Context: Detecting fatigue in drivers has become increasingly important for safe driving, especially with the use of more smart devices and Internet-connected vehicles. While sharing data between vehicles can enhance fatigue detection systems, privacy concerns pose significant barriers to this sharing process. We propose a Federated Learning (FL) approach for monitoring fatigue-driven behavior to address these challenges. However, there is a concern that the drivers' private information might be leaked in the FL system. In this paper, we introduce PRIV-DRIVE, a novel approach for privacy-enhanced fatigue detection applications. Our method integrates Paillier homo-morphic encryption (PHE) with a top-k parameter selection technique, bolstering privacy and confidentiality in federated fatigue detection systems. This approach reduces communication and computation overhead while ensuring model accuracy. To the best of our knowledge, this is the first paper to implement PHE in FL setups for fatigue detection applications. We ran several experiments and evaluated the PRIV-DRIVE method. The results show substantial efficiency gains with different HE key sizes, reducing computation time by up to 96% and communication traffic by up to 95%. Importantly, these improvements have minimal impact on accuracy, effectively meeting the requirements of fatigue detection applications.

Detecting lane markings in road scenes poses a significant challenge due to their intricate nature, which is susceptible to unfavorable conditions. While lane markings have strong shape priors, their visibility is easily compromised by varying lighting conditions, adverse weather, occlusions by other vehicles or pedestrians , road plane changes, and fading of colors over time. The detection process is further complicated by the presence of several lane shapes and natural variations, necessitating large amounts of high-quality and diverse data to train a robust lane detection model capable of handling various real-world scenarios. In this paper, we present a novel self-supervised learning method termed Contrastive Learning for Lane Detection via Cross-Similarity (CLLD) to enhance the resilience and effectiveness of lane detection models in real-world scenarios, particularly when the visibility of lane markings are compromised. CLLD introduces a novel contrastive learning (CL) method that assesses the similarity of local features within the global context of the input image. It uses the surrounding information to predict lane markings. This is achieved by integrating local feature contrastive learning with our newly proposed operation, dubbed cross-similarity . The local feature CL concentrates on extracting features from small patches, a necessity for accurately localizing lane segments. Meanwhile, cross-similarity captures global features, enabling the detection of obscured lane segments based on their surroundings. We enhance cross-similarity by randomly masking portions of input images in the process of augmentation. Extensive experiments on TuSimple and CuLane benchmark datasets demonstrate that CLLD consistently outperforms state-of-the-art contrastive learning methods, particularly in visibility-impairing conditions like shadows, while it also delivers comparable results under normal conditions. When compared to supervised learning, CLLD still excels in challenging scenarios such as shadows and crowded scenes, which are common in real-world driving.

Existing datasets for autonomous driving (AD) often lack diversity and long-range capabilities, focusing instead on 360° perception and temporal reasoning. To address this gap, we introduce Zenseact Open Dataset (ZOD), a large- scale and diverse multimodal dataset collected over two years in various European countries, covering an area 9×that of existing datasets. ZOD boasts the highest range and resolution sensors among comparable datasets, coupled with detailed keyframe annotations for 2D and 3D objects (up to 245m), road instance/semantic segmentation, traffic sign recognition, and road classification. We believe that this unique combination will facilitate breakthroughs in long-range perception and multi-task learning. The dataset is composed of Frames, Sequences, and Drives, designed to encompass both data diversity and support for spatio-temporal learning, sensor fusion, localization, and mapping. Frames consist of 100k curated camera images with two seconds of other supporting sensor data, while the 1473 Sequences and 29 Drives include the entire sensor suite for 20 seconds and a few minutes, respectively. ZOD is the only large-scale AD dataset released under a permissive license, allowing for both research and commercial use. More information, and an extensive devkit, can be found at zod.zenseact.com.

The ubiquity of camera-enabled devices has led to large amounts of unlabeled image data being produced at the edge. The integration of self-supervised learning (SSL) and federated learning (FL) into one coherent system can potentially offer data privacy guarantees while also advancing the quality and robustness of the learned visual representations without needing to move data around. However, client bias and divergence during FL aggregation caused by data heterogeneity limits the performance of learned visual representations on downstream tasks. In this paper, we propose a new aggregation strategy termed Layer-wise Divergence Aware Weight Aggregation (L-DAWA) to mitigate the influence of client bias and divergence during FL aggregation. The proposed method aggregates weights at the layer-level according to the measure of angular divergence between the clients’ model and the global model. Extensive experiments with cross-silo and cross-device settings on CIFAR-10/100 and Tiny ImageNet datasets demonstrate that our methods are effective and obtain new SOTA performance on both contrastive and non-contrastive SSL approaches.

To have competent 3D lane detection for real-world driving, a massive amount of data from all over the world is needed, but data collection and manual annotation are costly and time-consuming. The diversity of data collected by developmental cars might still be limited compared to the data collected by a large fleet of customer cars. Federated learning enables training models on edge without transferring data out of devices. However, training supervised learning tasks at the edge is directly tied to having access to high-quality labels, which is limited at the edge.In this paper, we propose a fully automatic method to generate 3D lane labels at the edge using a pre-recorded HD map to enable the federated training of the 3D lane detection model. As a reference, a semi-automatic method is applied for creating a 3D-lane dataset used as ground truth. Our experimental results show that the model can achieve comparable performance when training on the same dataset in both a centralized and a decentralized manner. And the models trained on semi-automatic labeled datasets slightly outperform those trained on fully-automatically labeled datasets. This study shows that a well-performing 3D lane detection model can be trained in a supervised and fully decentralized manner, and most importantly, data privacy at the edge is guaranteed.

The deployment of Deep Neural Networks (DNNs) on edge devices is hindered by the substantial gap between performance requirements and available computational power. While recent research has made significant strides in developing pruning methods to build a sparse network for reducing the computing overhead of DNNs, there remains considerable accuracy loss, especially at high pruning ratios. We find that the architectures designed for dense networks by differentiable architecture search methods are ineffective when pruning mechanisms are applied to them. The main reason is that the current methods do not support sparse architectures in their search space and use a search objective that is made for dense networks and does not focus on sparsity. This paper proposes a new method to search for sparsity-friendly neural architectures. It is done by adding two new sparse operations to the search space and modifying the search objective. We propose two novel parametric SparseConv and SparseLinear operations in order to expand the search space to include sparse operations. In particular, these operations make a flexible search space due to using sparse parametric versions of linear and convolution operations. The proposed search objective lets us train the architecture based on the sparsity of the search space operations. Quantitative analyses demonstrate that architectures found through DASS outperform those used in the state-of-the-art sparse networks on the CIFAR-10 and ImageNet datasets. In terms of performance and hardware effectiveness, DASS increases the accuracy of the sparse version of MobileNet-v2 from 73.44% to 81.35% (+7.91% improvement) with a 3.87× faster inference time.

In this paper, we consider risk-sensitive sequential decision-making in Reinforcement Learning (RL). Our contributions are two-fold. First, we introduce a novel and coherent quantification of risk, namely composite risk, which quantifies the joint effect of aleatory and epistemic risk during the learning process. Existing works considered either aleatory or epistemic risk individually, or as an additive combination. We prove that the additive formulation is a particular case of the composite risk when the epistemic risk measure is replaced with expectation. Thus, the composite risk is more sensitive to both aleatory and epistemic uncertainty than the individual and additive formulations. We also propose an algorithm, SENTINEL-K, based on ensemble bootstrapping and distributional RL for representing epistemic and aleatory uncertainty respectively. The ensemble of K learners uses Follow The Regularised Leader (FTRL) to aggregate the return distributions and obtain the composite risk. We experimentally verify that SENTINEL-K estimates the return distribution better, and while used with composite risk estimates, demonstrates higher risk-sensitive performance than state-of-the-art risk-sensitive and distributional RL algorithms.

Social robots are becoming a companion in everyday life. To be well accepted by humans, they should efficiently understand meanings of their partners' motions and body language and respond accordingly. Learning concepts by imitation brings them this ability in a user-friendly way. This paper presents a fast and robust model for incremental learning of concepts by imitation (ILoCI). In ILoCI, observed multimodal spatiotemporal demonstrations are incrementally abstracted and generalized based on their perceptual and functional similarities during the imitation. Perceptually similar demonstrations are abstracted by a dynamic model of the mirror neuron system. The functional similarities of demonstrations are also learned through a limited number of interactions with the teacher. Incremental relearning of acquired concepts together through memory rehearsal enables the learner to gradually extract and utilize the common structural relations among demonstrations to expedite the learning process especially at the initial stages. Performance of ILoCI is assessed using a standard benchmark dataset and a human-robot interaction task in which a humanoid robot learns to abstract teacher's hand motions during imitation. Its performance is also evaluated on occluded observations that are probable in real environments. The results show efficiency of ILoCI in concept acquisition, recognition, prediction, and generation in addition to its robustness to occlusions and high variability in observations.