MTBF Model for AVs - From Perception Errors to Vehicle-Level Failures

Oboril, Fabian; Buerkle, Cornelius; Sussmann, Alon; Bitton, Simcha; Fabris, Simone

doi:10.1109/iv51971.2022.9827006

Cited by 4 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Proposition 1 is contrary to the well-known minimax inequality for the unconstrained case where the player acting second has the advantage [35]. Since we assume controldisturbance-affine dynamics, both the HOCBF constraint from (6) and ∇V(x, t) T f (x, u A , u B ) term from (1) are linear in control input, we can apply Proposition 1 and hence instead consider a constrained HJ reachability problem,…”

Section: Safety Concept Synthesis Via Constrained Hj Reachabilitymentioning

confidence: 99%

See 1 more Smart Citation

Learning Autonomous Vehicle Safety Concepts from Demonstrations

Leung¹,

Veer²,

Szczerbicki³

et al. 2022

Preprint

View full text Add to dashboard Cite

Evaluating the safety of an autonomous vehicle (AV) depends on the behavior of surrounding agents which can be heavily influenced by factors such as environmental context and informally-defined driving etiquette. A key challenge is in determining a minimum set of assumptions on what constitutes reasonable foreseeable behaviors of other road users for the development of AV safety models and techniques. In this paper, we propose a data-driven AV safety design methodology that first learns "reasonable" behavioral assumptions from data, and then synthesizes an AV safety concept using these learned behavioral assumptions. We borrow techniques from control theory, namely high order control barrier functions and Hamilton-Jacobi reachability, to provide inductive bias to aid interpretability, verifiability, and tractability of our approach. In our experiments, we learn an AV safety concept using demonstrations collected from a highway traffic-weaving scenario, compare our learned concept to existing baselines, and showcase its efficacy in evaluating real-world driving logs.

show abstract

Section: Safety Concept Synthesis Via Constrained Hj Reachabilitymentioning

confidence: 99%

“…planning objective [5], or for perception safety evaluation metrics [6], [7]. Critically, different behavioral assumptions lead to different safety concepts which in turn affects realized AV safety and performance.…”

Section: Introductionmentioning

confidence: 99%

Learning Autonomous Vehicle Safety Concepts from Demonstrations

Leung¹,

Veer²,

Szczerbicki³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Enhancing the Reliability of Perception Systems using N-version Programming and Rejuvenation

Mendonca

Machida

Völp

2023

2023 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)

View full text Add to dashboard Cite

puter vision, natural language processing, autonomous driving, and robotics. Its use has become a powerful ally for autonomous systems of different domains to perform complex tasks accurately and efficiently with minimal human intervention. Perception systems are one of the most crucial components for autonomous systems, such as autonomous vehicles, employing ML to execute complex perception tasks. These systems perceive and

show abstract

The Application of Driver Models in the Safety Assessment of Autonomous Vehicles: Perspectives, Insights, Prospects

Wang,

Guo,

et al. 2024

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

MTBF Model for AVs - From Perception Errors to Vehicle-Level Failures

Cited by 4 publications

References 6 publications

Learning Autonomous Vehicle Safety Concepts from Demonstrations

Learning Autonomous Vehicle Safety Concepts from Demonstrations

Enhancing the Reliability of Perception Systems using N-version Programming and Rejuvenation

The Application of Driver Models in the Safety Assessment of Autonomous Vehicles: Perspectives, Insights, Prospects

Contact Info

Product

Resources

About