arXiv subjects

Claudius Glaeser

Publications and source records attributed to Claudius Glaeser.

5 recordsLinked to original sources

arXiv2023

Discovery of Perception Performance Limiting Triggering Conditions in Automated Driving

Highly automated driving (HAD) vehicles are complex systems operating in an open context. Performance limitations originating from sensing and understanding the open context under triggering conditions may result in unsafe behavior, thus, need to be identified and modeled. This aspect of safety is also discussed in standardization activities such as ISO 21448, safety of the intended functionality (SOTIF). Although SOTIF provides a non-exhaustive list of scenario factors to identify and analyze performance limitations under triggering conditions, no concrete methodology is yet provided to identify novel triggering conditions. We propose a methodology to identify and model novel triggering conditions in a scene in order to assess SOTIF using Bayesian network (BN) and p-value hypothesis testing. The experts provide the initial BN structure while the conditional belief tables (CBTs) are learned using dataset. P-value hypothesis testing is used to identify the relevant subset of scenes. These scenes are then analyzed by experts who provide potential triggering conditions present in the scenes. The novel triggering conditions are modeled in the BN and retested. As a case study, we provide p-value hypothesis testing of BN of LIDAR using real world data.

eess.SY↗

arXiv2022

Motion Estimation in Occupancy Grid Maps in Stationary Settings Using Recurrent Neural Networks

In this work, we tackle the problem of modeling the vehicle environment as dynamic occupancy grid map in complex urban scenarios using recurrent neural networks. Dynamic occupancy grid maps represent the scene in a bird's eye view, where each grid cell contains the occupancy probability and the two dimensional velocity. As input data, our approach relies on measurement grid maps, which contain occupancy probabilities, generated with lidar measurements. Given this configuration, we propose a recurrent neural network architecture to predict a dynamic occupancy grid map, i.e. filtered occupancy and velocity of each cell, by using a sequence of measurement grid maps. Our network architecture contains convolutional long-short term memories in order to sequentially process the input, makes use of spatial context, and captures motion. In the evaluation, we quantify improvements in estimating the velocity of braking and turning vehicles compared to the state-of-the-art. Additionally, we demonstrate that our approach provides more consistent velocity estimates for dynamic objects, as well as, less erroneous velocity estimates in static area.

cs.RO↗

arXiv2022

Understanding the Domain Gap in LiDAR Object Detection Networks

In order to make autonomous driving a reality, artificial neural networks have to work reliably in the open-world. However, the open-world is vast and continuously changing, so it is not technically feasible to collect and annotate training datasets which accurately represent this domain. Therefore, there are always domain gaps between training datasets and the open-world which must be understood. In this work, we investigate the domain gaps between high-resolution and low-resolution LiDAR sensors in object detection networks. Using a unique dataset, which enables us to study sensor resolution domain gaps independent of other effects, we show two distinct domain gaps - an inference domain gap and a training domain gap. The inference domain gap is characterised by a strong dependence on the number of LiDAR points per object, while the training gap shows no such dependence. These fndings show that different approaches are required to close these inference and training domain gaps.

cs.CV↗

arXiv2020

Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges

Recent advancements in perception for autonomous driving are driven by deep learning. In order to achieve robust and accurate scene understanding, autonomous vehicles are usually equipped with different sensors (e.g. cameras, LiDARs, Radars), and multiple sensing modalities can be fused to exploit their complementary properties. In this context, many methods have been proposed for deep multi-modal perception problems. However, there is no general guideline for network architecture design, and questions of "what to fuse", "when to fuse", and "how to fuse" remain open. This review paper attempts to systematically summarize methodologies and discuss challenges for deep multi-modal object detection and semantic segmentation in autonomous driving. To this end, we first provide an overview of on-board sensors on test vehicles, open datasets, and background information for object detection and semantic segmentation in autonomous driving research. We then summarize the fusion methodologies and discuss challenges and open questions. In the appendix, we provide tables that summarize topics and methods. We also provide an interactive online platform to navigate each reference: https://boschresearch.github.io/multimodalperception/.

cs.RO↗

arXiv2019

Can We Trust You? On Calibration of a Probabilistic Object Detector for Autonomous Driving

Reliable uncertainty estimation is crucial for perception systems in safe autonomous driving. Recently, many methods have been proposed to model uncertainties in deep learning based object detectors. However, the estimated probabilities are often uncalibrated, which may lead to severe problems in safety critical scenarios. In this work, we identify such uncertainty miscalibration problems in a probabilistic LiDAR 3D object detection network, and propose three practical methods to significantly reduce errors in uncertainty calibration. Extensive experiments on several datasets show that our methods produce well-calibrated uncertainties, and generalize well between different datasets.

cs.RO↗