1 code implementation • 28 Apr 2024 • Amir Samadi, Konstantinos Koufos, Kurt Debattista, Mehrdad Dianati
We evaluate the effectiveness of our framework in diverse domains, including ADS, Atari Pong, Pacman and space-invaders games, using traditional performance metrics such as validity, proximity and sparsity.
no code implementations • 11 Apr 2024 • Hakan Yekta Yatbaz, Mehrdad Dianati, Konstantinos Koufos, Roger Woodman
To address the real-time operation requirements in ADS, we also introduce a novel introspection method that combines activation patterns from multiple layers of the detector's backbone and report its performance.
2 code implementations • 8 Apr 2024 • Hamed Haghighi, Amir Samadi, Mehrdad Dianati, Valentina Donzella, Kurt Debattista
Diffusion Models (DMs) have achieved State-Of-The-Art (SOTA) results in the Lidar point cloud generation task, benefiting from their stable training and iterative refinement during sampling.
no code implementations • 2 Mar 2024 • Hakan Yekta Yatbaz, Mehrdad Dianati, Konstantinos Koufos, Roger Woodman
The proposed approach pre-processes the neural activation patterns of the object detector's backbone using several different modes.
no code implementations • 23 Feb 2024 • Yiting Wang, Haonan Zhao, Daniel Gummadi, Mehrdad Dianati, Kurt Debattista, Valentina Donzella
Motivated by such a need, this work proposes a unifying pipeline to assess the robustness of panoptic segmentation models for AAD, correlating it with traditional image quality.
no code implementations • 29 Jan 2024 • Hamed Haghighi, Xiaomeng Wang, Hao Jing, Mehrdad Dianati
This paper reviews the current state-of-the-art in learning-based sensor simulation methods and validation approaches, focusing on two main types of perception sensors: cameras and Lidars.
1 code implementation • 25 Dec 2023 • Hamed Haghighi, Mehrdad Dianati, Kurt Debattista, Valentina Donzella
Motivated by this potential, this paper focuses on sim-to-real mapping of Lidar point clouds, a widely used perception sensor in automated driving systems.
1 code implementation • 19 Sep 2023 • Mreza Alipour Sormoli, Amir Samadi, Sajjad Mozaffari, Konstantinos Koufos, Mehrdad Dianati, Roger Woodman
Anticipating the motion of other road users is crucial for automated driving systems (ADS), as it enables safe and informed downstream decision-making and motion planning.
no code implementations • 28 Jul 2023 • Amir Samadi, Amir Shirian, Konstantinos Koufos, Kurt Debattista, Mehrdad Dianati
A CF explainer identifies the minimum modifications in the input that would alter the model's output to its complement.
1 code implementation • 8 Jun 2023 • Sajjad Mozaffari, Mreza Alipour Sormoli, Konstantinos Koufos, Graham Lee, Mehrdad Dianati
In addition, we study the impact of the proposed prediction approach on motion planning and control tasks using extensive merging scenarios from the exiD dataset.
1 code implementation • 25 May 2023 • Amir Samadi, Konstantinos Koufos, Kurt Debattista, Mehrdad Dianati
Deep Reinforcement Learning (DRL) has demonstrated promising capability in solving complex control problems.
no code implementations • 24 Apr 2023 • Shunli Ren, Zixing Lei, Zi Wang, Mehrdad Dianati, Yafei Wang, Siheng Chen, Wenjun Zhang
To achieve comprehensive recovery, we design a communication-adaptive multi-scale spatial-temporal prediction model to extract multi-scale spatial-temporal features based on V2X communication conditions and capture the most significant information for the prediction of the missing information.
1 code implementation • 28 Mar 2023 • Sajjad Mozaffari, Mreza Alipour Sormoli, Konstantinos Koufos, Mehrdad Dianati
Due to the uncertain future behaviour of vehicles, multiple future behaviour modes are often plausible for a vehicle in a given driving scene.
1 code implementation • 14 Nov 2022 • Yifan Lu, Quanhao Li, Baoan Liu, Mehrdad Dianati, Chen Feng, Siheng Chen, Yanfeng Wang
Collaborative 3D object detection exploits information exchange among multiple agents to enhance accuracy of object detection in presence of sensor impairments such as occlusion.
no code implementations • 5 Sep 2022 • Mustafa Yıldırım, Sajjad Mozaffari, Luc McCutcheon, Mehrdad Dianati, Alireza Tamaddoni-Nezhad Saber Fallah
This paper proposes a Prediction-based Deep Reinforcement Learning (PDRL) decision-making model that considers the manoeuvre intentions of surrounding vehicles in the decision-making process for highway driving.
1 code implementation • 18 Dec 2021 • Eduardo Arnold, Sajjad Mozaffari, Mehrdad Dianati
The proposed method achieves on-par performance with state-of-the-art methods on the KITTI dataset, and outperforms existing methods for low overlapping point clouds.
1 code implementation • 22 Sep 2021 • Sajjad Mozaffari, Eduardo Arnold, Mehrdad Dianati, Saber Fallah
Lane change (LC) is one of the safety-critical manoeuvres in highway driving according to various road accident records.
no code implementations • 9 Jun 2021 • Eduardo Arnold, Sajjad Mozaffari, Mehrdad Dianati, Paul Jennings
Visual sensor networks are used for monitoring traffic in large cities and are promised to support automated driving in complex road segments.
no code implementations • 25 Dec 2019 • Sajjad Mozaffari, Omar Y. Al-Jarrah, Mehrdad Dianati, Paul Jennings, Alexandros Mouzakitis
Motivated by this increased popularity, we provide a comprehensive review of the state-of-the-art of deep learning-based approaches for vehicle behaviour prediction in this paper.
1 code implementation • 18 Dec 2019 • Eduardo Arnold, Mehrdad Dianati, Robert de Temple, Saber Fallah
In contrast, the late fusion scheme fuses the independently detected bounding boxes from multiple spatially diverse sensors.