NTT DATA Automobiligence Research Center, Ltd.
NTT DATA Group

For Our Future

Advanced Laboratory

GARDEN

Self-driving scenario-based verification platform

Challenge

Extensive running tests are required to secure the quality of a self-driving system.
It is impossible to guarantee all scenes are covered.

Countermeasures (Implemented Content)

For targeted use cases such as scenes of junctions and accidents, a comprehensive scenario-based approach implementing verification should be introduced.
To introduce virtual simulation environment with parallel batch-processing for many scenarios.

GARDEN verifies self-driving software based on scenarios.
It is a comprehensive verification environment (platform) generating scenarios automatically and realizing precise and efficient verification with various simulators.

1. Scenario-based approach is introduced to make scenarios from accumulated knowledge.

By extracting critical scenarios from "Road Traffic Law", "Guidelines", "Driving Data", "Accident Data", etc., it generates scenarios automatically based on rules for road signs and dynamic parameters.

2. The auto-generated extensive scenarios are narrowed down into feasible numbers with software test methods and rule models.

The logical combination is extracted with N-wisemethod.

3. The scenarios are executed by linking with UE4, CarSIM, MATLAB/Simulink, etc., and tests are implemented in a high-quality virtual environment.

In addition to high-quality visual images, you can reduce verification man-hours in real space by generating point group data through LiDARfunction.

GARDEN

RB(RuleBase)

Rule-based platform for edge intelligence

Background/Challenge

It is too risky to completely rely on deep-learning type AI for life-critical controls such as self-driving.Therefore, it is important to control AI for monitoring derived from deep-learning AI so that it follows traffic laws and manners based on rules.

Solution

RB(RuleBase) is a platform with a rule-based engine that can be embedded into an edge with its small footprint and with MBD tools modeling CEP (Complex Event Processing) in state transition. The target areas are all edges with intelligence, especially, it is especially attracting attention from businesses in the automotive area including ADAS (Advanced Driver-Assistance Systems) and already has a proven track record.

Rule-based light engine for embedded software&AI system development platform

It is a development environment where you can design rule-based engines quickly judging if a condition (rule) matches the status extracted from extensive information, and its rules, using Decision Table (DT) Editor.It supports C language and porting into various environments for embedded software is possible.

Verification to make the self-driving system operate faster

Verification to make the self-driving system operate faster

Learn rule-based architecture with Self-Driving Agent.

Learn rule-based architecture with Self-Driving Agent.

Visualization of software development process leveraging Graphic DB

Visualization of software development process leveraging Graphic DB

CONTACT

If you have any question, inquiries, or support regarding instllation or other, please feel free to contact us.