Self-Driving Vehicle Verification Towards a Benchmark

Roohi, Nima; Kaur, Ramandeep; Weimer, James; Sokolsky, Oleg; Lee, Insup

doi:10.48550/arxiv.1806.08810

Cited by 4 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Related Work. Formal methods [19], [20], [21], [22], [23], [24], [25], [26], [27], [28], [29], [30], [7] have been recently used as a tool to study safety of autonomous systems. These approaches have been successful for decision systems, such as obstacle avoidance [7], road rule compliance [30] and high-level decision-making [31], where the specifications are usually model-based and have well-defined semantics [8].…”

Section: Introductionmentioning

confidence: 99%

“…Formal methods [19], [20], [21], [22], [23], [24], [25], [26], [27], [28], [29], [30], [7] have been recently used as a tool to study safety of autonomous systems. These approaches have been successful for decision systems, such as obstacle avoidance [7], road rule compliance [30] and high-level decision-making [31], where the specifications are usually model-based and have well-defined semantics [8]. However, they are challenging to apply to perception systems, due to the complexity of modeling the physical environment [20], and the trade-off between evidence for certification and tractability of the model [32].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Monitoring and Diagnosability of Perception Systems

Antonante¹,

Spivak²,

Carlone³

2020

Preprint

View full text Add to dashboard Cite

Perception is a critical component of high-integrity applications of robotics and autonomous systems, such as selfdriving vehicles. In these applications, failure of perception systems may put human life at risk, and a broad adoption of these technologies requires the development of methodologies to guarantee and monitor safe operation. Despite the paramount importance of perception systems, currently there is no formal approach for system-level monitoring. In this work, we propose a mathematical model for runtime monitoring and fault detection and identification in perception systems. Towards this goal, we draw connections with the literature on diagnosability in multiprocessor systems, and generalize it to account for modules with heterogeneous outputs that interact over time. The resulting temporal diagnostic graphs (i) provide a framework to reason over the consistency of perception outputs -across modules and over time-thus enabling fault detection, (ii) allow us to establish formal guarantees on the maximum number of faults that can be uniquely identified in a given perception system, and (iii) enable the design of efficient algorithms for fault identification. We demonstrate our monitoring system, dubbed PerSyS, in realistic simulations using the LGSVL self-driving simulator and the Apollo Auto autonomy software stack, and show that PerSyS is able to detect failures in challenging scenarios (including scenarios that have caused self-driving car accidents in recent years), and is able to correctly identify faults while entailing a minimal computation overhead (< 5ms on a single-core CPU).

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Monitoring and Diagnosability of Perception Systems

Antonante¹,

Spivak²,

Carlone³

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The modularity of our simulation framework easily allows us to modify the safety objective to an alternative definition of TTC or even include more sophisticated notions of safety, e.g. temporal-logic specifications or implementations of responsibility-sensitive safety (RSS) [49,40].…”

Section: Methodsmentioning

confidence: 99%

Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation

O'Kelly,

Sinha,

Namkoong

et al. 2018

Preprint

View full text Add to dashboard Cite

While recent developments in autonomous vehicle (AV) technology highlight substantial progress, we lack tools for rigorous and scalable testing. Real-world testing, the de facto evaluation environment, places the public in danger, and, due to the rare nature of accidents, will require billions of miles in order to statistically validate performance claims. We implement a simulation framework that can test an entire modern autonomous driving system, including, in particular, systems that employ deep-learning perception and control algorithms. Using adaptive importance-sampling methods to accelerate rare-event probability evaluation, we estimate the probability of an accident under a base distribution governing standard traffic behavior. We demonstrate our framework on a highway scenario, accelerating system evaluation by 2-20 times over naive Monte Carlo sampling methods and 10-300P times (where P is the number of processors) over real-world testing. * Equal contribution * mttc = 0.23 − crash.mp4 * mttc = 0.30.mp4 * mttc = 0.42.mp4 * mttc = 0.56.mp4 -Non-crashes: * mttc = 0.23 − nocrash.mp4 * mttc = 0.79.mp4 * mttc = 1.43.mp4 * mttc = 2.01.mp4 * mttc = 3.05.mp4 * mttc = 6.00.mp4 * mttc = 6.01.mp4 * mttc = 10.11.mp4These videos contain overhead, RGB, segmented, and depth views. We also include higherresolution RGB videos with the same base names as above but the extension " hires.mp4".

show abstract

“…Formal methods [24,25,26,27,28,29,30,31,32] have been recently used as a tool to study safety of autonomous systems. These approaches have been successful for decision systems, such as obstacle avoidance [33], road rule compliance [34], high-level decision-making [35], and control [36,37], where the specifications are usually model-based and have well-defined semantics [38].…”

Section: State Of the Artmentioning

confidence: 99%

Monitoring of Perception Systems: Deterministic, Probabilistic, and Learning-based Fault Detection and Identification

Antonante¹,

Nilsen²,

Carlone³

2022

Preprint

View full text Add to dashboard Cite

This paper investigates runtime monitoring of perception systems. Perception is a critical component of high-integrity applications of robotics and autonomous systems, such as self-driving cars. In these applications, failure of perception systems may put human life at risk, and a broad adoption of these technologies requires the development of methodologies to guarantee and monitor safe operation. Despite the paramount importance of perception, currently there is no formal approach for system-level perception monitoring. In this paper, we formalize the problem of runtime fault detection and identification in perception systems and present a framework to model diagnostic information using a diagnostic graph. We then provide a set of deterministic, probabilistic, and learning-based algorithms that use diagnostic graphs to perform fault detection and identification. Moreover, we investigate fundamental limits and provide deterministic and probabilistic guarantees on the fault detection and identification results. We conclude the paper with an extensive experimental evaluation, which recreates several realistic failure modes in the LGSVL opensource autonomous driving simulator, and applies the proposed system monitors to a state-of-the-art autonomous driving software stack (Baidu's Apollo Auto).

show abstract

Self-Driving Vehicle Verification Towards a Benchmark

Cited by 4 publications

References 16 publications

Monitoring and Diagnosability of Perception Systems

Monitoring and Diagnosability of Perception Systems

Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation

Monitoring of Perception Systems: Deterministic, Probabilistic, and Learning-based Fault Detection and Identification

Contact Info

Product

Resources

About