon a Euclidean distance between the local estimates. The local estimates are fused in a Bayesian fusion center based upon the weight given to each of the local estimates.

Abstract: A method validates an obstacle identification system. In order to be able to demonstrate that obstacles are identified by an obstacle identification system at least as reliably as by a driver, it is provided that, in order to form driving scenarios, stochastic combinations of prespecified distributions of submodules are provided. The provided combinations are subjected first, for carrying out a simulation study, to simulation by a simulator and second to automatic processing by an obstacle identification algorithm of the obstacle identification system, and a result of a simulation study, which is carried out by the simulator, and a result of the automatic processing are automatically tested for agreement.

Abstract: A method, apparatus, and computer program product are provided for map matching probe data to map elements. Methods may include: receiving a plurality of probe data points, where each probe data point includes location information associated with the probe apparatus and time information associated with the location information; establishing locations of the probe data points of a probe apparatus temporally sequenced along a path; establishing a radius around each of the probe data points; identifying map elements found within each radius; filtering probe data points to obtain a subset of probe data points; establishing correspondences between map elements found within each radius of the subset of probe data points; and map matching the subset of probe data points to one or more road segments based on the correspondences between map elements found within each radius of the subset of probe data points.

Abstract: Controlling an unmanned aerial vehicle to traverse a portion of an operational environment of the unmanned aerial vehicle may include obtaining an object detection type, obtaining object detection input data, obtaining relative object orientation data based on the object detection type and the object detection input data, and performing a collision avoidance operation based on the relative object orientation data. The object detection type may be monocular object detection, which may include obtaining the relative object orientation data by obtaining motion data indicating a change of spatial location for the unmanned aerial vehicle between obtaining the first image and obtaining the second image based on searching along epipolar lines to obtain optical flow data.

Abstract: A calibrating device for calibrating vehicle assistance systems is described. The device includes: at least one target pattern; at least one sensor, which is designed to detect the position and the orientation of a vehicle to be measured with respect to the calibrating device; and a positioning device, which is designed to position the at least one target pattern on the basis of the position of the vehicle to be measured, which is detected by the at least one sensor, in such a way that the at least one target pattern is situated in a specified orientation at a specified position with respect to the vehicle to be measured.

Abstract: An automatic steering device may include a route calculator, an indirect target point calculating module, a command steering angle calculating module, and a steering controlling module. The route calculator may calculate a route of a ship based on positions of a plurality of target points. The indirect target point calculating module may calculate an indirect target point ahead of the ship. The command steering angle calculating module may calculate a command steering angle based on a positional relation between the route and the indirect target point. The steering controlling module may control a steering mechanism of the ship based on the command steering angle.

Abstract: A machine learning device training a learning model unique to a vehicle is provided with: a processor configured to use training data sets including values of state parameters detected by detectors provided at the vehicle, to train the learning model; and if an abnormality occurs in values of a state parameter detected by a detector, acquire values of the state parameter, where an abnormality has occurred, detected by another vehicle under conditions matching detection conditions when the values of the state parameter included in the training data sets were detected by the detector. If an abnormality occurs in values of the state parameter detected by the detector, the training part uses training data sets including values acquired from another vehicle by the parameter value acquiring part, instead of the values of the state parameter where an abnormality has occurred detected by the detector, to train the leaning model.

Abstract: Artificial-intelligence-based river information system. In an embodiment, a first training dataset is used to train a travel time prediction model to predict a travel time along the waterway for a given trip. In addition, a second training dataset is used to train a river level prediction model to predict a river level along the waterway for a given time. For each of a plurality of trips, a request is received that specifies the trip and a time of the trip, and, in response to the request, the travel time prediction model is used to predict a travel time for the trip, and the river level prediction model is used to predict a river level of the waterway at one or more points along the trip. Then, a voyage plan is generated based on one or both of the predicted travel time and the predicted river level.

Abstract: A vehicle seat can be configured to selectively provide support to a vehicle occupant in conditions when lateral acceleration is experienced. An actuator can be located within the vehicle seat. When activated, the actuator cause a portion of the seat to morph into an activated configuration. The actuator can be activated based on vehicle speed, steering angle, and/or lateral acceleration. The actuator can include a main body member, a first end member pivotably connected to a first end region of the main body member, and a second end member pivotably connected to a second end region of the main body member. The actuator can include shape memory material connecting members. The actuator can be configured such that, in response to an activation input, the shape memory material connecting members contract, causing the first and second end members pivot, which causes the actuator to morph into an activated configuration.

Abstract: The present disclosure provides an obstacle detection method as well as an apparatus and a robot using the same. The method includes: obtaining, through the sensor module, image(s); detecting an obstacle image of an obstacle from the image(s) according to characteristic(s) of the obstacle; extracting image feature(s) of the obstacle; obtaining, through the sensor module, a position of the obstacle; associating the image feature(s) of the obstacle with the position of the obstacle; calculating a motion state a the obstacle based on the position information of the obstacle at different moments; and estimating the position of the obstacle in a detection blind zone of the robot based on the motion state. In such a manner, it is capable of providing more accurate position information of the obstacle in the detection blind zone, which is beneficial to the robot to plan a safe and fast moving path.

Abstract: Methods and systems according to one or more examples are provided for avoiding foreign object strikes on rotorcraft vehicles. In one example, a vehicle comprises a rotor comprising a rotor blade, a first sensor configured to provide first sensor information associated with an object proximate the vehicle, and a second sensor configured to provide second sensor information associated with the rotor. The vehicle further comprises a processor coupled to the first sensor and the second sensor configured to selectively control the rotor to minimize damage to the vehicle by the object based on the first and second sensor information.

Abstract: This disclosure relates to an electrified vehicle and a method for gradually adjusting a displayed state of charge. An exemplary electrified vehicle includes a battery, a display configured to display a state of charge of the battery, and a controller configured to adjust the displayed state of charge such that the displayed state of charge gradually converges to an estimated state of charge of the battery.

Abstract: A robot includes a base, a spin body rotatably connected to the base, a tilting base tiltably connected at a tilting shaft to the spin body, a first tilting housing to which the tilting base is fixed therein, a second tilting housing which is fastened to the first tilting housing and to which the tilting base is fixed therein, and a tilting supporter connecting an inner side of the first tilting housing and an inner side of the second tilting housing. The tilting supporter is disposed at a position through which a rotational axis of the spin body passes.

Abstract: It is possible simply switch between a mode of causing one robot to perform an operation independently from another robot and another mode of causing one robot and another robot to perform an operation in cooperation. A robot system includes a first-type robot, a first-type control part which takes charge of drive control of the first-type robot, a second-type robot, and a second-type control part which takes charge of drive control of the second-type robot. When the first-type robot and the second-type robot perform an operation on the same object in cooperation, a control part in charge of drive control of the second-type robot is changed from the second-type control part to the first-type control part, and the first-type control part takes charge of drive control of the first-type robot and the second-type robot.

Abstract: An enhanced flight control system and method providing a technological improvement over a conventional flight control systems. A control module employs rules to determine whether or not a received traffic collision avoidance system (TCAS) evasive maneuver is automatically implemented. Specifically, the control module effectively couples the TCAS to the FMS, allowing access to the flight plan and to the navigation database and the approach procedures and runway data therein. An algorithm determines when there is a co-occurrence of the conditions (1) a flight plan uploaded in the FMS, (2) autopilot is engaged, (3) VNAV is engaged. Upon co-occurrence of (1) and (2) and (3), and an evasive maneuver is received from a TCAS, the control module determines whether or not to automatically implement the evasive maneuver. Look ahead algorithms may also analyse and modify the flight plan to preclude TCAS alerts and evasive procedures being required.

Abstract: Techniques are disclosed herein for reconfiguring reprogrammable hardware in an autonomous vehicle system. According to an embodiment, an autonomous driving system includes sensors and a configurable circuit having physical logic units. The autonomous driving system aggregates data observed from each of the sensors. The autonomous driving system detects a trigger indicative of a defect in the configurable circuit. The defect is identified as a function of the aggregated data. The autonomous driving system performs, in response to the trigger, a reconfiguration action on the configurable circuit to repair the defect.