Challenges in Perception and Decision Making for Intelligent Automotive Vehicles: A Case Study

Okumura, Bunyo; James, M. R.; Kanzawa, Yuchi; Derry, Matthew; Sakai, Katsuhiro; Nishi, Tomoki; Prokhorov, Danil

doi:10.1109/tiv.2016.2551545

Cited by 71 publications

(37 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Compared to intersections, roundabouts are even more challenging given the stringent time constraints on yielding and merging maneuvers. [30] reviews related studies and proposes an action planning method to enable an autonomous car to merge into a roundabout. While there are many studies focusing on intersections and roundabouts, [16], [19]- [31].…”

Section: Driveability Factorsmentioning

confidence: 99%

Is it Safe to Drive? An Overview of Factors, Metrics, and Datasets for Driveability Assessment in Autonomous Driving

Guo¹,

Kurup²,

Shah³

2020

IEEE Trans. Intell. Transport. Syst.

145

View full text Add to dashboard Cite

With recent advances in learning algorithms and hardware development, autonomous cars have shown promise when operating in structured environments under good driving conditions. However, for complex, cluttered and unseen environments with high uncertainty, autonomous driving systems still frequently demonstrate erroneous or unexpected behaviors, that could lead to catastrophic outcomes. Autonomous vehicles should ideally adapt to driving conditions; while this can be achieved through multiple routes, it would be beneficial as a first step to be able to characterize Driveability in some quantified form. To this end, this paper aims to create a framework for investigating different factors that can impact driveability. Also, one of the main mechanisms to adapt autonomous driving systems to any driving condition is to be able to learn and generalize from representative scenarios. The machine learning algorithms that currently do so learn predominantly in a supervised manner and consequently need sufficient data for robust and efficient learning. Therefore, we also perform a comparative overview of 45 public driving datasets that enable learning and publish this dataset index at https://sites.google.com/view/driveability-surveydatasets. Specifically, we categorize the datasets according to use cases, and highlight the datasets that capture complicated and hazardous driving conditions which can be better used for training robust driving models. Furthermore, by discussions of what driving scenarios are not covered by existing public datasets and what driveability factors need more investigation and data acquisition, this paper aims to encourage both targeted dataset collection and the proposal of novel driveability metrics that enhance the robustness of autonomous cars in adverse environments.

show abstract

Section: Driveability Factorsmentioning

confidence: 99%

Is it Safe to Drive? An Overview of Factors, Metrics, and Datasets for Driveability Assessment in Autonomous Driving

Guo¹,

Kurup²,

Shah³

2020

IEEE Trans. Intell. Transport. Syst.

145

View full text Add to dashboard Cite

show abstract

“…3. Qualitative analysis of test environments for automated driving in simple and complex structured environments (based on [2], [6], [1], [9], [4], [11]) selection of these test criteria are used to rate existing test environments for the use in test scenarios with pedestrians.…”

Section: Problem Descriptionmentioning

confidence: 99%

“…A classification in representative target groups might be advantageous. [2], [6], [1], [9], [4], [11], [12]) Fig. 5 summarizes a qualitative evaluation of existing test methods with important criteria.…”

Section: B Evaluation For Test Environments With Criteria In Collisimentioning

confidence: 99%

See 1 more Smart Citation

“Pedestrian in the loop”: An approach using virtual reality

Hartmann

Viehweger

Desmet

et al. 2017

2017 XXVI International Conference on Information, Communication and Automation Technologies (ICAT)

View full text Add to dashboard Cite

Abstract-A large number of testing procedures have been developed to ensure vehicle safety in common and extreme driving situations. However, these conventional testing procedures are insufficient for testing autonomous vehicles. They have to handle unexpected scenarios with the same or less risk a human driver would take. Currently, safety related systems are not adequately tested, e.g. in collision avoidance scenarios with pedestrians. Examples are the change of pedestrian behaviour caused by interaction, environmental influences and personal aspects, which cannot be tested in real environments. It is proposed to use Virtual Reality techniques. This method can be seen as a new Pedestrian in the Loop testing procedure.

show abstract

“…Testing of autonomous vehicles for complex and uncertain environments has become one of the biggest challenges in the automotive industry. Automation and computational intelligence will increase abilities of the vehicle [1]. The environment perception and situation understanding will be covered, by computer algorithms.…”

Section: Introductionmentioning

confidence: 99%

“Pedestrian in the Loop”: An Approach Using Augmented Reality

Hartmann

Viehweger

Stolz

et al. 2018

SAE Technical Paper Series

View full text Add to dashboard Cite

A large number of testing procedures have been developed to ensure vehicle safety in common and extreme driving situations. However, these conventional testing procedures are insufficient for testing autonomous vehicles. They have to handle unexpected scenarios with the same or less risk a human driver would take. Currently, safety related systems are not adequately tested, e.g. in collision avoidance scenarios with pedestrians. Examples are the change of pedestrian behaviour caused by interaction, environmental influences and personal aspects, which cannot be tested in real environments. It is proposed to use augmented reality techniques. This method can be seen as a new (Augmented) Pedestrian in the Loop testing procedure.

show abstract

Challenges in Perception and Decision Making for Intelligent Automotive Vehicles: A Case Study

Cited by 71 publications

References 28 publications

Is it Safe to Drive? An Overview of Factors, Metrics, and Datasets for Driveability Assessment in Autonomous Driving

Is it Safe to Drive? An Overview of Factors, Metrics, and Datasets for Driveability Assessment in Autonomous Driving

“Pedestrian in the loop”: An approach using virtual reality

“Pedestrian in the Loop”: An Approach Using Augmented Reality

Contact Info

Product

Resources

About