Related papers: Explainable Action Prediction through Self-Supervi…

When humans perform everyday tasks, we naturally adjust our actions based on the current state of the environment. For instance, if we intend to put something into a drawer but notice it is closed, we open it first. However, many autonomous…

Knowledge graphs represent real-world entities and their relations in a semantically-rich structure supported by ontologies. Exploring this data with machine learning methods often relies on knowledge graph embeddings, which produce latent…

In this paper, we propose a probabilistic method to generate abstract scene graphs for table-top scenes from 6D object pose estimates. We explicitly make use of task-specfic context knowledge by encoding this knowledge as descriptive rules…

While supervised learning is widely used for perception modules in conventional autonomous driving solutions, scalability is hindered by the huge amount of data labeling needed. In contrast, while end-to-end architectures do not require…

With the growing use of deep learning methods, particularly graph neural networks, which encode intricate interconnectedness information, for a variety of real tasks, there is a necessity for explainability in such settings. In this paper,…

Trajectory prediction in autonomous driving relies on accurate representation of all relevant contexts of the driving scene, including traffic participants, road topology, traffic signs, as well as their semantic relations to each other.…

Structured scene representations are a core component of embodied agents, helping to consolidate raw sensory streams into readable, modular, and searchable formats. Due to their high computational overhead, many approaches build such…

This paper explores how graph neural networks (GNNs) can be used to enhance visual scene understanding and surgical skill assessment. By using GNNs to analyze the complex visual data of surgical procedures represented as graph structures,…

Heterogeneous graphs offer powerful data representations for traffic, given their ability to model the complex interaction effects among a varying number of traffic participants and the underlying road infrastructure. With the recent advent…

Navigation through uncontrolled intersections is one of the key challenges for autonomous vehicles. Identifying the subtle differences in hidden traits of other drivers can bring significant benefits when navigating in such environments. We…

The autonomous driving (AD) industry is exploring the use of knowledge graphs (KGs) to manage the vast amount of heterogeneous data generated from vehicular sensors. The various types of equipped sensors include video, LIDAR and RADAR.…

Predicting the possible future behaviors of vehicles that drive on shared roads is a crucial task for safe autonomous driving. Many existing approaches to this problem strive to distill all possible vehicle behaviors into a simplified set…

We develop a fully automatic image colorization system. Our approach leverages recent advances in deep networks, exploiting both low-level and semantic representations. As many scene elements naturally appear according to multimodal color…

This work introduces an enhanced approach to generating scene graphs by incorporating both a relationship hierarchy and commonsense knowledge. Specifically, we begin by proposing a hierarchical relation head that exploits an informative…

This work provides a comprehensive analysis and interpretation of the graph spectral representation of traffic scenarios. Based on a spatio-temporal vehicle interaction graph, an observed traffic scenario can be transformed into the graph…

In this paper, we address the important problem in self-driving of forecasting multi-pedestrian motion and their shared scene occupancy map, critical for safe navigation. Our contributions are two-fold. First, we advocate for predicting…

We present a method for generating, predicting, and using Spatiotemporal Occupancy Grid Maps (SOGM), which embed future semantic information of real dynamic scenes. We present an auto-labeling process that creates SOGMs from noisy real…

We propose a model that is able to perform unsupervised physical parameter estimation of systems from video, where the differential equations governing the scene dynamics are known, but labeled states or objects are not available. Existing…

The trend in the development of highly automated vehicles goes towards scenario-based methods. Traffic Sequence Charts are a visual but yet formal language for describing scenario-based requirements on highly automated vehicles. This work…

Autonomous vehicles navigate in dynamically changing environments under a wide variety of conditions, being continuously influenced by surrounding objects. Modelling interactions among agents is essential for accurately forecasting other…