Uncertainty in Machine Learning: A Safety Perspective on Autonomous Driving

Shafaei, Sina; Kugele, Stefan; Osman, Mohd Hafeez; Knoll, Alois

doi:10.1007/978-3-319-99229-7_39

Cited by 52 publications

(31 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When applying this method to this field, research is centered on obstacle management for autonomous driving from various approaches. For example, in terms of the epistemic uncertainty of images [ 115 ], semantic segmentation methods achieve high inference classification accuracy in object recognition within interior spaces [ 116 ] or in different other additional challenges, as listed in [ 117 ].…”

Section: Computational Methods For Decision-making Under Uncertaintymentioning

confidence: 99%

Decision-Making under Uncertainty for the Deployment of Future Hyperconnected Networks: A Survey

Alzate-Mejía

Santos-Boada

Amazonas

2021

Sensors

View full text Add to dashboard Cite

Among the several emerging dimensioning, control and deployment of future communication network paradigms stands out the human-centric characteristic that creates an intricate relationship between telematics and human activities. The hard to model dynamics of user behavior introduces new uncertainties into these systems that give rise to difficult network resource management challenges. According to this context, this work reviews several decision-making computational methods under the influence of uncertainties. This work, by means of a systematic literature review, focuses on sensor-based Internet of Things scenarios such as Smart Spaces and Industry 4.0. According to our conclusions, it is mandatory to establish a means for modeling the human behavior context in order to improve resource assignment and management.

show abstract

Section: Computational Methods For Decision-making Under Uncertaintymentioning

confidence: 99%

Decision-Making under Uncertainty for the Deployment of Future Hyperconnected Networks: A Survey

Alzate-Mejía

Santos-Boada

Amazonas

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…The main challenge for MOT is the unknown correspondence between objects and measurements, which makes it necessary for the algorithms to infer such information [6]. Additionally, in many applications it is important that tracking systems provide accurate uncertainty estimates of their outputs, so that decision-making systems can take robust actions [7]. Evaluating the quality of MOT methods is also challenging, due to the lack of knowledge about the correct correspondence between the ground-truth set of object states and the tracker's state estimates and the associated uncertainties [8].…”

Section: Introductionmentioning

confidence: 99%

“…3) Other Common MOT Filters: The same assignment problem defined in (7) can be used to efficiently compute other special cases of the PMBM density. For instance, the PMB density is a special case of the PMBM with a single MB component (H = 1) [5], and the MBM density is a PMBM where λ(x) = 0, ∀x [5].…”

Section: Introductionmentioning

confidence: 99%

An Uncertainty-Aware Performance Measure for Multi-Object Tracking

Pinto

Xia

Svensson

et al. 2021

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

Evaluating the performance of multi-object tracking (MOT) methods is not straightforward, and existing performance measures fail to consider all the available uncertainty information in the MOT context. This can lead practitioners to select models which produce uncertainty estimates of lower quality, negatively impacting any downstream systems that rely on them. Additionally, most MOT performance measures have hyperparameters, which makes comparisons of different trackers less straightforward. We propose the use of the negative log-likelihood (NLL) of the multi-object posterior given the set of groundtruth objects as a performance measure. This measure takes into account all available uncertainty information in a sound mathematical manner without hyperparameters. We provide efficient algorithms for approximating the computation of the NLL for several common MOT algorithms, show that in some cases it decomposes and approximates the widely-used GOSPA metric, and provide several illustrative examples highlighting the advantages of the NLL in comparison to other MOT performance measures.

show abstract

“…In spite of the promising results on the application of machine learning methods in the overtaking control strate-B. Németh, T. Hegedűs gies, a crucial problem is the lack of performance guarantees, see [9]. A current issue is how it is possible to quantify and guarantee performance levels of a machinelearning-based agent in the sense of the control theory.…”

Section: Introductionmentioning

confidence: 99%

Performance Guarantees on Machine-Learning-based Overtaking Strategies for Autonomous Vehicles

Németh

Hegedüs

Gáspár

2020

2020 European Control Conference (ECC)

View full text Add to dashboard Cite

The control of autonomous vehicles in overtaking scenarios is an important challenge, in which an autonomous vehicle in a multiple vehicle environment must be safely driven. Due to the complexity of vehicle scenarios, several machinelearning-based design strategies have been developed, which provide outstanding results. However, in most of these methods it is difficult to provide a theoretical guarantee on the most important performance of the overtaking strategy, i.e., the avoidance of collisions with the surrounding vehicles. This paper proposes a design architecture with which this performance can be guaranteed. The method is based on the robust control framework and it is independent from the structure of the machine-learning-based agent. The effectiveness of the method is illustrated through simulation examples.

show abstract

Uncertainty in Machine Learning: A Safety Perspective on Autonomous Driving

Abstract: The user has requested enhancement of the downloaded file.

Cited by 52 publications

References 9 publications

Decision-Making under Uncertainty for the Deployment of Future Hyperconnected Networks: A Survey

Decision-Making under Uncertainty for the Deployment of Future Hyperconnected Networks: A Survey

An Uncertainty-Aware Performance Measure for Multi-Object Tracking

Performance Guarantees on Machine-Learning-based Overtaking Strategies for Autonomous Vehicles

Contact Info

Product

Resources

About