Learning to Drive Anywhere

• URL: http://arxiv.org/abs/2309.12295v2
• Date: Mon, 25 Sep 2023 17:54:27 GMT
• Title: Learning to Drive Anywhere
• Authors: Ruizhao Zhu, Peng Huang, Eshed Ohn-Bar, Venkatesh Saligrama
• Abstract summary: We propose AnyD, a single geographically-aware conditional imitation learning model. Our key insight is to introduce a high-capacity geo-location-based channel attention mechanism. Our proposed approach can efficiently scale across inherently imbalanced data distributions and location-dependent events.
• Score: 38.547150940396904
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Human drivers can seamlessly adapt their driving decisions across geographical locations with diverse conditions and rules of the road, e.g., left vs. right-hand traffic. In contrast, existing models for autonomous driving have been thus far only deployed within restricted operational domains, i.e., without accounting for varying driving behaviors across locations or model scalability. In this work, we propose AnyD, a single geographically-aware conditional imitation learning (CIL) model that can efficiently learn from heterogeneous and globally distributed data with dynamic environmental, traffic, and social characteristics. Our key insight is to introduce a high-capacity geo-location-based channel attention mechanism that effectively adapts to local nuances while also flexibly modeling similarities among regions in a data-driven manner. By optimizing a contrastive imitation objective, our proposed approach can efficiently scale across inherently imbalanced data distributions and location-dependent events. We demonstrate the benefits of our AnyD agent across multiple datasets, cities, and scalable deployment paradigms, i.e., centralized, semi-supervised, and distributed agent training. Specifically, AnyD outperforms CIL baselines by over 14% in open-loop evaluation and 30% in closed-loop testing on CARLA.

Related papers

• FedRAV: Hierarchically Federated Region-Learning for Traffic Object Classification of Autonomous Vehicles [7.8896851741869085]
  We propose a novel hierarchically Federated Region-learning framework of Autonomous Vehicles (FedRAV) FedRAV adaptively divides a large area containing vehicles into sub-regions based on the defined region-wise distance, and achieves personalized vehicular models and regional models. Experiment results demonstrate that our framework outperforms those known algorithms, and improves the accuracy by at least 3.69%.
  arXiv  Detail & Related papers  (2024-11-21T09:45:55Z)
• DiFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-Driving [55.53171248839489]
  We propose an ego-centric fully sparse paradigm, named DiFSD, for end-to-end self-driving. Specifically, DiFSD mainly consists of sparse perception, hierarchical interaction and iterative motion planner. Experiments conducted on nuScenes and Bench2Drive datasets demonstrate the superior planning performance and great efficiency of DiFSD.
  arXiv  Detail & Related papers  (2024-09-15T15:55:24Z)
• Reconsidering utility: unveiling the limitations of synthetic mobility data generation algorithms in real-life scenarios [49.1574468325115]
  We evaluate the utility of five state-of-the-art synthesis approaches in terms of real-world applicability. We focus on so-called trip data that encode fine granular urban movements such as GPS-tracked taxi rides. One model fails to produce data within reasonable time and another generates too many jumps to meet the requirements for map matching.
  arXiv  Detail & Related papers  (2024-07-03T16:08:05Z)
• FedDriveScore: Federated Scoring Driving Behavior with a Mixture of Metric Distributions [6.195950768412144]
  Vehicle-cloud collaboration is proposed as a privacy-friendly alternative to centralized learning. This framework includes a consistently federated version of the scoring method to reduce the performance degradation of the global scoring model.
  arXiv  Detail & Related papers  (2024-01-13T02:15:41Z)
• Spatially-Aware Car-Sharing Demand Prediction [3.085449079520639]
  We analyze the average monthly demand in a station-based car-sharing service with spatially-aware learning algorithms. We show that the global Random Forest model with geo-coordinates as an input feature achieves the highest predictive performance with an R-squared score of 0.87. Our study offers effective as well as highly interpretable methods for diagnosing and planning the placement of car-sharing stations.
  arXiv  Detail & Related papers  (2023-03-25T10:10:11Z)
• TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction [149.5716746789134]
  We show data-driven traffic simulation can be formulated as a world model. We present TrafficBots, a multi-agent policy built upon motion prediction and end-to-end driving. Experiments on the open motion dataset show TrafficBots can simulate realistic multi-agent behaviors.
  arXiv  Detail & Related papers  (2023-03-07T18:28:41Z)
• Generative AI-empowered Simulation for Autonomous Driving in Vehicular Mixed Reality Metaverses [130.15554653948897]
  In vehicular mixed reality (MR) Metaverse, distance between physical and virtual entities can be overcome. Large-scale traffic and driving simulation via realistic data collection and fusion from the physical world is difficult and costly. We propose an autonomous driving architecture, where generative AI is leveraged to synthesize unlimited conditioned traffic and driving data in simulations.
  arXiv  Detail & Related papers  (2023-02-16T16:54:10Z)
• One-Shot Domain Adaptive and Generalizable Semantic Segmentation with Class-Aware Cross-Domain Transformers [96.51828911883456]
  Unsupervised sim-to-real domain adaptation (UDA) for semantic segmentation aims to improve the real-world test performance of a model trained on simulated data. Traditional UDA often assumes that there are abundant unlabeled real-world data samples available during training for the adaptation. We explore the one-shot unsupervised sim-to-real domain adaptation (OSUDA) and generalization problem, where only one real-world data sample is available.
  arXiv  Detail & Related papers  (2022-12-14T15:54:15Z)
• Transferable and Adaptable Driving Behavior Prediction [34.606012573285554]
  We propose HATN, a hierarchical framework to generate high-quality, transferable, and adaptable predictions for driving behaviors. We demonstrate our algorithms in the task of trajectory prediction for real traffic data at intersections and roundabouts from the INTERACTION dataset.
  arXiv  Detail & Related papers  (2022-02-10T16:46:24Z)
• Data Driven Prediction Architecture for Autonomous Driving and its Application on Apollo Platform [1.1142354615369274]
  We introduce a highly automated learning-based prediction model pipeline to support different prediction learning sub-modules' data annotation, feature extraction, model training/tuning and deployment. This pipeline is completely automatic without any human intervention and shows an up to 400% efficiency increase in parameter tuning, when deployed at scale in different scenarios across nations.
  arXiv  Detail & Related papers  (2020-06-11T18:16:12Z)

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.