Investigating Robotaxi Crash Severity with Geographical Random Forest and the Urban Environment
- URL: http://arxiv.org/abs/2505.06762v2
- Date: Mon, 04 Aug 2025 04:59:12 GMT
- Title: Investigating Robotaxi Crash Severity with Geographical Random Forest and the Urban Environment
- Authors: Junfeng Jiao, Seung Gyu Baik, Seung Jun Choi, Yiming Xu,
- Abstract summary: This paper quantitatively investigates the crash severity of Autonomous Vehicles (AVs) with spatially localized machine learning and macroscopic measures of the urban built environment.<n>Land use was the most important predictor, compared to intersections, building footprints, public transit stops, and Points Of Interest (POIs)<n> AV crashes were more likely to result in low-severity incidents in city center areas with greater diversity and commercial activities, than in residential neighborhoods.
- Score: 5.023563968303034
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper quantitatively investigates the crash severity of Autonomous Vehicles (AVs) with spatially localized machine learning and macroscopic measures of the urban built environment. Extending beyond the microscopic effects of individual infrastructure elements, we focus on the city-scale land use and behavioral patterns, while addressing spatial heterogeneity and spatial autocorrelation. We implemented a spatially localized machine learning technique called Geographical Random Forest (GRF) on the California AV collision dataset. Analyzing multiple urban measures, including points of interest, building footprint, and land use, we built a GRF model and visualized it as a crash severity risk map of San Francisco. This paper presents three findings. First, spatially localized machine learning outperformed regular machine learning in predicting AV crash severity. The bias-variance tradeoff was evident as we adjusted the localization weight hyperparameter. Second, land use was the most important predictor, compared to intersections, building footprints, public transit stops, and Points Of Interest (POIs). Third, AV crashes were more likely to result in low-severity incidents in city center areas with greater diversity and commercial activities, than in residential neighborhoods. Residential land use is likely associated with higher severity due to human behavior and less restrictive environments. Counterintuitively, residential areas were associated with higher crash severity, compared to more complex areas such as commercial and mixed-use areas. When robotaxi operators train their AV systems, it is recommended to: (1) consider where their fleet operates and make localized algorithms for their perception system, and (2) design safety measures specific to residential neighborhoods, such as slower driving speeds and more alert sensors.
Related papers
- Spatially-Heterogeneous Causal Bayesian Networks for Seismic Multi-Hazard Estimation: A Variational Approach with Gaussian Processes and Normalizing Flows [4.522511094629472]
Post-earthquake hazard and impact estimation are critical for effective disaster response.<n>Traditional models employ fixed parameters regardless of geographical context, misrepresenting how seismic effects vary across diverse landscapes.<n>We address these challenges with a spatially-aware causal Bayesian network that decouples co-located hazards by modeling their causal relationships with location-specific parameters.
arXiv Detail & Related papers (2025-04-05T01:34:43Z) - Spatial-variant causal Bayesian inference for rapid seismic ground failures and impacts estimation [3.190793775376023]
Rapid and accurate estimation of post-earthquake ground failures and building damage is critical for effective post-disaster responses.<n>Previous advancements introduced a novel causal graph-based Bayesian network that continually refines seismic ground failure and building damage estimates derived from satellite imagery.<n>In this study, we pioneer an approach that accounts for spatial intricacies by introducing a spatial variable influenced by the bilateral filter to capture relationships from surrounding hazards.
arXiv Detail & Related papers (2024-11-18T15:01:28Z) - Risk Assessment for Autonomous Landing in Urban Environments using Semantic Segmentation [0.0]
We propose employing the SegFormer, a state-of-the-art visual transformer network, for semantic segmentation of urban environments.
The proposed strategy is validated through several case studies.
We believe will help unleash the full potential of UAVs on civil applications within urban areas.
arXiv Detail & Related papers (2024-10-16T19:34:03Z) - SpatialRank: Urban Event Ranking with NDCG Optimization on
Spatiotemporal Data [55.609946936979036]
We propose a novel spatial event ranking approach named SpatialRank.
We show that SpatialRank can effectively identify the top riskiest locations of crimes and traffic accidents.
arXiv Detail & Related papers (2023-09-30T06:20:21Z) - GeoNet: Benchmarking Unsupervised Adaptation across Geographies [71.23141626803287]
We study the problem of geographic robustness and make three main contributions.
First, we introduce a large-scale dataset GeoNet for geographic adaptation.
Second, we hypothesize that the major source of domain shifts arise from significant variations in scene context.
Third, we conduct an extensive evaluation of several state-of-the-art unsupervised domain adaptation algorithms and architectures.
arXiv Detail & Related papers (2023-03-27T17:59:34Z) - Dwelling Type Classification for Disaster Risk Assessment Using
Satellite Imagery [3.88838725116957]
Vulnerability and risk assessment of neighborhoods is essential for effective disaster preparedness.
Existing traditional systems, due to dependency on time-consuming and cost-intensive field surveying, do not provide a scalable way to decipher warnings and assess the precise extent of the risk at a hyper-local level.
In this work, machine learning was used to automate the process of identifying dwellings and their type to build a potentially more effective disaster vulnerability assessment system.
arXiv Detail & Related papers (2022-11-16T03:08:15Z) - Dfferentiable Raycasting for Self-supervised Occupancy Forecasting [52.61762537741392]
Motion planning for autonomous driving requires learning how the environment around an ego-vehicle evolves with time.
In this paper, we use geometric occupancy as a natural alternative to view-dependent representations such as freespace.
Our key insight is to use differentiable raycasting to "render" future occupancy predictions into future LiDAR sweep predictions.
arXiv Detail & Related papers (2022-10-04T21:35:21Z) - Visual-based Safe Landing for UAVs in Populated Areas: Real-time
Validation in Virtual Environments [0.0]
We propose a framework for real-time safe and thorough evaluation of vision-based autonomous landing in populated scenarios.
We propose to use the Unreal graphics engine coupled with the AirSim plugin for drone's simulation.
We study two different criteria for selecting the "best" SLZ, and evaluate them during autonomous landing of a virtual drone in different scenarios.
arXiv Detail & Related papers (2022-03-25T17:22:24Z) - HintNet: Hierarchical Knowledge Transfer Networks for Traffic Accident
Forecasting on Heterogeneous Spatio-Temporal Data [17.345649325770957]
Traffic accident forecasting is a significant problem for transportation management and public safety.
The occurrence of traffic accidents is affected by complex dependencies among spatial and temporal features.
Recent traffic accident prediction methods have attempted to use deep learning models to improve accuracy.
arXiv Detail & Related papers (2022-03-07T02:11:04Z) - Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers [126.81938540470847]
We propose Euro-PVI, a dataset of pedestrian and bicyclist trajectories.
In this work, we develop a joint inference model that learns an expressive multi-modal shared latent space across agents in the urban scene.
We achieve state of the art results on the nuScenes and Euro-PVI datasets demonstrating the importance of capturing interactions between ego-vehicle and pedestrians (bicyclists) for accurate predictions.
arXiv Detail & Related papers (2021-06-22T15:40:21Z) - Impacts of shared autonomous vehicles: Tradeoff between parking demand
reduction and congestion increase [0.0]
Shared autonomous vehicles (SAVs) can have significant impacts on the transport system and land use by replacing private vehicles.
This study estimates the impacts of SAVs at the local scale by simulating their operation on a developed simulator.
arXiv Detail & Related papers (2021-04-30T14:16:47Z) - Deep Multi-Task Learning for Joint Localization, Perception, and
Prediction [68.50217234419922]
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.
arXiv Detail & Related papers (2021-01-17T17:20:31Z) - Safety-Oriented Pedestrian Motion and Scene Occupancy Forecasting [91.69900691029908]
We advocate for predicting both the individual motions as well as the scene occupancy map.
We propose a Scene-Actor Graph Neural Network (SA-GNN) which preserves the relative spatial information of pedestrians.
On two large-scale real-world datasets, we showcase that our scene-occupancy predictions are more accurate and better calibrated than those from state-of-the-art motion forecasting methods.
arXiv Detail & Related papers (2021-01-07T06:08:21Z) - A Comparison of Statistical and Machine Learning Algorithms for
Predicting Rents in the San Francisco Bay Area [0.0]
We present a use case in which predictive accuracy is of primary importance, and compare the use of random forest regression to multiple regression.
We find that we are able to obtain useful predictions from both models using almost exclusively local accessibility variables.
arXiv Detail & Related papers (2020-11-26T08:50:45Z) - ParkPredict: Motion and Intent Prediction of Vehicles in Parking Lots [65.33650222396078]
We develop a parking lot environment and collect a dataset of human parking maneuvers.
We compare a multi-modal Long Short-Term Memory (LSTM) prediction model and a Convolution Neural Network LSTM (CNN-LSTM) to a physics-based Extended Kalman Filter (EKF) baseline.
Our results show that 1) intent can be estimated well (roughly 85% top-1 accuracy and nearly 100% top-3 accuracy with the LSTM and CNN-LSTM model); 2) knowledge of the human driver's intended parking spot has a major impact on predicting parking trajectory; and 3) the semantic representation of the environment
arXiv Detail & Related papers (2020-04-21T20:46:32Z)
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.