System, method and apparatus for object identification

Patent metadata

Field	Value
Publication number	US-10839216-B2
Application number	US-201916272918-A
Country	US
Kind code	B2
Filing date	Feb 11, 2019
Priority date	Feb 11, 2018
Publication date	Nov 17, 2020
Grant date	Nov 17, 2020

Abstract

The present disclosure provides a system, a method and an apparatus for object identification, capable of solving the problem in the related art that a system for centralized control and management of unmanned vehicles may not be able to identify an object effectively. The system for object identification includes a sensing device, a control device and one or more unmanned vehicles. The control device is configured to determine an object not belonging to a predetermined category as an unknown object by performing object identification based on sensed data; mark the unknown object in the sensed data including the unknown object; determine an unmanned vehicle within a predetermined range from the unknown object; transmit the sensed data with the marked unknown object and an instruction to identify the unknown object to the determined unmanned vehicle; receive a feedback message from the unmanned vehicle, and when the feedback message carries information on an object category, save the information on the object category and mark a category of the unknown object as the saved object category.

First claim

What is claimed is:

1. A system for object identification, comprising a sensing device, a control device and one or more unmanned vehicles, wherein
the sensing device is configured to sense a vehicle running condition and a road condition to obtain sensed data;
the control device is configured to determine an object not belonging to a predetermined category as an unknown object by performing object identification based on the sensed data; mark the unknown object in the sensed data including the unknown object; determine an unmanned vehicle within a predetermined range from the unknown object; transmit the sensed data with the marked unknown object and an instruction to identify the unknown object to the determined unmanned vehicle; receive a feedback message from the unmanned vehicle, and when the feedback message carries information on an object category, save the information on the object category and mark a category of the unknown object as the saved object category; and
the unmanned vehicle is configured to receive the instruction and the sensed data from the control device; identify an object based on sensed data obtained at the unmanned vehicle; compare the object in the sensed data from the control device with the identified object to determine whether the unknown object marked in the sensed data has been identified, and if so, transmit to the control device the feedback message carrying the information on the object category of the identified unknown object.

2. The system of claim 1 , wherein the unmanned vehicle is further configured to mark an object corresponding to the unknown object in the sensed data obtained at the unmanned vehicle, when determining that the unknown object has not been identified, transmit to the control device a feedback message carrying identification failure information and the sensed data obtained at the unmanned vehicle with the marked object; and
the control device is further configured to transmit the sensed data obtained at the unmanned vehicle with the marked object to a human identification process when the feedback message from the unmanned vehicle carries the identification failure information; receive a feedback message from the human identification process, and when the feedback message carries information on an object category, save the information on the object category and mark the category of the unknown object as the saved object category.

3. The system of claim 2 , wherein the control device is further configured to:
when the feedback message from the human identification process carries identification failure information, transmit to a human control process the received sensed data obtained at the unmanned vehicle and a human processing request for requesting the human control process to perform an object identification based vehicle control process.

4. The system of claim 1 , wherein the control device is further configured to, subsequent to marking the unknown object in the sensed data including the unknown object: transmit the sensed data with the marked unknown object to a human identification process, and
wherein said determining the unmanned vehicle within the predetermined range from the unknown object comprises:
receiving a feedback message from the human identification process, and when the feedback message carries information on an object category, saving the information on the object category and marking the category of the unknown object as the object category; or when the feedback message carries identification failure information, determining the unmanned vehicle within the predetermined range from the unknown object.

5. The system of claim 1 , wherein the control device is further configured to perform a vehicle control process based on the identified object, the vehicle control process comprising route planning or driving policy decision.

6. A method for object identification, comprising:
determining, by a control device, an object not belonging to a predetermined category as an unknown object by performing object identification based on sensed data from a sensing device, the sensed data being obtained by the sensing device sensing a vehicle running condition and a road condition;
marking the unknown object in the sensed data including the unknown object;
determining an unmanned vehicle within a predetermined range from the unknown object;
transmitting the sensed data with the marked unknown object and an instruction to identify the unknown object to the determined unmanned vehicle; and
receiving a feedback message from the unmanned vehicle, and when the feedback message carries information on an object category, saving the information on the object category and marking a category of the unknown object as the saved object category, wherein the information on the object category carried in the feedback information is the information on the object category of the unknown object identified by the unmanned vehicle and is included in the feedback information by the unmanned vehicle in response to identifying an object based on sensed data obtained at the unmanned vehicle, comparing the object in the sensed data from the control device with the identified object and determining that the unknown object has been identified.

7. The method of claim 6 , further comprising:
receiving, by the control device, the sensed data obtained at the unmanned vehicle from the unmanned vehicle, the sensed data obtained at the unmanned vehicle including a marked object corresponding to the unknown object determined by the control device;
transmitting the sensed data obtained at the unmanned vehicle with the marked object to a human identification process when the feedback message from the unmanned vehicle carries identification failure information; and
receiving a feedback message from the human identification process, and when the feedback message carries information on an object category, saving the information on the object category and marking the category of the unknown object as the saved object category.

8. The method of claim 7 , further comprising:
transmitting, when the feedback message from the human identification process carries identification failure information, to a human control process the received sensed data obtained at the unmanned vehicle and a human processing request for requesting the human control process to perform an object identification based vehicle control process.

9. The method of claim 6 , wherein the control device is further configured to, subsequent to marking the unknown object in the sensed data including the unknown object: transmit the sensed data with the marked unknown object to a human identification process, and
wherein said determining the unmanned vehicle within the predetermined range from the unknown object comprises:
receiving a feedback message from the human identification process, and when the feedback message carries information on an object category, saving the information on the object category and marking the category of the unknown object as the object category; or when the feedback message carries identification failure information, determining the unmanned vehicle within the predetermined range from the unknown object.

10. The method of claim 6 , further comprising:
performing, by the control device, a vehicle control process based on the identified object, the vehicle control process comprising route planning or driving policy decision.

11. An apparatus for object identification, comprising a processor and at least one memory storing at least one machine executable instruction, the processor being operative to execute the at least one machine executable instruction to:
determine an

Assignees

• TuSimple
• Tusimple Inc

Inventors

• Wu Nan

Classifications

• G06V20/58 Primary

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title

• G06V20/20

  in augmented reality scenes · CPC title

• G06F18/2178

  based on feedback of a supervisor · CPC title

• G06F18/22

  Matching criteria, e.g. proximity measures · CPC title

• G05D1/0212

  with means for defining a desired trajectory (involving a plurality of land vehicles G05D1/0287) · CPC title