UnO: Unsupervised Occupancy Fields for Perception and Forecasting

• URL: http://arxiv.org/abs/2406.08691v1
• Date: Wed, 12 Jun 2024 23:22:23 GMT
• Title: UnO: Unsupervised Occupancy Fields for Perception and Forecasting
• Authors: Ben Agro, Quinlan Sykora, Sergio Casas, Thomas Gilles, Raquel Urtasun,
• Abstract summary: Supervised approaches leverage annotated object labels to learn a model of the world. We learn to perceive and forecast a continuous 4D occupancy field with self-supervision from LiDAR data. This unsupervised world model can be easily and effectively transferred to tasks.
• Score: 33.205064287409094
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Perceiving the world and forecasting its future state is a critical task for self-driving. Supervised approaches leverage annotated object labels to learn a model of the world -- traditionally with object detections and trajectory predictions, or temporal bird's-eye-view (BEV) occupancy fields. However, these annotations are expensive and typically limited to a set of predefined categories that do not cover everything we might encounter on the road. Instead, we learn to perceive and forecast a continuous 4D (spatio-temporal) occupancy field with self-supervision from LiDAR data. This unsupervised world model can be easily and effectively transferred to downstream tasks. We tackle point cloud forecasting by adding a lightweight learned renderer and achieve state-of-the-art performance in Argoverse 2, nuScenes, and KITTI. To further showcase its transferability, we fine-tune our model for BEV semantic occupancy forecasting and show that it outperforms the fully supervised state-of-the-art, especially when labeled data is scarce. Finally, when compared to prior state-of-the-art on spatio-temporal geometric occupancy prediction, our 4D world model achieves a much higher recall of objects from classes relevant to self-driving.

Related papers

• Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving [15.100104512786107]
  Drive-OccWorld adapts a visioncentric- 4D forecasting world model to end-to-end planning for autonomous driving. We propose injecting flexible action conditions, such as velocity, steering angle, trajectory, and commands, into the world model. Experiments on the nuScenes dataset demonstrate that our method can generate plausible and controllable 4D occupancy.
  arXiv  Detail & Related papers  (2024-08-26T11:53:09Z)
• 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)
• DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving [67.46481099962088]
  Current vision-centric pre-training typically relies on either 2D or 3D pre-text tasks, overlooking the temporal characteristics of autonomous driving as a 4D scene understanding task. We introduce emphcentricDriveWorld, which is capable of pre-training from multi-camera driving videos in atemporal fashion. DriveWorld delivers promising results on various autonomous driving tasks.
  arXiv  Detail & Related papers  (2024-05-07T15:14:20Z)
• JRDB-Traj: A Dataset and Benchmark for Trajectory Forecasting in Crowds [79.00975648564483]
  Trajectory forecasting models, employed in fields such as robotics, autonomous vehicles, and navigation, face challenges in real-world scenarios. This dataset provides comprehensive data, including the locations of all agents, scene images, and point clouds, all from the robot's perspective. The objective is to predict the future positions of agents relative to the robot using raw sensory input data.
  arXiv  Detail & Related papers  (2023-11-05T18:59:31Z)
• Vehicle Motion Forecasting using Prior Information and Semantic-assisted Occupancy Grid Maps [6.99274104609965]
  Motion is a challenging task for autonomous vehicles due to uncertainty in the sensor data, the non-deterministic nature of future, and complex behavior. In this paper, we tackle this problem by representing the scene as dynamic occupancy grid maps (DOGMs) We propose a novel framework that combines deep-temporal and probabilistic approaches to predict vehicle behaviors.
  arXiv  Detail & Related papers  (2023-08-08T14:49:44Z)
• 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)
• Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting [58.45661235893729]
  One promising self-supervised task is 3D point cloud forecasting from unannotated LiDAR sequences. We show that this task requires algorithms to implicitly capture (1) sensor extrinsics (i.e., the egomotion of the autonomous vehicle), (2) sensor intrinsics (i.e., the sampling pattern specific to the particular LiDAR sensor), and (3) the shape and motion of other objects in the scene. We render point cloud data from 4D occupancy predictions given sensor extrinsics and intrinsics, allowing one to train and test occupancy algorithms with unannotated LiDAR sequences.
  arXiv  Detail & Related papers  (2023-02-25T18:12:37Z)
• T2FPV: Constructing High-Fidelity First-Person View Datasets From Real-World Pedestrian Trajectories [9.44806128120871]
  We present T2FPV, a method for constructing high-fidelity first-person view datasets given a real-world, top-down trajectory dataset. We showcase our approach on the ETH/UCY pedestrian dataset to generate the egocentric visual data of all interacting pedestrians.
  arXiv  Detail & Related papers  (2022-09-22T20:14:43Z)
• Predicting Future Occupancy Grids in Dynamic Environment with Spatio-Temporal Learning [63.25627328308978]
  We propose a-temporal prediction network pipeline to generate future occupancy predictions. Compared to current SOTA, our approach predicts occupancy for a longer horizon of 3 seconds. We publicly release our grid occupancy dataset based on nulis to support further research.
  arXiv  Detail & Related papers  (2022-05-06T13:45:32Z)
• Physically constrained short-term vehicle trajectory forecasting with naive semantic maps [6.85316573653194]
  We propose a model that learns to extract relevant road features from semantic maps as well as general motion of agents. We show that our model is not only capable of anticipating future motion whilst taking into consideration road boundaries, but can also effectively and precisely predict trajectories for a longer time horizon than initially trained for.
  arXiv  Detail & Related papers  (2020-06-09T09:52:44Z)

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.