Deep Multi-Task Learning for Joint Localization, Perception, and Prediction

• URL: http://arxiv.org/abs/2101.06720v2
• Date: Tue, 19 Jan 2021 03:17:34 GMT
• Title: Deep Multi-Task Learning for Joint Localization, Perception, and Prediction
• Authors: John Phillips, Julieta Martinez, Ioan Andrei B\^arsan, Sergio Casas, Abbas Sadat, Raquel Urtasun
• Abstract summary: This paper investigates the issues that arise in state-of-the-art autonomy stacks under localization error. We design a system that jointly performs perception, prediction, and localization. Our architecture is able to reuse computation between both tasks, and is thus able to correct localization errors efficiently.
• Score: 68.50217234419922
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Over the last few years, we have witnessed tremendous progress on many subtasks of autonomous driving, including perception, motion forecasting, and motion planning. However, these systems often assume that the car is accurately localized against a high-definition map. In this paper we question this assumption, and investigate the issues that arise in state-of-the-art autonomy stacks under localization error. Based on our observations, we design a system that jointly performs perception, prediction, and localization. Our architecture is able to reuse computation between both tasks, and is thus able to correct localization errors efficiently. We show experiments on a large-scale autonomy dataset, demonstrating the efficiency and accuracy of our proposed approach.

Related papers

• RING#: PR-by-PE Global Localization with Roto-translation Equivariant Gram Learning [20.688641105430467]
  Global localization is crucial in autonomous driving and robotics applications when GPS signals are unreliable. Most approaches achieve global localization by sequential place recognition (PR) and pose estimation (PE) We introduce a new paradigm, PR-by-PE localization, which bypasses the need for separate place recognition by directly deriving it from pose estimation. We propose RING#, an end-to-end PR-by-PE localization network that operates in the bird's-eye-view (BEV) space, compatible with both vision and LiDAR sensors.
  arXiv  Detail & Related papers  (2024-08-30T18:42:53Z)
• Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization using Geometrical Information [68.10033984296247]
  This paper explores the domain of active localization, emphasizing the importance of viewpoint selection to enhance localization accuracy. Our contributions involve using a data-driven approach with a simple architecture designed for real-time operation, a self-supervised data training method, and the capability to consistently integrate our map into a planning framework tailored for real-world robotics applications.
  arXiv  Detail & Related papers  (2024-07-22T12:32:09Z)
• Monocular Localization with Semantics Map for Autonomous Vehicles [8.242967098897408]
  We propose a novel visual semantic localization algorithm that employs stable semantic features instead of low-level texture features. First, semantic maps are constructed offline by detecting semantic objects, such as ground markers, lane lines, and poles, using cameras or LiDAR sensors. Online visual localization is performed through data association of semantic features and map objects.
  arXiv  Detail & Related papers  (2024-06-06T08:12:38Z)
• 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)
• Change Detection for Local Explainability in Evolving Data Streams [72.4816340552763]
  Local feature attribution methods have become a popular technique for post-hoc and model-agnostic explanations. It is often unclear how local attributions behave in realistic, constantly evolving settings such as streaming and online applications. We present CDLEEDS, a flexible and model-agnostic framework for detecting local change and concept drift.
  arXiv  Detail & Related papers  (2022-09-06T18:38:34Z)
• The Traveling Observer Model: Multi-task Learning Through Spatial Variable Embeddings [28.029643109302715]
  We frame a general prediction system as an observer traveling around a continuous space, measuring values at some locations, and predicting them at others. This perspective leads to a machine learning framework in which seemingly unrelated tasks can be solved by a single model. In experiments, the approach is shown to (1) recover intuitive locations of variables in space and time, (2) exploit regularities across related datasets with completely disjoint input and output spaces, and (3) exploit regularities across seemingly unrelated tasks.
  arXiv  Detail & Related papers  (2020-10-05T21:51:37Z)
• Visual Localization for Autonomous Driving: Mapping the Accurate Location in the City Maze [16.824901952766446]
  We propose a novel feature voting technique for visual localization. In our work, we craft the proposed feature voting method into three state-of-the-art visual localization networks. Our approach can predict location robustly even in challenging inner-city settings.
  arXiv  Detail & Related papers  (2020-08-13T03:59:34Z)
• The Importance of Prior Knowledge in Precise Multimodal Prediction [71.74884391209955]
  Roads have well defined geometries, topologies, and traffic rules. In this paper we propose to incorporate structured priors as a loss function. We demonstrate the effectiveness of our approach on real-world self-driving datasets.
  arXiv  Detail & Related papers  (2020-06-04T03:56:11Z)
• From Simulation to Real World Maneuver Execution using Deep Reinforcement Learning [69.23334811890919]
  Deep Reinforcement Learning has proved to be able to solve many control tasks in different fields, but the behavior of these systems is not always as expected when deployed in real-world scenarios. This is mainly due to the lack of domain adaptation between simulated and real-world data together with the absence of distinction between train and test datasets. We present a system based on multiple environments in which agents are trained simultaneously, evaluating the behavior of the model in different scenarios.
  arXiv  Detail & Related papers  (2020-05-13T14:22:20Z)
• DA4AD: End-to-End Deep Attention-based Visual Localization for Autonomous Driving [19.02445537167235]
  We present a visual localization framework based on novel deep attention aware features for autonomous driving. Our method achieves a competitive localization accuracy when compared to the LiDAR-based localization solutions.
  arXiv  Detail & Related papers  (2020-03-06T04:34:39Z)

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.