As communication technologies develop, an au- tonomous vehicle will receive information not only from its own sensing system but also from infrastructures and other vehicles through communication. This paper discusses how to exploit a sequence of future information that is shared among autonomous vehicles, including the planned positions, the velocities and the lane numbers. A hybrid system model is constructed, and a control policy is designed to utilize shared sequence information for making navigation decisions. For the high-level discrete state transitions, the shared information is used to determine when to change lane, if lane changing will bring reward for the autonomous vehicle and there exists a feasible continuous state controller. For the low-level continuous state space controller generation, the shared information can relax the safety interval constraints in the existing model predictive control method. In the system level, the information sharing can increase the traffic flow and improve driving comfort. We demonstrate the advantages of information sharing in control and navigation in simulation.
more »
« less
Deep Learning Based Anomaly Detection for Lane Changing Decision
Vehicles can utilize their sensors or receive messages from other vehicles to acquire information about the
surrounding environments. However, the information may be
inaccurate, faulty, or maliciously compromised due to sensor
failures, communication faults, or security attacks. The goal
of this work is to detect if a lane-changing decision and the
sensed or received information are anomalous. We develop
three anomaly detection approaches based on deep learning:
a classifier approach, a predictor approach, and a hybrid
approach combining the classifier and the predictor. All of
them do not need anomalous data nor lateral features so that
they can generally consider lane-changing decisions before the
vehicles start moving along the lateral axis. They achieve at
least 82% and up to 93% F1 scores against anomaly on data
from Simulation of Urban MObility (SUMO) and HighD.
We also examine system properties and verify that the detected
anomaly includes more dangerous scenarios.
more »
« less
- Award ID(s):
- 1908549
- NSF-PAR ID:
- 10374121
- Date Published:
- Journal Name:
- IEEE Intelligent Vehicles Symposium (IV 2022)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Autonomous vehicle trajectory tracking control is challenged by situations of varying road surface friction, especially in the scenario where there is a sudden decrease in friction in an area with high road curvature. If the situation is unknown to the control law, vehicles with high speed are more likely to lose tracking performance and/or stability, resulting in loss of control or the vehicle departing the lane unexpectedly. However, with connectivity either to other vehicles, infrastructure, or cloud services, vehicles may have access to upcoming roadway information, particularly the friction and curvature in the road path ahead. This paper introduces a model-based predictive trajectory-tracking control structure using the previewed knowledge of path curvature and road friction. In the structure, path following and vehicle stabilization are incorporated through a model predictive controller. Meanwhile, long-range vehicle speed planning and tracking control are integrated to ensure the vehicle can slow down appropriately before encountering hazardous road conditions. This approach has two major advantages. First, the prior knowledge of the desired path is explicitly incorporated into the computation of control inputs. Second, the combined transmission of longitudinal and lateral tire forces is considered in the controller to avoid violation of tire force limits while keeping performance and stability guarantees. The efficacy of the algorithm is demonstrated through an application case where a vehicle navigates a sharply curving road with varying friction conditions, with results showing that the controller can drive a vehicle up to the handling limits and track the desired trajectory accurately.more » « less
-
more » « less
Abstract Rio Grande Rise (RGR) and Walvis Ridge (WR) are South Atlantic large igneous provinces (LIPs), formed on the South American and African plates, respectively, mainly by volcanism from a hot spot erupting at the Mid‐Atlantic Ridge (MAR) during the Late Cretaceous. Both display morphologic complexities that imply their tectonic evolution is incompletely understood. We studied bathymetry, gravity, and vertical gravity gradient maps derived from satellite altimetry to trace faults providing indications of seafloor spreading directions and changes. We also examined magnetic anomalies for time constraint and reflection seismic data for structural information. Abyssal hill fabric and magnetic anomaly data indicate that the area between RGR and WR was anomalous between anomalies C34 (83.6 Ma) and C30 (66.4 Ma) owing to reorganization of a right‐lateral transform on the MAR. This event began ∼92 Ma as the transform shifted south to form multiple, short‐offset right‐lateral transforms, with the reorganization extending through anomaly C34 and ending before anomaly C30. Anomalous spacing of magnetic anomalies and discordant fault fabric indicate that a microplate formed with a core of Cretaceous Quiet Zone seafloor. As the MAR jumped eastward, this microplate was captured by the South American plate and now resides mostly in a basin between the main RGR plateau and a related ridge to the east (East Rio Grande Rise). The microplate is ringed by igneous massifs, implying a link with volcanism. The results presented here indicate that these two LIPs had a complex Late Cretaceous history that belies simple hot spot models.
-
Sampling-based motion planning (SBMP) is a major trajectory planning approach in autonomous driving given its high efficiency in practice. As the core of SBMP schemes, sampling strategy holds the key to whether a smooth and collision-free trajectory can be found in real-time. Although some bias sampling strategies have been explored in the literature to accelerate SBMP, the trajectory generated under existing bias sampling strategies may lead to sharp lane changing. To address this issue, we propose a new learning framework for SBMP. Specifically, we develop a novel automatic labeling scheme and a 2-Stage prediction model to improve the accuracy in predicting the intention of surrounding vehicles. We then develop an imitation learning scheme to generate sample points based on the experience of human drivers. Using the prediction results, we design a new bias sampling strategy to accelerate the SBMP algorithm by strategically selecting necessary sample points that can generate a smooth and collision-free trajectory and avoid sharp lane changing. Data-driven experiments show that the proposed sampling strategy outperforms existing sampling strategies, in terms of the computing time, traveling time, and smoothness of the trajectory. The results also show that our scheme is even better than human drivers.more » « less
-
Lateral movement is a key stage of system compromise used by advanced persistent threats. Detecting it is no simple task. When network host logs are abstracted into discrete temporal graphs, the problem can be reframed as anomalous edge detection in an evolving network. Research in modern deep graph learning techniques has produced many creative and complicated models for this task. However, as is the case in many machine learning fields, the generality of models is of paramount importance for accuracy and scalability during training and inference. In this article, we propose a formalized approach to this problem with a framework we call Euler . It consists of a model-agnostic graph neural network stacked upon a model-agnostic sequence encoding layer such as a recurrent neural network. Models built according to the Euler framework can easily distribute their graph convolutional layers across multiple machines for large performance improvements. Additionally, we demonstrate that Euler -based models are as good, or better, than every state-of-the-art approach to anomalous link detection and prediction that we tested. As anomaly-based intrusion detection systems, our models efficiently identified anomalous connections between entities with high precision and outperformed all other unsupervised techniques for anomalous lateral movement detection. Additionally, we show that as a piece of a larger anomaly detection pipeline, Euler models perform well enough for use in real-world systems. With more advanced, yet still lightweight, alerting mechanisms ingesting the embeddings produced by Euler models, precision is boosted from 0.243, to 0.986 on real-world network traffic.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
