Interpretable Feature Generation using Deep Neural Networks and its Application to Lane Change Detection

Gallitz, Oliver; Candido, Oliver De; Botsch, Michael; Utschick, Wolfgang

doi:10.1109/itsc.2019.8917524

Cited by 11 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the increasing attention on trustworthiness and transparency of machine learning models and systems, we are seeing a focus in recent literature on explainable models for the lane change prediction task, to be able to explain the reasons behind a predicted vehicle lane change for a human user or road stakeholder. The main goal is to move away from predicting with black-box models and aiming to increase the performance of white-box models like expert systems and other explainable classifiers [10,11]. One paper by Dank et al reformulated the prediction task based on tabular data to a regression problem [8].…”

Section: Related Workmentioning

confidence: 99%

Explainable Online Lane Change Predictions on a Digital Twin with a Layer Normalized LSTM and Layer-wise Relevance Propagation

Wehner¹,

Powlesland²,

Altakrouri³

et al. 2022

Preprint

View full text Add to dashboard Cite

Artificial Intelligence and Digital Twins play an integral role in driving innovation in the domain of intelligent driving. Long shortterm memory (LSTM) is a leading driver in the field of lane change prediction for manoeuvre anticipation. However, the decision-making process of such models is complex and non-transparent, hence reducing the trustworthiness of the smart solution. This work presents an innovative approach and a technical implementation for explaining lane change predictions of layer normalized LSTMs using Layer-wise Relevance Propagation (LRP). The core implementation includes consuming live data from a digital twin on a German highway, live predictions and explanations of lane changes by extending LRP to layer normalized LSTMs, and an interface for communicating and explaining the predictions to a human user. We aim to demonstrate faithful, understandable, and adaptable explanations of lane change prediction to increase the adoption and trustworthiness of AI systems that involve humans. Our research also emphases that explainability and state-of-the-art performance of ML models for manoeuvre anticipation go hand in hand without negatively affecting predictive effectiveness.

show abstract

Section: Related Workmentioning

confidence: 99%

Explainable Online Lane Change Predictions on a Digital Twin with a Layer Normalized LSTM and Layer-wise Relevance Propagation

Wehner¹,

Powlesland²,

Altakrouri³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Similarly, [23] also used an attention model to visualize the perception of deep networks for autonomous driving. Saliency has also been employed to explain AI models for navigation [24], lane change detection [25], and driving behavior reasoning (e.g. hazard stop or red light stop) [26].…”

Section: Xai For Autonomous Drivingmentioning

confidence: 99%

“…XAI has been receiving growing attention in autonomous driving. Attempts have been made to explain the functions of various AI models for autonomous driving [21,22,23,24,25,26]. Yet, studies on XAI for AI-powered accident anticipation do not catch the accelerating pace of accident anticipation research.…”

Section: Introductionmentioning

confidence: 99%

Towards explainable artificial intelligence (XAI) for early anticipation of traffic accidents

Karim

Qin

2021

Preprint

View full text Add to dashboard Cite

Traffic accident anticipation is a vital function of Automated Driving Systems (ADSs) for providing a safety-guaranteed driving experience. An accident anticipation model aims to predict accidents promptly and accurately before they occur. Existing Artificial Intelligence (AI) models of accident anticipation lack a human-interpretable explanation of their decision-making. Although these models perform well, they remain a black-box to the ADS users, thus difficult to get their trust. To this end, this paper presents a Gated Recurrent Unit (GRU) network that learns spatio-temporal relational features for the early anticipation of traffic accidents from dashcam video data. A post-hoc attention mechanism named Grad-CAM is integrated into the network to generate saliency maps as the visual explanation of the accident anticipation decision. An eye tracker captures human eye fixation points for generating human attention maps. The explainability of network-generated saliency maps is evaluated in comparison to human attention maps. Qualitative and quantitative results on a public crash dataset confirm that the proposed explainable network can anticipate an accident on average 4.57 seconds before it occurs, with 94.02% average precision. In further, various post-hoc attention-based XAI methods are evaluated and compared. It confirms that the Grad-CAM chosen by this study can generate high-quality, human-interpretable saliency maps (with 1.42 Normalized Scanpath Saliency) for explaining the crash anticipation decision. Importantly, results confirm that the proposed AI model, with a human-inspired design, can outperform humans in the accident anticipation.

show abstract

“…Another advantage is the ability of recording various objects with a single device. Some relevant applications of aerial imagery for automotive data acquisition include the traffic flow analysis [4], the training of machine learning techniques [5] and the validation of autonomous vehicles [6].…”

Section: Introductionmentioning

confidence: 99%

Accuracy Characterization of the Vehicle State Estimation from Aerial Imagery

Morales

Kruber

Botsch

et al. 2020

2020 IEEE Intelligent Vehicles Symposium (IV)

Self Cite

View full text Add to dashboard Cite

Due to their capability of acquiring aerial imagery, camera-equipped Unmanned Aerial Vehicles (UAVs) are very cost-effective tools for acquiring traffic information. However, not enough attention has been given to the validation of the accuracy of these systems. In this paper, an analysis of the most significant sources of error is done. This includes three key components. First, a vehicle state estimation by means of statistical filtering. Second, a quantification of the most significant sources of error. Third, a benchmark of the estimated state compared with state-of-the-art reference sensors. This work presents ways to minimize the errors of the most relevant sources. With these error reductions, camera-equipped UAVs are very attractive tools for traffic data acquisition. The test data and the source code are made publicly available.

show abstract

Interpretable Feature Generation using Deep Neural Networks and its Application to Lane Change Detection

Cited by 11 publications

References 20 publications

Explainable Online Lane Change Predictions on a Digital Twin with a Layer Normalized LSTM and Layer-wise Relevance Propagation

Explainable Online Lane Change Predictions on a Digital Twin with a Layer Normalized LSTM and Layer-wise Relevance Propagation

Towards explainable artificial intelligence (XAI) for early anticipation of traffic accidents

Accuracy Characterization of the Vehicle State Estimation from Aerial Imagery

Contact Info

Product

Resources

About