V2XP-ASG: Generating Adversarial Scenes for Vehicle-to-Everything Perception

• URL: http://arxiv.org/abs/2209.13679v1
• Date: Tue, 27 Sep 2022 20:34:41 GMT
• Title: V2XP-ASG: Generating Adversarial Scenes for Vehicle-to-Everything Perception
• Authors: Hao Xiang, Runsheng Xu, Xin Xia, Zhaoliang Zheng, Bolei Zhou, Jiaqi Ma
• Abstract summary: V2X perception systems will soon be deployed at scale. How can we evaluate and improve its performance under challenging traffic scenarios before the real-world deployment? We propose the first open adversarial scene generator V2XP-ASG.
• Score: 37.41995438002604
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent advancements in Vehicle-to-Everything communication technology have enabled autonomous vehicles to share sensory information to obtain better perception performance. With the rapid growth of autonomous vehicles and intelligent infrastructure, the V2X perception systems will soon be deployed at scale, which raises a safety-critical question: how can we evaluate and improve its performance under challenging traffic scenarios before the real-world deployment? Collecting diverse large-scale real-world test scenes seems to be the most straightforward solution, but it is expensive and time-consuming, and the collections can only cover limited scenarios. To this end, we propose the first open adversarial scene generator V2XP-ASG that can produce realistic, challenging scenes for modern LiDAR-based multi-agent perception system. V2XP-ASG learns to construct an adversarial collaboration graph and simultaneously perturb multiple agents' poses in an adversarial and plausible manner. The experiments demonstrate that V2XP-ASG can effectively identify challenging scenes for a large range of V2X perception systems. Meanwhile, by training on the limited number of generated challenging scenes, the accuracy of V2X perception systems can be further improved by 12.3% on challenging and 4% on normal scenes.

Related papers

• Towards Intelligent Transportation with Pedestrians and Vehicles In-the-Loop: A Surveillance Video-Assisted Federated Digital Twin Framework [62.47416496137193]
  We propose a surveillance video assisted federated digital twin (SV-FDT) framework to empower ITSs with pedestrians and vehicles in-the-loop. The architecture consists of three layers: (i) the end layer, which collects traffic surveillance videos from multiple sources; (ii) the edge layer, responsible for semantic segmentation-based visual understanding, twin agent-based interaction modeling, and local digital twin system (LDTS) creation in local regions; and (iii) the cloud layer, which integrates LDTSs across different regions to construct a global DT model in realtime.
  arXiv  Detail & Related papers  (2025-03-06T07:36:06Z)
• Dynamic V2X Autonomous Perception from Road-to-Vehicle Vision [14.666587433945363]
  We propose to build V2X perception from road-to-vehicle vision and present Adaptive Road-to-Vehicle Perception (AR2VP) method. AR2VP is devised to tackle both intra-scene and inter-scene changes. We conduct perception experiment on 3D object detection and segmentation, and the results show that AR2VP excels in both performance-bandwidth trade-offs and adaptability within dynamic environments.
  arXiv  Detail & Related papers  (2023-10-29T19:01:20Z)
• Towards Vehicle-to-everything Autonomous Driving: A Survey on Collaborative Perception [40.90789787242417]
  Vehicle-to-everything (V2X) autonomous driving opens up a promising direction for developing a new generation of intelligent transportation systems. Collaborative perception (CP) as an essential component to achieve V2X can overcome the inherent limitations of individual perception. We provide a comprehensive review of CP methods for V2X scenarios, bringing a profound and in-depth understanding to the community.
  arXiv  Detail & Related papers  (2023-08-31T13:28:32Z)
• V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception [49.7212681947463]
  Vehicle-to-Vehicle (V2V) cooperative perception system has great potential to revolutionize the autonomous driving industry. We present V2V4Real, the first large-scale real-world multi-modal dataset for V2V perception. Our dataset covers a driving area of 410 km, comprising 20K LiDAR frames, 40K RGB frames, 240K annotated 3D bounding boxes for 5 classes, and HDMaps.
  arXiv  Detail & Related papers  (2023-03-14T02:49:20Z)
• Policy Pre-training for End-to-end Autonomous Driving via Self-supervised Geometric Modeling [96.31941517446859]
  We propose PPGeo (Policy Pre-training via Geometric modeling), an intuitive and straightforward fully self-supervised framework curated for the policy pretraining in visuomotor driving. We aim at learning policy representations as a powerful abstraction by modeling 3D geometric scenes on large-scale unlabeled and uncalibrated YouTube driving videos. In the first stage, the geometric modeling framework generates pose and depth predictions simultaneously, with two consecutive frames as input. In the second stage, the visual encoder learns driving policy representation by predicting the future ego-motion and optimizing with the photometric error based on current visual observation only.
  arXiv  Detail & Related papers  (2023-01-03T08:52:49Z)
• CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers [36.838065731893735]
  CoBEVT is the first generic multi-agent perception framework that can cooperatively generate BEV map predictions. CoBEVT achieves state-of-the-art performance for cooperative BEV semantic segmentation.
  arXiv  Detail & Related papers  (2022-07-05T17:59:28Z)
• V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer [58.71845618090022]
  We build a holistic attention model, namely V2X-ViT, to fuse information across on-road agents. V2X-ViT consists of alternating layers of heterogeneous multi-agent self-attention and multi-scale window self-attention. To validate our approach, we create a large-scale V2X perception dataset.
  arXiv  Detail & Related papers  (2022-03-20T20:18:25Z)
• V2X-Sim: A Virtual Collaborative Perception Dataset for Autonomous Driving [26.961213523096948]
  Vehicle-to-everything (V2X) denotes the collaboration between a vehicle and any entity in its surrounding. We present the V2X-Sim dataset, the first public large-scale collaborative perception dataset in autonomous driving.
  arXiv  Detail & Related papers  (2022-02-17T05:14:02Z)
• SceneGen: Learning to Generate Realistic Traffic Scenes [92.98412203941912]
  We present SceneGen, a neural autoregressive model of traffic scenes that eschews the need for rules and distributions. We demonstrate SceneGen's ability to faithfully model distributions of real traffic scenes.
  arXiv  Detail & Related papers  (2021-01-16T22:51:43Z)
• V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction [74.42961817119283]
  We use vehicle-to-vehicle (V2V) communication to improve the perception and motion forecasting performance of self-driving vehicles. By intelligently aggregating the information received from multiple nearby vehicles, we can observe the same scene from different viewpoints.
  arXiv  Detail & Related papers  (2020-08-17T17:58:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.