Human Insights Driven Latent Space for Different Driving Perspectives: A Unified Encoder for Efficient Multi-Task Inference

• URL: http://arxiv.org/abs/2409.10095v1
• Date: Mon, 16 Sep 2024 08:54:03 GMT
• Title: Human Insights Driven Latent Space for Different Driving Perspectives: A Unified Encoder for Efficient Multi-Task Inference
• Authors: Huy-Dung Nguyen, Anass Bairouk, Mirjana Maras, Wei Xiao, Tsun-Hsuan Wang, Patrick Chareyre, Ramin Hasani, Marc Blanchon, Daniela Rus,
• Abstract summary: We propose a shared encoder trained on multiple computer vision tasks critical for urban navigation. We introduce a multi-scale feature network for pose estimation to improve depth learning. Our findings demonstrate that a shared backbone trained on diverse visual tasks is capable of providing overall perception capabilities.
• Score: 43.474068248379815
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autonomous driving holds great potential to transform road safety and traffic efficiency by minimizing human error and reducing congestion. A key challenge in realizing this potential is the accurate estimation of steering angles, which is essential for effective vehicle navigation and control. Recent breakthroughs in deep learning have made it possible to estimate steering angles directly from raw camera inputs. However, the limited available navigation data can hinder optimal feature learning, impacting the system's performance in complex driving scenarios. In this paper, we propose a shared encoder trained on multiple computer vision tasks critical for urban navigation, such as depth, pose, and 3D scene flow estimation, as well as semantic, instance, panoptic, and motion segmentation. By incorporating diverse visual information used by humans during navigation, this unified encoder might enhance steering angle estimation. To achieve effective multi-task learning within a single encoder, we introduce a multi-scale feature network for pose estimation to improve depth learning. Additionally, we employ knowledge distillation from a multi-backbone model pretrained on these navigation tasks to stabilize training and boost performance. Our findings demonstrate that a shared backbone trained on diverse visual tasks is capable of providing overall perception capabilities. While our performance in steering angle estimation is comparable to existing methods, the integration of human-like perception through multi-task learning holds significant potential for advancing autonomous driving systems. More details and the pretrained model are available at https://hi-computervision.github.io/uni-encoder/.

Related papers

• Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving [100.3848723827869]
  We present an effective multi-task framework, VE-Prompt, which introduces visual exemplars via task-specific prompting. Specifically, we generate visual exemplars based on bounding boxes and color-based markers, which provide accurate visual appearances of target categories. We bridge transformer-based encoders and convolutional layers for efficient and accurate unified perception in autonomous driving.
  arXiv  Detail & Related papers  (2023-03-03T08:54:06Z)
• 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)
• ALSO: Automotive Lidar Self-supervision by Occupancy estimation [70.70557577874155]
  We propose a new self-supervised method for pre-training the backbone of deep perception models operating on point clouds. The core idea is to train the model on a pretext task which is the reconstruction of the surface on which the 3D points are sampled. The intuition is that if the network is able to reconstruct the scene surface, given only sparse input points, then it probably also captures some fragments of semantic information.
  arXiv  Detail & Related papers  (2022-12-12T13:10:19Z)
• Learning Perceptual Locomotion on Uneven Terrains using Sparse Visual Observations [75.60524561611008]
  This work aims to exploit the use of sparse visual observations to achieve perceptual locomotion over a range of commonly seen bumps, ramps, and stairs in human-centred environments. We first formulate the selection of minimal visual input that can represent the uneven surfaces of interest, and propose a learning framework that integrates such exteroceptive and proprioceptive data. We validate the learned policy in tasks that require omnidirectional walking over flat ground and forward locomotion over terrains with obstacles, showing a high success rate.
  arXiv  Detail & Related papers  (2021-09-28T20:25:10Z)
• YOLOP: You Only Look Once for Panoptic Driving Perception [21.802146960999394]
  We present a panoptic driving perception network (YOLOP) to perform traffic object detection, drivable area segmentation and lane detection simultaneously. It is composed of one encoder for feature extraction and three decoders to handle the specific tasks. Our model performs extremely well on the challenging BDD100K dataset, achieving state-of-the-art on all three tasks in terms of accuracy and speed.
  arXiv  Detail & Related papers  (2021-08-25T14:19:42Z)
• Fine-Grained Vehicle Perception via 3D Part-Guided Visual Data Augmentation [77.60050239225086]
  We propose an effective training data generation process by fitting a 3D car model with dynamic parts to vehicles in real images. Our approach is fully automatic without any human interaction. We present a multi-task network for VUS parsing and a multi-stream network for VHI parsing.
  arXiv  Detail & Related papers  (2020-12-15T03:03:38Z)
• Robot Perception enables Complex Navigation Behavior via Self-Supervised Learning [23.54696982881734]
  We propose an approach to unify successful robot perception systems for active target-driven navigation tasks via reinforcement learning (RL) Our method temporally incorporates compact motion and visual perception data, directly obtained using self-supervision from a single image sequence. We demonstrate our approach on two real-world driving dataset, KITTI and Oxford RobotCar, using the new interactive CityLearn framework.
  arXiv  Detail & Related papers  (2020-06-16T07:45:47Z)
• End-to-end Autonomous Driving Perception with Sequential Latent Representation Learning [34.61415516112297]
  An end-to-end approach might clean up the system and avoid huge efforts of human engineering. A latent space is introduced to capture all relevant features useful for perception, which is learned through sequential latent representation learning. The learned end-to-end perception model is able to solve the detection, tracking, localization and mapping problems altogether with only minimum human engineering efforts.
  arXiv  Detail & Related papers  (2020-03-21T05:37:44Z)

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.