MCRL4OR: Multimodal Contrastive Representation Learning for Off-Road Environmental Perception

• URL: http://arxiv.org/abs/2501.13988v1
• Date: Thu, 23 Jan 2025 08:27:15 GMT
• Title: MCRL4OR: Multimodal Contrastive Representation Learning for Off-Road Environmental Perception
• Authors: Yi Yang, Zhang Zhang, Liang Wang,
• Abstract summary: We propose a Multimodal Contrastive Representation Learning approach for Off-Road environmental perception, namely MCRL4OR. This approach aims to jointly learn three encoders for processing visual images, locomotion states, and control actions. In experiments, we pre-train the MCRL4OR with a large-scale off-road driving dataset and adopt the learned multimodal representations for various downstream perception tasks in off-road driving scenarios.
• Score: 28.394436093801797
• License:
• Abstract: Most studies on environmental perception for autonomous vehicles (AVs) focus on urban traffic environments, where the objects/stuff to be perceived are mainly from man-made scenes and scalable datasets with dense annotations can be used to train supervised learning models. By contrast, it is hard to densely annotate a large-scale off-road driving dataset manually due to the inherently unstructured nature of off-road environments. In this paper, we propose a Multimodal Contrastive Representation Learning approach for Off-Road environmental perception, namely MCRL4OR. This approach aims to jointly learn three encoders for processing visual images, locomotion states, and control actions by aligning the locomotion states with the fused features of visual images and control actions within a contrastive learning framework. The causation behind this alignment strategy is that the inertial locomotion state is the result of taking a certain control action under the current landform/terrain condition perceived by visual sensors. In experiments, we pre-train the MCRL4OR with a large-scale off-road driving dataset and adopt the learned multimodal representations for various downstream perception tasks in off-road driving scenarios. The superior performance in downstream tasks demonstrates the advantages of the pre-trained multimodal representations. The codes can be found in \url{https://github.com/1uciusy/MCRL4OR}.

Related papers

• DAVE: Diverse Atomic Visual Elements Dataset with High Representation of Vulnerable Road Users in Complex and Unpredictable Environments [60.69159598130235]
  We present a new dataset, DAVE, designed for evaluating perception methods with high representation of Vulnerable Road Users (VRUs) DAVE is a manually annotated dataset encompassing 16 diverse actor categories (spanning animals, humans, vehicles, etc.) and 16 action types (complex and rare cases like cut-ins, zigzag movement, U-turn, etc.) Our experiments show that existing methods suffer degradation in performance when evaluated on DAVE, highlighting its benefit for future video recognition research.
  arXiv  Detail & Related papers  (2024-12-28T06:13:44Z)
• Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention [61.3281618482513]
  We present CogDriving, a novel network designed for synthesizing high-quality multi-view driving videos. CogDriving leverages a Diffusion Transformer architecture with holistic-4D attention modules, enabling simultaneous associations across the dimensions. CogDriving demonstrates strong performance on the nuScenes validation set, achieving an FVD score of 37.8, highlighting its ability to generate realistic driving videos.
  arXiv  Detail & Related papers  (2024-12-04T18:02:49Z)
• Human Insights Driven Latent Space for Different Driving Perspectives: A Unified Encoder for Efficient Multi-Task Inference [43.474068248379815]
  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.
  arXiv  Detail & Related papers  (2024-09-16T08:54:03Z)
• AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception [26.84439405241999]
  We present an AssIstive Driving pErception dataset (AIDE) that considers context information both inside and outside the vehicle. AIDE facilitates holistic driver monitoring through three distinctive characteristics. Two fusion strategies are introduced to give new insights into learning effective multi-stream/modal representations.
  arXiv  Detail & Related papers  (2023-07-26T03:12:05Z)
• 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)
• Learning to Walk by Steering: Perceptive Quadrupedal Locomotion in Dynamic Environments [25.366480092589022]
  A quadrupedal robot must exhibit robust and agile walking behaviors in response to environmental clutter and moving obstacles. We present a hierarchical learning framework, named PRELUDE, which decomposes the problem of perceptive locomotion into high-level decision-making. We demonstrate the effectiveness of our approach in simulation and with hardware experiments.
  arXiv  Detail & Related papers  (2022-09-19T17:55:07Z)
• Federated Deep Learning Meets Autonomous Vehicle Perception: Design and Verification [168.67190934250868]
  Federated learning empowered connected autonomous vehicle (FLCAV) has been proposed. FLCAV preserves privacy while reducing communication and annotation costs. It is challenging to determine the network resources and road sensor poses for multi-stage training.
  arXiv  Detail & Related papers  (2022-06-03T23:55:45Z)
• 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)
• Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers [14.509254362627576]
  We propose to address quadrupedal locomotion tasks using Reinforcement Learning (RL) We introduce LocoTransformer, an end-to-end RL method for quadrupedal locomotion.
  arXiv  Detail & Related papers  (2021-07-08T17:41:55Z)
• BoMuDANet: Unsupervised Adaptation for Visual Scene Understanding in Unstructured Driving Environments [54.22535063244038]
  We present an unsupervised adaptation approach for visual scene understanding in unstructured traffic environments. Our method is designed for unstructured real-world scenarios with dense and heterogeneous traffic consisting of cars, trucks, two-and three-wheelers, and pedestrians.
  arXiv  Detail & Related papers  (2020-09-22T08:25:44Z)

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.