Collision avoidance assistance system
Abstract
The objective of the present disclosure is to provide a collision avoidance assistance system for assisting avoidance of collision between a ship and an obstacle using a result obtained by (i) detecting the obstacle on a ship travel route using sensors, (ii) identifying the detected obstacle, (iii) collecting sensor data, and (iv) analyzing the collected sensor data. By using the system including, as a component, a sensor group, a three dimensional viewing field acquirer, an obstacle identifier, a database regarding obstacles, an analyzer, a deep learning unit, a learning unit, and communicator, the obstacle on the ship travel route is detected and identified, and by using a result obtained by detecting, identifying, collecting, and analyzing sensor data, avoidance of collision between the ship and the obstacle is assisted.
Claims
exact text as granted — not AI-modified1 : A collision avoidance assistance system for assisting avoidance of collision between a ship and an obstacle using sensors selected from among a video camera, a color meter, a spectrometer, an infrared sensor, a temperature sensor, a radar, a device for LIDAR, a sonar, an air-speed meter, a ship-speed meter, and a global navigation satellite system (GNSS) receiver, the system comprising:
(a) three dimensional viewing field acquisition means for acquiring a three dimensional viewing field in a ship travel route by integrating sensor data obtained via sensors selected from among the video camera, the infrared sensor, and the device for LIDAR; and (b) learning means (i) for collecting the sensor data obtained via the sensors in the three dimensional viewing field in which the obstacle is located and (ii) for outputting an evaluation of the obstacle based on the collected sensor data by using a deep learning method in which a pair of the collected sensor data and the evaluation of the obstacle is used as learning data, wherein the evaluation of the obstacle includes identification information about a floating object on a sea, and the system provides, as information for assisting avoidance of collision with the obstacle, an evaluation of a current obstacle that is outputted by the learning means based on the sensor data on a current three dimensional viewing field obtained via the sensors.
2 : The collision avoidance assistance system according to claim 1 , wherein the sensors are fixed to poles included in the ship.
3 : The collision avoidance assistance system according to claim 1 , wherein
the evaluation of the obstacle further includes identification information about an object on or in the sea, and the object on or in the sea is another ship different from the ship, a buoy, or a hidden rock.
4 : The collision avoidance assistance system according to claim 1 , wherein the sensors are attached to a drone for obtaining an observation altitude and an observation distance, and the drone is connected to the ship with a wired or wireless connection.
5 : The collision avoidance assistance system according to claim 1 , wherein
the evaluation is displayed on at least one selected from among (i) a screen installed on the ship in order to warn a ship pilot, (ii) a head-up display installed on the ship, (iii) a terminal device for the ship pilot, (iv) a head mounted display for the ship pilot, and (v) a visor for the ship pilot.
6 : The collision avoidance assistance system according to claim 1 , wherein the evaluation is transmitted to an autopilot system installed in the ship and used for avoiding potential collisions.
7 : The collision avoidance assistance system according to claim 1 , wherein the evaluation is transmitted by a device for long distance communication and is shared with a database on a network or a system of another ship sailing near the ship.
8 : The collision avoidance assistance system according to claim 1 , wherein the learning data includes
a pair of (i) sensor data collected in another collision avoidance assistance system different from the system and (ii) an evaluation of the obstacle, or a pair of (i) sensor data generated as test data and (ii) an evaluation of the obstacle.
9 : The collision avoidance assistance system according to claim 1 , wherein the learning means (i) collects sensor data in a plurality of collision avoidance assistance systems connected to one another via communication and (ii) uses, as learning data, a pair of the collected sensor data and an evaluation of the obstacle.Join the waitlist — get patent alerts
Track US2020216152A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.