Tongtong Bai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tongtong Bai has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Changyou Zheng
College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007, China
2 shared publications - Song Huang
College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007, China
2 shared publications - Chunyan Xia
College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007, China
1 shared publication - Kui Yao
Army Engineering University of PLA, Nanjing 210007, Jiangsu, P. R. China
1 shared publication - Kunyuan Li
Laboratory of Intelligent Information Processing, Army Engineering University of PLA, Nanjing 210007, P. R. China
1 shared publication - Lele Sun
College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007, China
1 shared publication
Latest Publications
- Open Access
RKGRScen: Road-Network Knowledge Graph Retrieval-Based Scenario Generation for Autonomous Driving Testing
Simulation-based scenario testing is central to the safety validation of autonomous driving systems (ADS), where abstract scenarios must be instantiated into executable concrete scenarios. A key challenge in this process is road matching, which aims to identify a concrete site on a map that genuinely satisfies the road-semantic requirements of a scenario. Existing methods often reduce this step to template-based mapping or coarse geometric filtering, which capture coarse road types but fail to meet the finer structural and topological constraints of a scenario, thereby undermining the executability and behavioral fidelity of the generated scenarios. To address this, we propose RKGRScen (Road-Network Knowledge Graph Retrieval-Based Scenario Generation), which formalizes road matching as a semantic location retrieval problem over a road-network knowledge graph. Its indexing module constructs a road-network knowledge graph from OpenDRIVE maps and partitions it into topologically coherent communities annotated with LLM-generated semantic summaries and violation tags, organizing them into a searchable semantic community index. Its instantiation module then grounds each scenario onto concrete road sites through two-level global-to-local retrieval and resolves executable parameters and conflict-point timing with a constraint solver. In a scenario-quality evaluation on a CARLA Town01–Town05 map pool comprising 2649 scenarios, RKGRScen achieves an executability rate of 93.88%, an end-to-end behavior reproduction rate of 72.59%, and a road–environment matching rate of 93.43%. Therefore, RKGRScen can reliably ground high-level scenarios into executable scenarios that satisfy complex road and topological constraints, providing effective support for the safety validation of autonomous driving systems.
Open AccessRKGRScen: Road-Network Knowledge Graph Retrieval-Based Scenario Generation for Autonomous Driving Testing
Simulation-based scenario testing is central to the safety validation of autonomous driving systems (ADS), where abstract scenarios must be instantiated into executable concrete scenarios. A key challenge in this process is road matching, which aims to identify a concrete site on a map that genuinely satisfies the road-semantic requirements of a scenario. Existing methods often reduce this step to template-based mapping or coarse geometric filtering, which capture coarse road types but fail to meet the finer structural and topological constraints of a scenario, thereby undermining the executability and behavioral fidelity of the generated scenarios. To address this, we propose RKGRScen (Road-Network Knowledge Graph Retrieval-Based Scenario Generation), which formalizes road matching as a semantic location retrieval problem over a road-network knowledge graph. Its indexing module constructs a road-network knowledge graph from OpenDRIVE maps and partitions it into topologically coherent communities annotated with LLM-generated semantic summaries and violation tags, organizing them into a searchable semantic community index. Its instantiation module then grounds each scenario onto concrete road sites through two-level global-to-local retrieval and resolves executable parameters and conflict-point timing with a constraint solver. In a scenario-quality evaluation on a CARLA Town01–Town05 map pool comprising 2649 scenarios, RKGRScen achieves an executability rate of 93.88%, an end-to-end behavior reproduction rate of 72.59%, and a road–environment matching rate of 93.43%. Therefore, RKGRScen can reliably ground high-level scenarios into executable scenarios that satisfy complex road and topological constraints, providing effective support for the safety validation of autonomous driving systems.
- Open Access
- 25 March 2024
- Published by MDPI AG in Electronics
- Vol. 13 (7) , 1197
TraModeAVTest: Modeling Scenario and Violation Testing for Autonomous Driving Systems Based on Traffic Regulations
Current testing methods for autonomous driving systems primarily focus on simple traffic scenarios, generating test cases based on traffic accidents, while research on generating edge test cases for complex driving environments by traffic regulations is not adequately comprehensive. Therefore, we propose a method for scenario modeling and violation testing using an autonomous driving system based on traffic regulations named TraModeAVTest. Initially, TraModeAVTest constructs a Petri net model for complex scenarios based on the combination relationships of basic traffic regulation scenarios and verifies the consistency of the model’s design with traffic regulation requirements using formal methods, to provide a representation of traffic regulation scenario models for the violation testing of autonomous driving systems. Subsequently, based on the coverage criteria of the Petri net model, it utilizes a search strategy to generate model paths that represent traffic regulations, and employs a parameter combination method to generate test cases that cover the model paths, to test the violation behaviors of autonomous driving systems. Finally, simulation experiment results on the Baidu Apollo demonstrate that the test cases representing traffic regulations generated by TraModeAVTest can effectively identify the behaviors of autonomous vehicles violating traffic regulations, and TraModeAVTest can effectively improve the efficiency of generating different types of violation scenarios.
- 25 March 2024
- Published by MDPI AG in Electronics
- Vol. 13 (7) , 1197
Open AccessTraModeAVTest: Modeling Scenario and Violation Testing for Autonomous Driving Systems Based on Traffic Regulations
Current testing methods for autonomous driving systems primarily focus on simple traffic scenarios, generating test cases based on traffic accidents, while research on generating edge test cases for complex driving environments by traffic regulations is not adequately comprehensive. Therefore, we propose a method for scenario modeling and violation testing using an autonomous driving system based on traffic regulations named TraModeAVTest. Initially, TraModeAVTest constructs a Petri net model for complex scenarios based on the combination relationships of basic traffic regulation scenarios and verifies the consistency of the model’s design with traffic regulation requirements using formal methods, to provide a representation of traffic regulation scenario models for the violation testing of autonomous driving systems. Subsequently, based on the coverage criteria of the Petri net model, it utilizes a search strategy to generate model paths that represent traffic regulations, and employs a parameter combination method to generate test cases that cover the model paths, to test the violation behaviors of autonomous driving systems. Finally, simulation experiment results on the Baidu Apollo demonstrate that the test cases representing traffic regulations generated by TraModeAVTest can effectively identify the behaviors of autonomous vehicles violating traffic regulations, and TraModeAVTest can effectively improve the efficiency of generating different types of violation scenarios.