Results 1-9 of 9.
((uid:50033316))

Bookmark and Share    
Full Text
Peer Reviewed
See detailConnected Car Platforms, A Field Trial: Are they Ready for Usage Based Insurance?
Colot, Christian UL; Robinet, François UL; Nichils, Geoffrey

in Advances in Transdisciplinary Engineering (2023)

Following a regulatory change in Europe which mandates that car manufacturers include an “eCall” system in new vehicles, many car manufacturers are adding additional services on top, so that more and more ... [more ▼]

Following a regulatory change in Europe which mandates that car manufacturers include an “eCall” system in new vehicles, many car manufacturers are adding additional services on top, so that more and more cars become connected vehicles and act like IoT sensors. In the following study, we analyse the maturity level of this new technology to build insurance products that would take vehicle usage into account. For this, the connectivity of recent cars a-priori eligible has been first tested. Then, an ad-hoc platform has been designed to collect driving data. In particular, 4 cars have been connected to this platform for periods of over one month. Our results highlight that, while this technological innovation appears very promising in the future, the pricing, the lack of uniformity of data collected and the enrollment process are currently three pain points that should be addressed to offer large-scale opportunities. In the meantime, this technology might still be used for high value use cases such as the insurance of luxurious cars. [less ▲]

Detailed reference viewed: 31 (6 UL)
Full Text
See detailMinimizing Supervision for Vision-Based Perception and Control in Autonomous Driving
Robinet, François UL

Doctoral thesis (2022)

The research presented in this dissertation focuses on reducing the need for supervision in two tasks related to autonomous driving: end-to-end steering and free space segmentation. For end-to-end ... [more ▼]

The research presented in this dissertation focuses on reducing the need for supervision in two tasks related to autonomous driving: end-to-end steering and free space segmentation. For end-to-end steering, we devise a new regularization technique which relies on pixel-relevance heatmaps to force the steering model to focus on lane markings. This improves performance across a variety of offline metrics. In relation to this work, we publicly release the RoboBus dataset, which consists of extensive driving data recorded using a commercial bus on a cross-border public transport route on the Luxembourgish-French border. We also tackle pseudo-supervised free space segmentation from three different angles: (1) we propose a Stochastic Co-Teaching training scheme that explicitly attempts to filter out the noise in pseudo-labels, (2) we study the impact of self-training and of different data augmentation techniques, (3) we devise a novel pseudo-label generation method based on road plane distance estimation from approximate depth maps. Finally, we investigate semi-supervised free space estimation and find that combining our techniques with a restricted subset of labeled samples results in substantial improvements in IoU, Precision and Recall. [less ▲]

Detailed reference viewed: 42 (5 UL)
Full Text
Peer Reviewed
See detailStriving for Less: Minimally-Supervised Pseudo-Label Generation for Monocular Road Segmentation
Robinet, François UL; Akl, Yussef UL; Ullah, Kaleem UL et al

in IEEE Robotics and Automation Letters (2022), 7(4), 10628-10634

Identifying traversable space is one of the most important problems in autonomous robot navigation and is primarily tackled using learning-based methods. To alleviate the prohibitively high annotation ... [more ▼]

Identifying traversable space is one of the most important problems in autonomous robot navigation and is primarily tackled using learning-based methods. To alleviate the prohibitively high annotation-cost associated with labeling large and diverse datasets, research has recently shifted from traditional supervised methods to focus on unsupervised and semi-supervised approaches. This work focuses on monocular road segmentation and proposes a practical, generic, and minimally-supervised approach based on task-specific feature extraction and pseudo-labeling. Building on recent advances in monocular depth estimation models, we process approximate dense depth maps to estimate pixel-wise road-plane distance maps. These maps are then used in both unsupervised and semi-supervised road segmentation scenarios. In the unsupervised case, we propose a pseudo-labeling pipeline that reaches state-of-the-art Intersection-over-Union (IoU), while reducing complexity and computations compared to existing approaches. We also investigate a semi-supervised extension to our method and find that even minimal labeling efforts can greatly improve results. Our semi-supervised experiments using as little as 1% and 10% of ground truth data, yield models scoring 0.9063 and 0.9332 on the IoU metric respectively. These results correspond to a comparative performance of 95.9% and 98.7% of a fully-supervised model's IoU score, which motivates a pragmatic approach to labeling. [less ▲]

Detailed reference viewed: 32 (6 UL)
Full Text
Peer Reviewed
See detailConnected Vehicle Platforms for Dynamic Insurance
Colot, Christian UL; Robinet, François UL; Nichil, Geoffrey et al

in in Proceedings of the 6th International Conference on Intelligent Traffic and Transportation (2022)

Detailed reference viewed: 39 (3 UL)
Full Text
Peer Reviewed
See detailWeakly-Supervised Free Space Estimation through Stochastic Co-Teaching
Robinet, François UL; Parera, Claudia UL; Hundt, Christian UL et al

in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, 2022 (2022, January 04)

Free space estimation is an important problem for autonomous robot navigation. Traditional camera-based approaches train a segmentation model using an annotated dataset. The training data needs to capture ... [more ▼]

Free space estimation is an important problem for autonomous robot navigation. Traditional camera-based approaches train a segmentation model using an annotated dataset. The training data needs to capture the wide variety of environments and weather conditions encountered at runtime, making the annotation cost prohibitively high. In this work, we propose a novel approach for obtaining free space estimates from images taken with a single road-facing camera. We rely on a technique that generates weak free space labels without any supervision, which are then used as ground truth to train a segmentation model for free space estimation. Our work differs from prior attempts by explicitly taking label noise into account through the use of Co-Teaching. Since Co-Teaching has traditionally been investigated in classification tasks, we adapt it for segmentation and examine how its parameters affect performances in our experiments. In addition, we propose Stochastic Co-Teaching, which is a novel method to select clean samples that leads to enhanced results. We achieve an IoU of 82.6%, a Precision of 90.9%, and a Recall of 90.3%. Our best model reaches 87% of the IoU, 93% of the Precision, and 93% of the Recall of the equivalent fully-supervised baseline while using no human annotations. To the best of our knowledge, this work is the first to use Co-Teaching to train a free space segmentation model under explicit label noise. Our implementation and trained models are freely available online. [less ▲]

Detailed reference viewed: 91 (22 UL)
Full Text
Peer Reviewed
See detailRefining Weakly-Supervised Free Space Estimation Through Data Augmentation and Recursive Training
Robinet, François UL; Frank, Raphaël

in Artificial Intelligence and Machine Learning (2022)

Free space estimation is an important problem for autonomous robot navigation. Traditional camera-based approaches rely on pixel-wise ground truth annotations to train a segmentation model. To cover the ... [more ▼]

Free space estimation is an important problem for autonomous robot navigation. Traditional camera-based approaches rely on pixel-wise ground truth annotations to train a segmentation model. To cover the wide variety of environments and lighting conditions encountered on roads, training supervised models requires large datasets. This makes the annotation cost prohibitively high. In this work, we propose a novel approach for obtaining free space estimates from images taken with a single road-facing camera. We rely on a technique that generates weak free space labels without any supervision, which are then used as ground truth to train a segmentation model for free space estimation. We study the impact of different data augmentation techniques on the performances of free space predictions, and propose to use a recursive training strategy. Our results are benchmarked using the Cityscapes dataset and improve over comparable published work across all evaluation metrics. Our best model reaches 83.64% IoU (+2.3%), 91.75 Precision (+2.4%) and 91.29% Recall (+0.4%). These results correspond to 88.8% of the IoU, 94.3% of the Precision and 93.1% of the Recall obtained by an equivalent fully-supervised baseline, while using no ground truth annotation. Our code and models are freely available online. [less ▲]

Detailed reference viewed: 44 (6 UL)
Full Text
Peer Reviewed
See detailRefining Weakly-Supervised Free Space Estimation through Data Augmentation and Recursive Training
Robinet, François UL; Frank, Raphaël UL

in Proceedings of BNAIC/BeneLearn 2021 (2021, November 12)

Free space estimation is an important problem for autonomous robot navigation. Traditional camera-based approaches rely on pixel-wise ground truth annotations to train a segmentation model. To cover the ... [more ▼]

Free space estimation is an important problem for autonomous robot navigation. Traditional camera-based approaches rely on pixel-wise ground truth annotations to train a segmentation model. To cover the wide variety of environments and lighting conditions encountered on roads, training supervised models requires large datasets. This makes the annotation cost prohibitively high. In this work, we propose a novel approach for obtaining free space estimates from images taken with a single road-facing camera. We rely on a technique that generates weak free space labels without any supervision, which are then used as ground truth to train a segmentation model for free space estimation. We study the impact of different data augmentation techniques on the performances of free space predictions, and propose to use a recursive training strategy. Our results are benchmarked using the Cityscapes dataset and improve over comparable published work across all evaluation metrics. Our best model reaches 83.64% IoU (+2.3%), 91:75% Precision (+2.4%) and 91.29% Recall (+0.4%). These results correspond to 88.8% of the IoU, 94.3% of the Precision and 93.1% of the Recall obtained by an equivalent fully-supervised baseline, while using no ground truth annotation. Our code and models are freely available online. [less ▲]

Detailed reference viewed: 114 (29 UL)
Full Text
Peer Reviewed
See detailRoboBus: A Diverse and Cross-Border Public Transport Dataset
Varisteas, Georgios; Frank, Raphaël UL; Robinet, François UL

in Proceedings of the 19th International Conference on Pervasive Computing and Communications (PerCom 2021) (2021, March 22)

Detailed reference viewed: 160 (30 UL)
Full Text
Peer Reviewed
See detailLeveraging Privileged Information to Limit Distraction in End-to-End Lane Following
Robinet, François UL; Demeules, Antoine; Frank, Raphaël UL et al

in 2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC) (2020)

Convolutional Neural Networks have been successfully used to steer vehicles using only road-facing cameras. In this work, we investigate the use of Privileged Information for training an end-to-end lane ... [more ▼]

Convolutional Neural Networks have been successfully used to steer vehicles using only road-facing cameras. In this work, we investigate the use of Privileged Information for training an end-to-end lane following model. Starting from the prior assumption that such a model should spend a sizeable fraction of its focus on lane markings, we take advantage of lane geometry information available at training time to improve its performance. To this end, we constrain the class of learnable functions by imposing a prior stemming from a lane segmentation task. For each input frame, we compute the set of pixels that most contribute to the prediction of the model using the VisualBackProp method. These pixel-relevance heatmaps are then compared with ground truth lane segmentation masks. A Distraction Loss term is added to the objective to regularize the training process. We learn from real-world data collected using our experimental vehicle and compare the results to those obtained using the simple Mean Squared Error objective. We show that the presence of our regularizer benefits both the performance and the stability of the model across a variety of evaluation metrics. We use a pretrained lane segmentation model without fine-tuning to extract lane marking masks and show that valuable learning signals can be extracted even from imperfect privileged knowledge. This method can be implemented easily and very efficiently on top of an existing architecture, without requiring the addition of any trainable parameter. [less ▲]

Detailed reference viewed: 195 (46 UL)