Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer

Shao, Hu; Wang, LeTian; Chen, RuoBing; Li, Hongsheng; Liu, Yu

doi:10.48550/arxiv.2207.14024

Cited by 5 publications

(4 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To satisfy this time-varying power balance constraint, the safety layer provides a feasible solution space, which enables the RL agent to explore safely in it. Such a safety layer is common in many other similar tasks with high-security requirements [31,32].…”

Section: Das Model-free Rl Gridzeromentioning

confidence: 99%

Real-time scheduling of renewable power systems through planning-based reinforcement learning

Liu¹,

Wang²,

Ye³

et al. 2023

Preprint

View full text Add to dashboard Cite

The growing renewable energy sources have posed significant challenges to traditional power scheduling. It is difficult for operators to obtain accurate day-ahead forecasts of renewable generation, thereby requiring the future scheduling system to make real-time scheduling decisions aligning with ultra-short-term forecasts. Restricted by the computation speed, traditional optimization-based methods can not solve this problem. Recent developments in reinforcement learning (RL) have demonstrated the potential to solve this challenge. However, the existing RL methods are inadequate in terms of constraint complexity, algorithm performance, and environment fidelity. We are the first to propose a systematic solution

show abstract

Section: Das Model-free Rl Gridzeromentioning

confidence: 99%

Real-time scheduling of renewable power systems through planning-based reinforcement learning

Liu¹,

Wang²,

Ye³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…However, only a few of them provide the necessary code and well-trained models for their methodologies to be evaluated and built upon. We specifically tested Interfuser [22], TCP [29], and LAV [4], all three currently in the top 5 of the leaderboard. Within a few test runs of the AI agent provided with TCP, we noticed that the ego vehicle brakes to a standstill as soon as any other vehicle arrives next to it in its adjacent lane.…”

Section: Carla Simulation Model and Ai Componentsmentioning

confidence: 99%

“…Its ScenarioRunner tool [25] further enhances its capabilities by enabling the specification of diverse and complex scenarios based on the reuse of various predefined car behaviors. Various works proposed AI-based solutions (e.g., [4,22,29]) for the perception and control components of cars that are integrated with the CARLA simulator for their validation. The CARLA community also organized a competition to compare and rank such solutions [24].…”

Section: Introductionmentioning

confidence: 99%

Automatic Generation of Scenarios for System-level Simulation-based Verification of Autonomous Driving Systems

Goyal,

Griggio,

Kimblad

et al. 2023

Electron. Proc. Theor. Comput. Sci.

View full text Add to dashboard Cite

With increasing complexity of Automated Driving Systems (ADS), ensuring their safety and reliability has become a critical challenge. The Verification and Validation (V&V) of these systems are particularly demanding when AI components are employed to implement perception and/or control functions. In ESA-funded project VIVAS, we developed a generic framework for system-level simulation-based V&V of autonomous systems. The approach is based on a simulation model of the system, an abstract model that describes symbolically the system behavior, and formal methods to generate scenarios and verify the simulation executions. Various coverage criteria can be defined to guide the automated generation of the scenarios.In this paper, we describe the instantiation of the VIVAS framework for an ADS case study. This is based on the integration of CARLA, a widely-used driving simulator, and its ScenarioRunner tool, which enables the creation of diverse and complex driving scenarios. This is also used in the CARLA Autonomous Driving Challenge to validate different ADS agents for perception and control based on AI, shared by the CARLA community. We describe the development of an abstract ADS model and the formulation of a coverage criterion that focuses on the behaviors of vehicles relative to the vehicle with ADS under verification. Leveraging the VIVAS framework, we generate and execute various driving scenarios, thus testing the capabilities of the AI components. The results show the effectiveness of VIVAS in automatically generating scenarios for system-level simulationbased V&V of an automated driving system using CARLA and ScenarioRunner. Therefore, they highlight the potential of the approach as a powerful tool in the future of ADS V&V methodologies.

show abstract

“…With the increasing development of machine learning (ML) models, their credibility has become an important issue. , The credibility of a model describes the extent to which a user can trust the model’s output; thus, it is essential for ML techniques, particularly in autonomous driving, spam filtering, and so on.…”

Section: Introductionmentioning

confidence: 99%

Interpretable Attribution Assignment for Octanol–Water Partition Coefficient

Yokogawa

Suda

2023

J. Phys. Chem. B

View full text Add to dashboard Cite

With the increasing development of machine learning models, their credibility has become an important issue. In chemistry, attribution assignment is gaining relevance when it comes to designing molecules and debugging models. However, attention has only been paid to which atoms are important in the prediction and not to whether the attribution is reasonable. In this study, we developed a graph neural network model, a highly interpretable attribution model in chemistry, and modified the integrated gradients method. The credibility of our approach was confirmed by predicting the octanol–water partition coefficient (logP) and evaluating the three metrics (accuracy, consistency, and stability) in the attribution assignment.

show abstract

Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer

Cited by 5 publications

References 36 publications

Real-time scheduling of renewable power systems through planning-based reinforcement learning

Real-time scheduling of renewable power systems through planning-based reinforcement learning

Automatic Generation of Scenarios for System-level Simulation-based Verification of Autonomous Driving Systems

Interpretable Attribution Assignment for Octanol–Water Partition Coefficient

Contact Info

Product

Resources

About