Search

Anonymization plays a key role in protecting sensible information of individuals in real world datasets. Self-driving cars for example need high resolution facial features to track people and their viewing direction to predict future behaviour and react accordingly. In order to protect people's privacy whilst keeping important features in the dataset, it is important to replace the full body of a person with a highly detailed anonymized one. In contrast to doing face anonymization, full body replacement decreases the ability of recognizing people by their hairstyle or clothes. In this paper, we propose a workflow for full body person anonymization utilizing Stable Diffusion as a generative backend. Text-to-image diffusion models, like Stable Diffusion, OpenAI's DALL-E or Midjourney, have become very popular in recent time, being able to create photorealistic images from a single text prompt. We show that our method outperforms state-of-the art anonymization pipelines with respect to image quality, resolution, Inception Score (IS) and Frechet Inception Distance (FID). Additionally, our method is invariant with respect to the image generator and thus able to be used with the latest models available.

Self-driving vehicles rely on multimodal motion forecasts to effectively interact with their environment and plan safe maneuvers. We introduce SceneMotion, an attention-based model for forecasting scene-wide motion modes of multiple traffic agents. Our model transforms local agent-centric embeddings into scene-wide forecasts using a novel latent context module. This module learns a scene-wide latent space from multiple agent-centric embeddings, enabling joint forecasting and interaction modeling. The competitive performance in the Waymo Open Interaction Prediction Challenge demonstrates the effectiveness of our approach. Moreover, we cluster future waypoints in time and space to quantify the interaction between agents. We merge all modes and analyze each mode independently to determine which clusters are resolved through interaction or result in conflict. Our implementation is available at: https://github.com/kit-mrt/future-motion, Comment: ITSC'24; updated table VI

With growing complexity and responsibility of automated driving functions in road traffic and growing scope of their operational design domains, there is increasing demand for covering significant parts of development, validation, and verification via virtual environments and simulation models. If, however, simulations are meant not only to augment real-world experiments, but to replace them, quantitative approaches are required that measure to what degree and under which preconditions simulation models adequately represent reality, and thus allow their usage for virtual testing of driving functions. Especially in research and development areas related to the safety impacts of the "open world", there is a significant shortage of real-world data to parametrize and/or validate simulations - especially with respect to the behavior of human traffic participants, whom automated vehicles will meet in mixed traffic. This paper presents the intermediate results of the German AVEAS research project (www.aveas.org) which aims at developing methods and metrics for the harmonized, systematic, and scalable acquisition of real-world data for virtual verification and validation of advanced driver assistance systems and automated driving, and establishing an online database following the FAIR principles., Comment: 6 pages, 5 figures, 2 tables

With growing complexity and criticality of automated driving functions in road traffic and their operational design domains (ODD), there is increasing demand for covering significant proportions of development, validation, and verification in virtual environments and through simulation models. If, however, simulations are meant not only to augment real-world experiments, but to replace them, quantitative approaches are required that measure to what degree and under which preconditions simulation models adequately represent reality, and thus, using their results accordingly. Especially in R&D areas related to the safety impact of the "open world", there is a significant shortage of real-world data to parameterize and/or validate simulations - especially with respect to the behavior of human traffic participants, whom automated driving functions will meet in mixed traffic. We present an approach to systematically acquire data in public traffic by heterogeneous means, transform it into a unified representation, and use it to automatically parameterize traffic behavior models for use in data-driven virtual validation of automated driving functions., Comment: 8 pages, 5 figures

There is a gap in risk assessment of trajectories between the trajectory information coming from a traffic motion prediction module and what is actually needed. Closing this gap necessitates advancements in prediction beyond current practices. Existing prediction models yield joint predictions of agents' future trajectories with uncertainty weights or marginal Gaussian probability density functions (PDFs) for single agents. Although, these methods achieve high accurate trajectory predictions, they only provide little or no information about the dependencies of interacting agents. Since traffic is a process of highly interdependent agents, whose actions directly influence their mutual behavior, the existing methods are not sufficient to reliably assess the risk of future trajectories. This paper addresses that gap by introducing a novel approach to motion prediction, focusing on predicting agent-pair covariance matrices in a ``scene-centric'' manner, which can then be used to model Gaussian joint PDFs for all agent-pairs in a scene. We propose a model capable of predicting those agent-pair covariance matrices, leveraging an enhanced awareness of interactions. Utilizing the prediction results of our model, this work forms the foundation for comprehensive risk assessment with statistically based methods for analyzing agents' relations by their joint PDFs., Comment: Accepted for publication in Proceedings of the IEEE Intelligent Vehicles Symposium (IV), Jeju Island - Korea, 2-5 June 2024

We present JointMotion, a self-supervised pre-training method for joint motion prediction in self-driving vehicles. Our method jointly optimizes a scene-level objective connecting motion and environments, and an instance-level objective to refine learned representations. Scene-level representations are learned via non-contrastive similarity learning of past motion sequences and environment context. At the instance level, we use masked autoencoding to refine multimodal polyline representations. We complement this with an adaptive pre-training decoder that enables JointMotion to generalize across different environment representations, fusion mechanisms, and dataset characteristics. Notably, our method reduces the joint final displacement error of Wayformer, HPTR, and Scene Transformer models by 3\%, 8\%, and 12\%, respectively; and enables transfer learning between the Waymo Open Motion and the Argoverse 2 Motion Forecasting datasets. Code: https://github.com/kit-mrt/future-motion, Comment: CoRL'24 camera-ready

This technical document presents the committee driven innovation modeling methodology "Innovation Modeling Grid" in detail. This document is the successor of three publications on IMoG and focuses on presenting all details of the methodology, Comment: ~170p, many figures, technical document

We introduce RedMotion, a transformer model for motion prediction in self-driving vehicles that learns environment representations via redundancy reduction. Our first type of redundancy reduction is induced by an internal transformer decoder and reduces a variable-sized set of local road environment tokens, representing road graphs and agent data, to a fixed-sized global embedding. The second type of redundancy reduction is obtained by self-supervised learning and applies the redundancy reduction principle to embeddings generated from augmented views of road environments. Our experiments reveal that our representation learning approach outperforms PreTraM, Traj-MAE, and GraphDINO in a semi-supervised setting. Moreover, RedMotion achieves competitive results compared to HPTR or MTR++ in the Waymo Motion Prediction Challenge. Our open-source implementation is available at: https://github.com/kit-mrt/future-motion, Comment: 17 pages, 8 figures; v2: focus on transformer model; v3: TMLR camera-ready

In self-driving applications, LiDAR data provides accurate information about distances in 3D but lacks the semantic richness of camera data. Therefore, state-of-the-art methods for perception in urban scenes fuse data from both sensor types. In this work, we introduce a novel self-supervised method to fuse LiDAR and camera data for self-driving applications. We build upon masked autoencoders (MAEs) and train deep learning models to reconstruct masked LiDAR data from fused LiDAR and camera features. In contrast to related methods that use birds-eye-view representations, we fuse features from dense spherical LiDAR projections and features from fish-eye camera crops with a similar field of view. Therefore, we reduce the learned spatial transformations to moderate perspective transformations and do not require additional modules to generate dense LiDAR representations. Code is available at: https://github.com/KIT-MRT/masked-fusion-360, Comment: Technical report, 6 pages, 4 figures, accepted at ICLR 2023 Tiny Papers

[Context and motivation] The automotive industry is currently undergoing a fundamental transformation towards software defined vehicles. The automotive market of the future demands a higher level of automation, electrification of the power train, and individually configurable comfort functions. [Question/problem] These demands pose a challenge to the automotive development cycle, because they introduce complexity by larger and not yet well explored design spaces that are difficult to manage. [Principal ideas/results] To cope with these challenges, the main players along the value chain have an increased interest in collaborating and aligning their development efforts along joint roadmaps. Roadmap development can be viewed as a field of requirements engineering with the goal to capture product aspects on an appropriate level of abstraction to speed up investment decisions, reduce communication overhead and parallelize development activities, while complying with competition laws. [Contribution] In this paper, we present a refinement of the "Innovation Modeling Grid" (IMoG), which encompasses a methodology, a process and a proposed notation to support joint analysis of development roadmaps. IMoG is focused on the automotive domain, yet there are clear potentials for other applications., Comment: 15 pages, 7 figures

In order to protect vulnerable road users (VRUs), such as pedestrians or cyclists, it is essential that intelligent transportation systems (ITS) accurately identify them. Therefore, datasets used to train perception models of ITS must contain a significant number of vulnerable road users. However, data protection regulations require that individuals are anonymized in such datasets. In this work, we introduce a novel deep learning-based pipeline for face anonymization in the context of ITS. In contrast to related methods, we do not use generative adversarial networks (GANs) but build upon recent advances in diffusion models. We propose a two-stage method, which contains a face detection model followed by a latent diffusion model to generate realistic face in-paintings. To demonstrate the versatility of anonymized images, we train segmentation methods on anonymized data and evaluate them on non-anonymized data. Our experiment reveal that our pipeline is better suited to anonymize data for segmentation than naive methods and performes comparably with recent GAN-based methods. Moreover, face detectors achieve higher mAP scores for faces anonymized by our method compared to naive or recent GAN-based methods., Comment: 6 pages, 5 figures

We propose to create a secondary beam of neutral kaons in Hall D at Jefferson Lab to be used with the GlueX experimental setup for strange hadron spectroscopy. The superior CEBAF electron beam will enable a flux on the order of $1\times 10^4~K_L/sec$, which exceeds the flux of that previously attained at SLAC by three orders of magnitude. The use of a deuteron target will provide first measurements ever with neutral kaons on neutrons. The experiment will measure both differential cross sections and self-analyzed polarizations of the produced $\Lambda$, $\Sigma$, $\Xi$, and $\Omega$ hyperons using the GlueX detector at the Jefferson Lab Hall D. The measurements will span CM $\cos\theta$ from $-0.95$ to 0.95 in the range W = 1490 MeV to 2500 MeV. The new data will significantly constrain the partial wave analyses and reduce model-dependent uncertainties in the extraction of the properties and pole positions of the strange hyperon resonances, and establish the orbitally excited multiplets in the spectra of the $\Xi$ and $\Omega$ hyperons. Comparison with the corresponding multiplets in the spectra of the charm and bottom hyperons will provide insight into he accuracy of QCD-based calculations over a large range of masses. The proposed facility will have a defining impact in the strange meson sector through measurements of the final state $K\pi$ system up to 2 GeV invariant mass. This will allow the determination of pole positions and widths of all relevant $K^\ast(K\pi)$ $S$-,$P$-,$D$-,$F$-, and $G$-wave resonances, settle the question of the existence or nonexistence of scalar meson $\kappa/K_0^\ast(700)$ and improve the constrains on their pole parameters. Subsequently improving our knowledge of the low-lying scalar nonet in general., Comment: Final version of the KLF Proposal [C12-19-001] approved by JLab PAC48. The intermediate version of the proposal was posted in arXiv:1707.05284 [hep-ex]. 103 pages, 52 figures, 8 tables, 324 references. Several typos were fixed