Adaptive Mobile Robot System with Knowledge-Driven Architecture

• US 20090187278A1
• Filed: 12/27/2007
• Published: 07/23/2009
• Est. Priority Date: 04/17/2007
• Status: Active Grant

• Current Assignee: Yefim Zhuk
• Original Assignee: Yefim Zhuk
• Inventors: Zhuk, Yefim
• Granted Patent: US 7,966,093 B2
• Time in Patent Office: Days
• US Class Current: 700/246
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G05D 1/0278 using satellite positioning signals, e.g. GPS
• CPC Class Codes: G05D 1/0291 Fleet control monitoring fleets in traffic control systems for road vehicles G08G1/127, G08G1/127
• CPC Class Codes: G06N 3/008 based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour

Abstract

The invention integrates software and knowledge engineering with robotics technology to improve robot-to-robot and robot-to-human conversational interface and provide on-the-fly translations of situational requirements into adaptive behavior models and further down to service scenarios for a collaborative robot teams.

Claims

1. An adaptive mobile robot system comprising multiple robots connected via wireless network and sharing tasks and data with specialized knowledge nodes and subject matter experts while translating new and changeable situational task requirements into adaptive behavior models and down to orchestrated service scenarios executed by robots

2. The robot of claim 1, further comprising distributed knowledge node connected to a Scenario Orchestration Engine, which transforms service scenarios into rule-based service invocations on a hierarchy of robot controllers

3. The distributed knowledge node of claim 2, further comprising Conversation Manager which enables multi-directional data exchange between the knowledge nodes and subject matter experts while resolving new situational data and requirements into a well formatted service scenario

4. The distributed knowledge node of claim 2, further comprising Specialized Data Interpreter, Natural Language Interpreter, and Scenario Data interpreter and Formatter, which parse incoming data trying to transform them into scenario formats and report their results to the Conversation Manager, which can send a request for more information or assembles successful results into service scenarios and knowledge rules

5. The distributed knowledge node of claim 2, further comprising Service Dictionary with multiple service descriptions, which stores service scenarios that represent a set of skills for a robot or a specialized knowledge node

6. The distributed knowledge node of claim 2, further comprising Knowledgebase, which includes pre-defined fundamental concepts, generic facts, and rules and enables knowledge update

7. The distributed knowledge node of claim 2, further comprising the Knowledge Bus Manager, which supports publish and subscribe mechanisms for multiple knowledge topics;

based on knowledge topics enables information exchange between subject matter experts and multiple knowledge nodes, including specialized and built-in robots;

distinguishes incoming data types and direct data to proper data interpreters and conversational manager inside the knowledge nodes

8. The specialized or built-in robot distributed knowledge node of claim 2 may participate in collaborative action by multiple robots and specialized knowledge nodes and can be assigned at run-time to play a specific role in this collaborative action

9. Multiple Distributed Knowledge Nodes of claim 2 may respond to the situational requirements when requirements match knowledge topics registered in their Knowledge Bus Managers

10. The Knowledge Bus Manager of claim 7 may evaluate its fitness to the situational requirements and publish its criteria indicators to the network

11. The Knowledge Bus Manager of claim 9 with the highest fitness score may register itself as the team coordinator for the request, and, when task requires more skills and efforts that can be provided by the selected coordinator, the coordinator may select and register more participants for the task based on their published criteria indicators

12. The distributed knowledge node of claim 2, further comprising the Inference Engine, which checks for Knowledgebase integrity with every information update and reports to the Conversation Manager success or failure such an update, and in the case of failure the Conversation Manager is requesting for additional information

13. The Conversational Manager of claim 3 registers initial information of situational requirements and converse with multiple parties to resolve this information into instructional scenario executable by the system

14. The Conversational Manager of claim 3 arranges data exchange between subject matter experts, Natural Language Interpreter, and Knowledgebase, that transforms situational requirements into specific rules added to the Knowledgebase and built-in or referenced by the resulting scenarios

15. The Conversational Manager of claim 3 will store the resulting scenario in the Service Dictionary increasing this way the set of skills of a particular robot or a specialized knowledge node

16. The Scenario Data Interpreter and Formatter of claim 4 contacts the Service Dictionary to check if any parts of the scenario can be resolved via existing scenarios stored in the Service Dictionary

17. The Specialized Data Interpreter of claim 4 can enables interpretation of special data types, for example coming from robot mechanical, video, or other sensors

18. The Scenario Data Interpreter and Formatter of claim 12 receives incoming information to create formatted service scenarios, which consist of service invocations and business logics or conditions provided by references to existing Knowledgebase rules or built-in scenario rules based on existing Knowledgebase rules expressed in close to natural language format, for example, with associated noun-constants, verb-predicates, and etc.

19. The Scenario Data Interpreter and Formatter of claim 12 reports completed scenario to the Conversational Manager and further to the Knowledge Bus Manager which can store a new scenario in the Service Dictionary and send it for execution to the Service Orchestration Engine of the current distributed node or if team responding to the task consists from more than one member, the scenario can be sent to another node selected by the team coordinator'"'"'s Knowledge Bus Manager

20. The Service Orchestration Engine of claim 2 makes the final transformation of the service scenarios into service invocations of robot controllers using the Service Dictionary where operations on robot sensors, drivers, and all kinds of controlled elements are stored as services

21. The Knowledge Bus Manager of claim 7 can receive new data from robot sensors and other sources during the execution of a scenario and arrange a new cycle of transformation of situational information into another executable scenario