Perceive, Attend, and Drive: Learning Spatial Attention for Safe Self-Driving

• URL: http://arxiv.org/abs/2011.01153v2
• Date: Fri, 26 Mar 2021 03:43:18 GMT
• Title: Perceive, Attend, and Drive: Learning Spatial Attention for Safe Self-Driving
• Authors: Bob Wei, Mengye Ren, Wenyuan Zeng, Ming Liang, Bin Yang, Raquel Urtasun
• Abstract summary: We propose an end-to-end self-driving network featuring a sparse attention module that learns to automatically attend to important regions of the input. The attention module specifically targets motion planning, whereas prior literature only applied attention in perception tasks.
• Score: 84.59201486239908
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose an end-to-end self-driving network featuring a sparse attention module that learns to automatically attend to important regions of the input. The attention module specifically targets motion planning, whereas prior literature only applied attention in perception tasks. Learning an attention mask directly targeted for motion planning significantly improves the planner safety by performing more focused computation. Furthermore, visualizing the attention improves interpretability of end-to-end self-driving.

Related papers

• Enhancing End-to-End Autonomous Driving with Latent World Model [78.22157677787239]
  We propose a novel self-supervised method to enhance end-to-end driving without the need for costly labels. Our framework textbfLAW uses a LAtent World model to predict future latent features based on the predicted ego actions and the latent feature of the current frame. As a result, our approach achieves state-of-the-art performance in both open-loop and closed-loop benchmarks without costly annotations.
  arXiv  Detail & Related papers  (2024-06-12T17:59:21Z)
• Implicit Occupancy Flow Fields for Perception and Prediction in Self-Driving [68.95178518732965]
  A self-driving vehicle (SDV) must be able to perceive its surroundings and predict the future behavior of other traffic participants. Existing works either perform object detection followed by trajectory of the detected objects, or predict dense occupancy and flow grids for the whole scene. This motivates our unified approach to perception and future prediction that implicitly represents occupancy and flow over time with a single neural network.
  arXiv  Detail & Related papers  (2023-08-02T23:39:24Z)
• Where and What: Driver Attention-based Object Detection [13.5947650184579]
  We bridge the gap between pixel-level and object-level attention prediction. Our framework achieves competitive state-of-the-art performance on both pixel-level and object-level.
  arXiv  Detail & Related papers  (2022-04-26T08:38:22Z)
• Importance is in your attention: agent importance prediction for autonomous driving [4.176937532441124]
  Trajectory prediction is an important task in autonomous driving. We show that attention information can also be used to measure the importance of each agent with respect to the ego vehicle's future planned trajectory.
  arXiv  Detail & Related papers  (2022-04-19T20:34:30Z)
• Important Object Identification with Semi-Supervised Learning for Autonomous Driving [37.654878298744855]
  We propose a novel approach for important object identification in egocentric driving scenarios. We present a semi-supervised learning pipeline to enable the model to learn from unlimited unlabeled data. Our approach also outperforms rule-based baselines by a large margin.
  arXiv  Detail & Related papers  (2022-03-05T01:23:13Z)
• CoCAtt: A Cognitive-Conditioned Driver Attention Dataset [16.177399201198636]
  Driver attention prediction can play an instrumental role in mitigating and preventing high-risk events. We present a new driver attention dataset, CoCAtt. CoCAtt is the largest and the most diverse driver attention dataset in terms of autonomy levels, eye tracker resolutions, and driving scenarios.
  arXiv  Detail & Related papers  (2021-11-19T02:42:34Z)
• Alignment Attention by Matching Key and Query Distributions [48.93793773929006]
  This paper introduces alignment attention that explicitly encourages self-attention to match the distributions of the key and query within each head. It is simple to convert any models with self-attention, including pre-trained ones, to the proposed alignment attention. On a variety of language understanding tasks, we show the effectiveness of our method in accuracy, uncertainty estimation, generalization across domains, and robustness to adversarial attacks.
  arXiv  Detail & Related papers  (2021-10-25T00:54:57Z)
• Safety-aware Motion Prediction with Unseen Vehicles for Autonomous Driving [104.32241082170044]
  We study a new task, safety-aware motion prediction with unseen vehicles for autonomous driving. Unlike the existing trajectory prediction task for seen vehicles, we aim at predicting an occupancy map. Our approach is the first one that can predict the existence of unseen vehicles in most cases.
  arXiv  Detail & Related papers  (2021-09-03T13:33:33Z)
• IntentNet: Learning to Predict Intention from Raw Sensor Data [86.74403297781039]
  In this paper, we develop a one-stage detector and forecaster that exploits both 3D point clouds produced by a LiDAR sensor as well as dynamic maps of the environment. Our multi-task model achieves better accuracy than the respective separate modules while saving computation, which is critical to reducing reaction time in self-driving applications.
  arXiv  Detail & Related papers  (2021-01-20T00:31:52Z)
• Explaining Autonomous Driving by Learning End-to-End Visual Attention [25.09407072098823]
  Current deep learning based autonomous driving approaches yield impressive results also leading to in-production deployment in certain controlled scenarios. One of the most popular and fascinating approaches relies on learning vehicle controls directly from data perceived by sensors. The main drawback of this approach as also in other learning problems is the lack of explainability. Indeed, a deep network will act as a black-box outputting predictions depending on previously seen driving patterns without giving any feedback on why such decisions were taken.
  arXiv  Detail & Related papers  (2020-06-05T10:12:31Z)

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.