Efficient and Safe Vehicle Navigation Based on Driver Behavior Classification

Cheung, Ernest; Bera, Aniket; Manocha, Dinesh

doi:10.1109/cvprw.2018.00149

Cited by 17 publications

(9 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PORCA [21] infers intentions with Bayesian inference, but it assumes responsibility changes deterministically and all the agents are fully attentive. The work in [22] learns a linear mapping from selected features to attention values. The mapping, however, is learned for cars and might not be suitable for traffic agents of other types.…”

Section: Related Work a Traditional Approaches For Motion Predictionmentioning

confidence: 99%

GAMMA: A General Agent Motion Model for Autonomous Driving

Luo¹,

Cai²,

Lee³

et al. 2019

Preprint

View full text Add to dashboard Cite

Autonomous driving in mixed traffic requires reliable motion prediction of nearby traffic agents such as pedestrians, bicycles, cars, buses, etc.. This prediction problem is extremely challenging because of the diverse dynamics and geometry of traffic agents, complex road conditions, and intensive interactions among the agents. In this paper, we proposed GAMMA, a general agent motion prediction model for autonomous driving, that can predict the motion of heterogeneous traffic agents with different kinematics, geometry, human agents' inner states, etc.. GAMMA formalizes motion prediction as geometric optimization in the velocity space, and integrates physical constraints and human inner states into this unified framework. Our results show that GAMMA outperforms state-of-the-art approaches significantly on diverse real-world datasets.

show abstract

Section: Related Work a Traditional Approaches For Motion Predictionmentioning

confidence: 99%

GAMMA: A General Agent Motion Model for Autonomous Driving

Luo¹,

Cai²,

Lee³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…After analyzing the vehicle trajectory to identify the driver's behavior, the automatic vehicle navigation algorithm (Autono Vi) was optimized and extended to reduce the influence of navigation on the driving behavior [23]. Cheung proposed an autonomous driving planning algorithm that considered the behavior of neighboring drivers' behaviors, which greatly improved the safety and effectiveness of the navigation system [24]. ese studies show that people have a deep understanding of the secondary tasks that are generated in the process of driving, but the impact of the smartphone as a navigation tool on driving behavior has not been studied extensively.…”

Section: Introductionmentioning

confidence: 99%

Research on the Influence of Smartphone Navigation on Driving Behavior Based on Real Vehicle Driving

Dong

Rong-guo

Zhang

et al. 2019

Mobile Information Systems

View full text Add to dashboard Cite

This paper discusses a study of the influence of different positions and modes of smartphone navigation devices on driving behavior based on real vehicle driving. Twenty professional drivers participated in the experiment in free-flowing traffic and good weather conditions. The eye movement and vehicle control data obtained in the experiment were used as indicators for evaluation. Comparison of the mean, variance, and significance analysis shows that a smartphone navigation device placed on the right side of the car dashboard (position 1) has less impact on driving behavior than when placed above the air conditioning vent (position 2). A smaller angle of view can increase the fixation frequency and the length of time that the driver spends looking out the windshield and reduce the range and time spent in glancing at the navigation device. Using only sound navigation (the audio group in this paper) has the least influence on driving behavior because the driver’s visual attention is not transferred inside the vehicle rather than on the road ahead, and the vehicle is operated in the most stable state. These findings have practical significance for reducing the negative influence of smartphone navigation.

show abstract

“…Variants such as GVO [23], NH-ORCA [24], B-ORCA [25], PORCA [26] explicitly handle non-holonomic traffic agents. Some variants model behavioral types of crowd agents such as patience [26] and attention [27]. A recent model GAMMA [28] can simulate heterogeneous traffic agents with different geometry, kinematics, and behavioral types in a unified, velocity-space framework.…”

Section: B Crowd Simulation Algorithmsmentioning

confidence: 99%