Rule-based optimal control for autonomous driving

Xiao, Wei; Mehdipour, Noushin; Collin, Anne; Bin-Nun, Amitai Y.; Tebbens, Radboud Duintjer; Belta, Călin

doi:10.1145/3450267.3450542

Cited by 45 publications

(28 citation statements)

References 30 publications

(103 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Refs. [13], [17] propose sets of rules using temporal logic that AVs should strive to follow, such as minimizing collisions, staying within lane, and driving below the speed limit. Ref.…”

Section: A Av Performance Representationmentioning

confidence: 99%

Plane and Sample: Maximizing Information about Autonomous Vehicle Performance using Submodular Optimization

Collin¹,

Bin-Nun²,

Tebbens³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

As autonomous vehicles (AVs) take on growing Operational Design Domains (ODDs), they need to go through a systematic, transparent, and scalable evaluation process to demonstrate their benefits to society. Current scenario sampling techniques for AV performance evaluation usually focus on a specific functionality, such as lane changing, and do not accommodate a transfer of information about an AV system from one ODD to the next. In this paper, we reformulate the scenario sampling problem across ODDs and functionalities as a submodular optimization problem. To do so, we abstract AV performance as a Bayesian Hierarchical Model, which we use to infer information gained by revealing performance in new scenarios. We propose the information gain as a measure of scenario relevance and evaluation progress. Furthermore, we leverage the submodularity, or diminishing returns, property of the information gain not only to find a near-optimal scenario set, but also to propose a stopping criterion for an AV performance evaluation campaign. We find that we only need to explore about 7.5% of the scenario space to meet this criterion, a 23% improvement over Latin Hypercube Sampling.

show abstract

“…Refs. [13], [17] propose sets of rules using temporal logic that AVs should strive to follow, such as minimizing collisions, staying within lane, and driving below the speed limit. Ref.…”

Section: A Av Performance Representationmentioning

confidence: 99%

Plane and Sample: Maximizing Information about Autonomous Vehicle Performance using Submodular Optimization

Collin¹,

Bin-Nun²,

Tebbens³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…A violation metric is a function specific to a rule that takes as input a realization, and outputs a violation score that captures the degree of violation of the rule by ego's trajectory over the duration of the realization [1]. For example, we can define the violation score for the "drive under the speed limit" rule as the square (L2) norm of how much ego drives faster than the speed limit over the duration of the realization [13].…”

Section: A Rulesmentioning

confidence: 99%

“…Central to this paper is the Rulebooks approach [1], which proposes a set of interpretable rules endowed with a priority structure to rank driving behaviors. The priority structure can be a pre-order [1] or a total order over equivalence classes [13]. We also examine interpretable Machine Learning (ML) models, including Bayesian networks, decision trees, and linear support vector machines, as well as non-interpretable ML models such as random forests and neural networks to explore the interpretability vs performance trade-off.…”

Section: Introductionmentioning

confidence: 99%

The Reasonable Crowd: Towards evidence-based and interpretable models of driving behavior

Helou¹,

Dusi²,

Collin³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Autonomous vehicles must balance a complex set of objectives. There is no consensus on how they should do so, nor on a model for specifying a desired driving behavior. We created a dataset to help address some of these questions in a limited operating domain. The data consists of 92 traffic scenarios, with multiple ways of traversing each scenario. Multiple annotators expressed their preference between pairs of scenario traversals. We used the data to compare an instance of a rulebook [1], carefully hand-crafted independently of the dataset, with several interpretable machine learning models such as Bayesian networks, decision trees, and logistic regression trained on the dataset. To compare driving behavior, these models use scores indicating by how much different scenario traversals violate each of 14 driving rules. The rules are interpretable and designed by subject-matter experts. First, we found that these rules were enough for these models to achieve a high classification accuracy on the dataset. Second, we found that the rulebook provides high interpretability without excessively sacrificing performance. Third, the data pointed to possible improvements in the rulebook and the rules, and to potential new rules. Fourth, we explored the interpretability vs performance trade-off by also training non-interpretable models such as a random forest. Finally, we make the dataset publicly available to encourage a discussion from the wider community on behavior specification for AVs. Please find it at github.com/bassam-motional/Reasonable-Crowd.

show abstract

“…It has been a challenging task to design a controller for autonomous driving. Conventional approaches to design a controller are based on rule-based methods [1]- [4], reinforcement learning (RL) [5]- [8], and imitation learning (IL) [9]- [12]. However, rule-based methods are not proficient at covering all exception cases due to the diversity of exceptions in the open road.…”

Section: Introductionmentioning

confidence: 99%

Towards Defensive Autonomous Driving: Collecting and Probing Driving Demonstrations of Mixed Qualities

Oh¹,

Lee²,

Park³

et al. 2021

Preprint

View full text Add to dashboard Cite

Designing or learning an autonomous driving policy is undoubtedly a challenging task as the policy has to maintain its safety in all corner cases. In order to secure safety in autonomous driving, the ability to detect hazardous situations, which can be seen as an out-of-distribution (OOD) detection problem, becomes crucial. However, most conventional datasets only provide expert driving demonstrations, although some non-expert or uncommon driving behavior data are needed to implement a safety guaranteed autonomous driving platform. To this end, we present a novel dataset called the R3 Driving Dataset, composed of driving data with different qualities. The dataset categorizes abnormal driving behaviors into eight categories and 369 different detailed situations. The situations include dangerous lane changes and near-collision situations. To further enlighten how these abnormal driving behaviors can be detected, we utilize different uncertainty estimation and anomaly detection methods to the proposed dataset. From the results of the proposed experiment, it can be inferred that by using both uncertainty estimation and anomaly detection, most of the abnormal cases in the proposed dataset can be discriminated. The dataset of this paper can be downloaded from https://rllab-snu.github.io/projects/R3-Driving-Dataset/doc.html.

show abstract

Rule-based optimal control for autonomous driving

Abstract: where he is the Director of the BU Robotics Lab. His research focuses on dynamics and control theory, with particular emphasis on hybrid and cyber-physical systems, formal synthesis and verification, with applications to robotics, autonomous driving, and systems biology.

Cited by 45 publications

References 30 publications

Plane and Sample: Maximizing Information about Autonomous Vehicle Performance using Submodular Optimization

Plane and Sample: Maximizing Information about Autonomous Vehicle Performance using Submodular Optimization

The Reasonable Crowd: Towards evidence-based and interpretable models of driving behavior

Towards Defensive Autonomous Driving: Collecting and Probing Driving Demonstrations of Mixed Qualities

Contact Info

Product

Resources

About