Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userUnderstanding the merging behavior patterns and evolutionary mechanism at freeway on-ramps
114
0
0.0
(
0
)
Added by
Yue Zhang
Publication date
2021
fields
Electronic Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Understanding the merging behavior patterns at freeway on-ramps is important for assistanting the decisions of autonomous driving. This study develops a primitive-based framework to identify the driving patterns during merging processes and reveal the evolutionary mechanism at freeway on-ramps in congested traffic flow. The Nonhomogeneous Hidden Markov Model is introduced to decompose the merging processes into primitives containing semantic information. Then, the time-series K-means clustering is utilized to gather these primitives with variable-length time series into interpretable merging behavior patterns. Different from traditional state segmentation methods (e.g. Hidden Markov Model), the model proposed in this study considers the dependence of transition probability on exogenous variables, thereby revealing the influence of covariates on the evolution of driving patterns. This approach is evaluated in the merging area at a freeway on-ramp using the INTERACTION dataset. Results demonstrate that the approach provides an insight about the complicated merging processes. The findings about interpretable merging behavior patterns as well as the evolutionary mechanism can be used to design and improve the merging decision-making for autonomous vehicles.
rate research
Read More
Merging at highway on-ramps while interacting with other human-driven vehicles is challenging for autonomous vehicles (AVs). An efficient route to this challenge requires exploring and exploiting knowledge of the interaction process from demonstrations by humans. However, it is unclear what information (or environmental states) is utilized by the human driver to guide their behavior throughout the whole merging process. This paper provides quantitative analysis and evaluation of the merging behavior at highway on-ramps with congested traffic in a volume of time and space. Two types of social interaction scenarios are considered based on the social preferences of surrounding vehicles: courteous and rude. The significant levels of environmental states for characterizing the interactive merging process are empirically analyzed based on the real-world INTERACTION dataset. Experimental results reveal two fundamental mechanisms in the merging process: 1) Human drivers select different states to make sequential decisions at different moments of task execution, and 2) the social preference of surrounding vehicles can impact variable selection for making decisions. It implies that efficient decision-making design should filter out irrelevant information while considering social preference to achieve comparable human-level performance. These essential findings shed light on developing new decision-making approaches for AVs.
Humans make daily routine decisions based on their internal states in intricate interaction scenarios. This paper presents a probabilistically reconstructive learning approach to identify the internal states of multi-vehicle sequential interactions when merging at highway on-ramps. We treated the merging tasks sequential decision as a dynamic, stochastic process and then integrated the internal states into an HMM-GMR model, a probabilistic combination of an extended Gaussian mixture regression (GMR) and hidden Markov models (HMM). We also developed a variant expectation-maximum (EM) algorithm to estimate the model parameters and verified it based on a real-world data set. Experiment results reveal that three interpretable internal states can semantically describe the interactive merge procedure at highway on-ramps. This finding provides a basis to develop an efficient model-based decision-making algorithm for autonomous vehicles (AVs) in a partially observable environment.
Freeway on-ramps are typical bottlenecks in the freeway network due to the frequent disturbances caused by their associated merging, weaving, and lane-changing behaviors. With real-time communication and precise motion control, Connected and Autonomous Vehicles (CAVs) provide an opportunity to substantially enhance the traffic operational performance of on-ramp bottlenecks. In this paper, we propose an upper-level control strategy to coordinate the two traffic streams at on-ramp merging through proactive gap creation and platoon formation. The coordination consists of three components: (1) mainline vehicles proactively decelerate to create large merging gaps; (2) ramp vehicles form platoons before entering the main road; (3) the gaps created on the main road and the platoons formed on the ramp are coordinated with each other in terms of size, speed, and arrival time. The coordination is formulated as a constrained optimization problem, incorporating both macroscopic and microscopic traffic flow models, for flow-level efficiency gains. The model uses traffic state parameters as inputs and determines the optimal coordination plan adaptive to real-time traffic conditions. The benefits of the proposed coordination are demonstrated through an illustrative case study. Results show that the coordination is compatible with real-world implementation and can substantially improve the overall efficiency of on-ramp merging, especially under high traffic volume conditions, where recurrent traffic congestion is prevented, and merging throughput increased.
The human ability of deep cognitive skills are crucial for the development of various real-world applications that process diverse and abundant user generated input. While recent progress of deep learning and natural language processing have enabled learning system to reach human performance on some benchmarks requiring shallow semantics, such human ability still remains challenging for even modern contextual embedding models, as pointed out by many recent studies. Existing machine comprehension datasets assume sentence-level input, lack of casual or motivational inferences, or could be answered with question-answer bias. Here, we present a challenging novel task, trope detection on films, in an effort to create a situation and behavior understanding for machines. Tropes are storytelling devices that are frequently used as ingredients in recipes for creative works. Comparing to existing movie tag prediction tasks, tropes are more sophisticated as they can vary widely, from a moral concept to a series of circumstances, and embedded with motivations and cause-and-effects. We introduce a new dataset, Tropes in Movie Synopses (TiMoS), with 5623 movie synopses and 95 different tropes collecting from a Wikipedia-style database, TVTropes. We present a multi-stream comprehension network (MulCom) leveraging multi-level attention of words, sentences, and role relations. Experimental result demonstrates that modern models including BERT contextual embedding, movie tag prediction systems, and relational networks, perform at most 37% of human performance (23.97/64.87) in terms of F1 score. Our MulCom outperforms all modern baselines, by 1.5 to 5.0 F1 score and 1.5 to 3.0 mean of average precision (mAP) score. We also provide a detailed analysis and human evaluation to pave ways for future research.
We revisit the dynamics of Prometheus and Pandora, two small moons flanking Saturns F ring. Departures of their orbits from freely precessing ellipses result from mutual interactions via their 121:118 mean motion resonance. Motions are chaotic because the resonance is split into four overlapping components. Orbital longitudes were observed to drift away from Voyager predictions, and a sudden jump in mean motions took place close to the time at which the orbits apses were antialigned in 2000. Numerical integrations reproduce both the longitude drifts and the jumps. The latter have been attributed to the greater strength of interactions near apse antialignment (every 6.2 years), and it has been assumed that this drift-jump behavior will continue indefinitely. We re-examine the dynamics by analogy with that of a nearly adiabatic, parametric pendulum. In terms of this analogy, the current value of the action of the satellite system is close to its maximum in the chaotic zone. Consequently, at present, the two separatrix crossings per precessional cycle occur close to apse antialignment. In this state libration only occurs when the potentials amplitude is nearly maximal, and the jumps in mean motion arise during the short intervals of libration that separate long stretches of circulation. Because chaotic systems explore the entire region of phase space available to them, we expect that at other times the system would be found in states of medium or low action. In a low action state it would spend most of the time in libration, and separatrix crossings would occur near apse alignment. We predict that transitions between these different states can happen in as little as a decade. Therefore, it is incorrect to assume that sudden changes in the orbits only happen near apse antialignment.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
