skip to main content


Title: Clustering Trajectories for Map Construction
We propose a new approach for constructing the underlying map from trajectory data. Our algorithm is based on the idea that road segments can be identified as stable subtrajectory clusters in the data. For this, we consider how subtrajectory clusters evolve for varying distance values, and choose stable values for these. In doing so we avoid a global proximity parameter. Within trajectory clusters, we choose representatives, which are combined to form the map. We experimentally evaluate our algorithm on vehicle and hiking tracking data. These experiments demonstrate that our approach can naturally separate roads that run close to each other and can deal with outliers in the data, two issues that are notoriously difficult in road network reconstruction.  more » « less
Award ID(s):
1637576
NSF-PAR ID:
10072475
Author(s) / Creator(s):
; ; ; ; ; ; ; ;
Date Published:
Journal Name:
Proceedings of the 25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems
Page Range / eLocation ID:
Article 14
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Traffic shockwaves demonstrate the formation and spreading of traffic fluctuation on roads. Existing methods mainly detect the shockwaves and their propagation by estimating traffic density and flow, which presents weaknesses in applications when traffic data is only partially or locally collected. This paper proposed a four-step data-driven approach that integrates machine learning with the traffic features to detect shockwaves and estimate their propagation speeds only using partial vehicle trajectory data. Specifically, we first denoise the speed data derived from trajectory data by the Fast Fourier Transform (FFT) to mitigate the effect of spontaneous random speed fluctuation. Next, we identify trajectory curves’ turning points where a vehicle runs into a shockwave and its speed presents a high standard deviation within a short interval. Furthermore, the Density-based Spatial Clustering of Applications with Noise algorithm (DBSCAN) combined with traffic flow features is adopted to split the turning points into different clusters, each corresponding to a shockwave with constant speed. Last, the one-norm distance regression method is used to estimate the propagation speed of detected shockwaves. The proposed framework was applied to the field data collected from the I-80 and US-101 freeway by the Next Generation Simulation (NGSIM) program. The results show that this four-step data-driven method could efficiently detect the shockwaves and their propagation speeds without estimating the traffic densities and flows nearby. It performs well for both homogenous and nonhomogeneous road segments with trajectory data collected from total or partial traffic flow. 
    more » « less
  2. Modern smart cities need smart transportation solutions to quickly detect various traffic emergencies and incidents in the city to avoid cascading traffic disruptions. To materialize this, roadside units and ambient transportation sensors are being deployed to collect speed data that enables the monitoring of traffic conditions on each road segment. In this paper, we first propose a scalable data-driven anomaly-based traffic incident detection framework for a city-scale smart transportation system. Specifically, we propose an incremental region growing approximation algorithm for optimal Spatio-temporal clustering of road segments and their data; such that road segments are strategically divided into highly correlated clusters. The highly correlated clusters enable identifying a Pythagorean Mean-based invariant as an anomaly detection metric that is highly stable under no incidents but shows a deviation in the presence of incidents. We learn the bounds of the invariants in a robust manner such that anomaly detection can generalize to unseen events, even when learning from real noisy data. Second, using cluster-level detection, we propose a folded Gaussian classifier to pinpoint the particular segment in a cluster where the incident happened in an automated manner. We perform extensive experimental validation using mobility data collected from four cities in Tennessee, compare with the state-of-the-art ML methods, to prove that our method can detect incidents within each cluster in real-time and outperforms known ML methods. 
    more » « less
  3. The significantly increasing number of vehicles brings convenience to daily life while also introducing significant challenges to the transportation network and air pollution. It has been proved that platooning/clustering-based driving can significantly reduce road congestion and exhaust emissions and improve road capacity and energy efficiency. This paper aims to improve the stability of vehicle clustering to enhance the lifetime of cooperative driving. Specifically, we use a Graph Neural Network (GNN) model to learn effective node representations, which can help aggregate vehicles with similar patterns into stable clusters. To the best of our knowledge, this is the first generalized learnable GNN-based model for vehicular ad hoc network clustering. In addition, our centralized approach makes full use of the ubiquitous presence of the base stations and edge clouds. It is noted that a base station has a vantage view of the vehicle distribution within the coverage area as compared to distributed clustering approaches. Specifically, eNodeB-assisted clustering can greatly reduce the control message overhead during the cluster formation and offload to eNodeB the complex computations required for machine learning algorithms. We evaluated the performance of the proposed clustering algorithms on the open-source highD dataset. The experiment results demonstrate that the average cluster lifetime and cluster efficiency of our GNN-based clustering algorithm outperforms state-of-the-art baselines. 
    more » « less
  4. This paper focuses on inverse reinforcement learning (IRL) for autonomous robot navigation using semantic observations. The objective is to infer a cost function that explains demonstrated behavior while relying only on the expert’s observations and state-control trajectory. We develop a map encoder, which infers semantic class probabilities from the observation sequence, and a cost encoder, defined as deep neural network over the semantic features. Since the expert cost is not directly observable, the representation parameters can only be optimized by differentiating the error between demonstrated controls and a control policy computed from the cost estimate. The error is optimized using a closed-form subgradient computed only over a subset of promising states via a motion planning algorithm. We show that our approach learns to follow traffic rules in the autonomous driving CARLA simulator by relying on semantic observations of cars, sidewalks and road lanes. 
    more » « less
  5. Current wireless networks employ sophisticated multi-user transmission techniques to fully utilize the physical layer resources for data transmission. At the MAC layer, these techniques rely on a semi-static map that translates the channel quality of users to the potential transmission rate (more precisely, a map from the Channel Quality Index to the Modulation and Coding Scheme) for user selection and scheduling decisions. However, such a static map does not adapt to the actual deployment scenario and can lead to large performance losses. Furthermore, adaptively learning this map can be inefficient, particularly when there are a large number of users. In this work, we make this learning efficient by clustering users. Specifically, we develop an online learning approach that jointly clusters users and channel-states, and learns the associated rate regions of each cluster. This approach generates a scenario-specific map that replaces the static map that is currently used in practice. Furthermore, we show that our learning algorithm achieves sub- linear regret when compared to an omniscient genie. Next, we develop a user selection algorithm for multi-user scheduling using the learned user-clusters and associated rate regions. Our algorithms are validated on the WiNGS simulator from AT&T Labs, that implements the PHY/MAC stack and simulates the channel. We show that our algorithm can efficiently learn user clusters and the rate regions associated with the user sets for any observed channel state. Moreover, our simulations show that a deployment-scenario-specific map significantly outperforms the current static map approach for resource allocation at the MAC layer. 
    more » « less