Automatic driving decision-making method and system based on knowledge graph

Abstract

An automatic driving decision-making system based on a knowledge graph comprises a knowledge graph database and a decision reinforcement learning module. The knowledge graph database maps the driving knowledge on the Internet into a triple form, and knowledge expression and reasoning are performed by using the driving knowledge graph, so that massive knowledge can be managed in a classified manner, the time spent in a traditional rule-case matching process can be shortened, and the real-time performance of knowledge retrieval is improved. The knowledge graph database obtains a driving scene, provides expert experience for the decision reinforcement learning module through a driving scene experience sample stored in the knowledge graph database, outputs a high-confidence-coefficient driving strategy to the decision module, guides the decision module to adapt to a complex and changeable traffic environment, guarantees the safety of a vehicle, and improves the safety of the vehicle. And meanwhile, the interpretability of the automatic driving decision information is realized through the knowledge graph of the knowledge graph, so that the credibility of the automatic driving decision system is improved, and the credibility of passengers on automatic driving vehicles is improved.

Description

technical field [0001] The invention relates to the field of unmanned driving technology, in particular to a knowledge graph-based automatic driving decision-making method and system. Background technique [0002] With the expansion of knowledge, the application of the concept of knowledge graph is more and more common. The knowledge graph can use the appropriate knowledge representation method to mine the connection between the data through the relational layer, which makes the knowledge easier to be circulated and collaboratively processed between computers. The knowledge graph is a graph data structure to represent the relationship between entities. Compared with simple text information, the graph representation method is easier to understand and accept. The knowledge graph is composed of "entity-relation-entity" or "entity-attribute-attribute value" relationship edges, which mainly represent the relationship between entities or between entities and attributes. [0003]...

AI Technical Summary

Problems solved by technology

[0005] The Chinese patent number is CN110288847A, and the title of the invention is "A Decision-making Method, Device, System, Storage Medium and Terminal for Automatic Driving". The invention discloses a decision-making method, device, system, storage medium and terminal for automatic driving. The information is sent to the processing module of the corresponding driving function, and the corresponding control information is generated by the processing module; The final control information of the vehicle, because the invention only directly corresponds the environmental information to the control information, the mapped states are few and the logic is simple, and the mixed state of multiple states is not considered, so it can only deal with simple scenes and cannot deal with complex and changeable actual road environment

Similarly, this invention only outputs the lane-changing decision through simple rules, without considering the mixture of multiple states, so it is only applicable to simple scenarios

Images