Robert Wille

IROS Conference 2025 Conference Paper

ELMAR: Enhancing LiDAR Detection with 4D Radar Motion Awareness and Cross-modal Uncertainty

• Xiangyuan Peng
• Miao Tang
• Huawei Sun
• Kay Bierzynski
• Lorenzo Servadei
• Robert Wille

LiDAR and 4D radar are widely used in autonomous driving and robotics. While LiDAR provides rich spatial information, 4D radar offers velocity measurement and remains robust under adverse conditions. As a result, increasing studies have focused on the 4D radar-LiDAR fusion method to enhance the perception. However, the misalignment between different modalities is often overlooked. To address this challenge and leverage the strengths of both modalities, we propose a LiDAR detection framework enhanced by 4D radar motion status and cross-modal uncertainty. The object movement information from 4D radar is first captured using a Dynamic Motion-Aware Encoding module during feature extraction to enhance 4D radar predictions. Subsequently, the instance-wise uncertainties of bounding boxes are estimated to mitigate the cross-modal misalignment and refine the final LiDAR predictions. Extensive experiments on the View-of-Delft (VoD) dataset highlight the effectiveness of our method, achieving state-of-the-art performance with the mAP of 74. 89% in the entire area and 88. 70% within the driving corridor while maintaining a real-time inference speed of 30. 02 FPS.

TMLR Journal 2025 Journal Article

Exploiting Benford's Law for Weight Regularization of Deep Neural Networks

• Julius Ott
• Huawei Sun
• Enrico Rinaldi
• Gianfranco Mauro
• Lorenzo Servadei
• Robert Wille

Stochastic learning of Deep Neural Network (DNN) parameters is highly sensitive to training strategy, hyperparameters, and available training data. Many state-of-the-art solutions use weight regularization to adjust parameter distributions, prevent overfitting, and support generalization of DNNs. None of the existing regularization techniques have ever exploited a typical distribution of numerical datasets with respect to the first non-zero (or significant) digit, called Benford's Law (BL). In this paper, we show that the deviation of the significant digit distribution of the DNN weights from BL is closely related to the generalization of the DNN. In particular, when the DNN is presented with limited training data. To take advantage of this finding, we use BL to target the weight regularization of DNNs. Extensive experiments are performed on image, table, and speech data, considering convolutional (CNN) and Transformer-based neural network architectures with varying numbers of parameters. We show that the performance of DNNs is improved by minimizing the distance between the significant digit distributions of the DNN weights and the BL distribution along with L2 regularization. The improvements depend on the network architecture and how it deals with limited data. However, the proposed penalty term improves consistently and some CNN-based architectures gain up to $15\%$ test accuracy over the default training scheme with L2 regularization on subsets of CIFAR 100.

TMLR Journal 2025 Journal Article

TRIDE: A Text-assisted Radar-Image weather-aware fusion network for Depth Estimation

• Huawei Sun
• Zixu Wang
• Hao Feng
• Julius Ott
• Lorenzo Servadei
• Robert Wille

Depth estimation, essential for autonomous driving, seeks to interpret the 3D environment surrounding vehicles. The development of radar sensors, known for their cost-efficiency and robustness, has spurred interest in radar-camera fusion-based solutions. However, existing algorithms fuse features from these modalities without accounting for weather conditions, despite radars being known to be more robust than cameras under adverse weather. Additionally, while Vision-Language models have seen rapid advancement, utilizing language descriptions alongside other modalities for depth estimation remains an open challenge. This paper first introduces a text-generation strategy along with feature extraction and fusion techniques that can assist monocular depth estimation pipelines, leading to improved accuracy across different algorithms on the KITTI dataset. Building on this, we propose TRIDE, a radar-camera fusion algorithm that enhances text feature extraction by incorporating radar point information. To address the impact of weather on sensor performance, we introduce a weather-aware fusion block that adaptively adjusts radar weighting based on current weather conditions. Our method, benchmarked on the nuScenes dataset, demonstrates performance gains over the state-of-the-art, achieving a 12.87% improvement in MAE and a 9.08% improvement in RMSE. Code: https://github.com/harborsarah/TRIDE

IROS Conference 2024 Conference Paper

CaFNet: A Confidence-Driven Framework for Radar Camera Depth Estimation

• Huawei Sun
• Hao Feng
• Julius Ott
• Lorenzo Servadei
• Robert Wille

Depth estimation is critical in autonomous driving for interpreting 3D scenes accurately. Recently, radar-camera depth estimation has become of sufficient interest due to the robustness and low-cost properties of radar. Thus, this paper introduces a two-stage, end-to-end trainable Confidence-aware Fusion Net (CaFNet) for dense depth estimation, combining RGB imagery with sparse and noisy radar point cloud data. The first stage addresses radar-specific challenges, such as ambiguous elevation and noisy measurements, by predicting a radar confidence map and a preliminary coarse depth map. A novel approach is presented for generating the ground truth for the confidence map, which involves associating each radar point with its corresponding object to identify potential projection surfaces. These maps, together with the initial radar input, are processed by a second encoder. For the final depth estimation, we innovate a confidence-aware gated fusion mechanism to integrate radar and image features effectively, thereby enhancing the reliability of the depth map by filtering out radar noise. Our methodology, evaluated on the nuScenes dataset, demonstrates superior performance, improving upon the current leading model by 3. 2% in Mean Absolute Error (MAE) and 2. 7% in Root Mean Square Error (RMSE). Code: https://github.com/harborsarah/CaFNet

SAT Conference 2022 Conference Paper

Towards a SAT Encoding for Quantum Circuits: A Journey From Classical Circuits to Clifford Circuits and Beyond

• Lucas Berent
• Lukas Burgholzer
• Robert Wille

Boolean Satisfiability (SAT) techniques are well-established in classical computing where they are used to solve a broad variety of problems, e. g. , in the design of classical circuits and systems. Analogous to the classical realm, quantum algorithms are usually modelled as circuits and similar design tasks need to be tackled. Thus, it is natural to pose the question whether these design tasks in the quantum realm can also be approached using SAT techniques. To the best of our knowledge, no SAT formulation for arbitrary quantum circuits exists and it is unknown whether such an approach is feasible at all. In this work, we define a propositional SAT encoding that, in principle, can be applied to arbitrary quantum circuits. However, we show that, due to the inherent complexity of representing quantum states, constructing such an encoding is not feasible in general. Therefore, we establish general criteria for determining the feasibility of the proposed encoding and identify classes of quantum circuits fulfilling these criteria. We explicitly demonstrate how the proposed encoding can be applied to the class of Clifford circuits as a representative. Finally, we empirically demonstrate the applicability and efficiency of the proposed encoding for Clifford circuits. With these results, we lay the foundation for continuing the ongoing success of SAT in classical circuit and systems design for quantum circuits.

FLAP Journal 2018 Journal Article

Preface to the Special Issue of the 48th IEEE International Symposium on Multiple Valued Logic.

• Robert Wille
• Martin Lukac