Intervention minimized semi-autonomous control using decoupled model predictive control

Kim, Hayoung; Cho, Jeongmin; Kim, Dongchan; Huh, Kunsoo

doi:10.1109/ivs.2017.7995787

Cited by 20 publications

(12 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A random forest classifier is first designed to assess the driving risk while learning the personal desired velocities, and then the safety-focused MPC and the personalized MPC are conducted to ensure safety in risky situations, and to perform personal driving in risky-free situations, respectively. A shared control problem based on MPC is investigated in [115,116], in which a lane-following, a left turn and a right turn MPC controllers are respectively designed as candidates to match the driver's intended behavior, and the control authority allocation can be dynamically adapted with respect to the driver's authority intention.…”

Section: Mpc For Combined Motion Planning and Control Of An Individual Agvmentioning

confidence: 99%

Model predictive control for autonomous ground vehicles: a review

Hirche

Huang

et al. 2021

Auton. Intell. Syst.

View full text Add to dashboard Cite

This paper reviews model predictive control (MPC) and its wide applications to both single and multiple autonomous ground vehicles (AGVs). On one hand, MPC is a well-established optimal control method, which uses the predicted future information to optimize the control actions while explicitly considering constraints. On the other hand, AGVs are able to make forecasts and adapt their decisions in uncertain environments. Therefore, because of the nature of MPC and the requirements of AGVs, it is intuitive to apply MPC algorithms to AGVs. AGVs are interesting not only for considering them alone, which requires centralized control approaches, but also as groups of AGVs that interact and communicate with each other and have their own controller onboard. This calls for distributed control solutions. First, a short introduction into the basic theoretical background of centralized and distributed MPC is given. Then, it comprehensively reviews MPC applications for both single and multiple AGVs. Finally, the paper highlights existing issues and future research directions, which will promote the development of MPC schemes with high performance in AGVs.

show abstract

Section: Mpc For Combined Motion Planning and Control Of An Individual Agvmentioning

confidence: 99%

Model predictive control for autonomous ground vehicles: a review

Hirche

Huang

et al. 2021

Auton. Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…In equation ( 8), C P C represents the transition matrix from the camera body coordinate system to the image coordinate system, as detailed in equation (5). and x C ru are the theoretical values of the coordinates of the bottom-left and top-right of the ROI in the camera body coordinates, respectively.…”

Section: Adaptively Dynamic Adjustment (Ada) Modelmentioning

confidence: 99%

“…3,4 According to the multimodal sensors data fusion and its own state, the autonomous driving vehicle realizes the driving trajectory planning. 5 Furthermore, it uses the control module to finally obtain control instructions for the steering wheel, accelerator, and brake. 6 Traffic light recognition is an essential part of the perception system.…”

Section: Introductionmentioning

confidence: 99%

An improved traffic lights recognition algorithm for autonomous driving in complex scenarios

Zeng

Liu³

et al. 2021

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Image recognition is susceptible to interference from the external environment. It is challenging to accurately and reliably recognize traffic lights in all-time and all-weather conditions. This article proposed an improved vision-based traffic lights recognition algorithm for autonomous driving, integrating deep learning and multi-sensor data fusion assist (MSDA). We introduce a method to obtain the best size of the region of interest (ROI) dynamically, including four aspects. First, based on multi-sensor data (RTK BDS/GPS, IMU, camera, and LiDAR) acquired in a normal environment, we generated a prior map that contained sufficient traffic lights information. And then, by analyzing the relationship between the error of the sensors and the optimal size of ROI, the adaptively dynamic adjustment (ADA) model was built. Furthermore, according to the multi-sensor data fusion positioning and ADA model, the optimal ROI can be obtained to predict the location of traffic lights. Finally, YOLOv4 is employed to extract and identify the image features. We evaluated our algorithm using a public data set and actual city road test at night. The experimental results demonstrate that the proposed algorithm has a relatively high accuracy rate in complex scenarios and can promote the engineering application of autonomous driving technology.

show abstract

“…velocities, free drivable areas, obstacles' locations, etc.). Third, the path planning module [35], which determines the motion and the optimal path that the vehicle has to follow in order to avoid obstacles and reach a target location, based on the outputs of the perception module. Finally, the control module [36], which commands the vehicle to execute planned actions, such as accelerating, braking and steering, among others.…”

Section: B Visual Attention For Autonomous Vehiclesmentioning

confidence: 99%

Interpretable Global-Local Dynamics for the Prediction of Eye Fixations in Autonomous Driving Scenarios

2020

View full text Add to dashboard Cite

Human eye movements while driving reveal that visual attention largely depends on the context in which it occurs. Furthermore, an autonomous vehicle which performs this function would be more reliable if its outputs were understandable. Capsule Networks have been presented as a great opportunity to explore new horizons in the Computer Vision field, due to their capability to structure and relate latent information. In this paper, we present a hierarchical approach for the prediction of eye fixations in autonomous driving scenarios. Context-driven visual attention can be modeled by considering different conditions which, in turn, are represented as combinations of several spatio-temporal features. With the aim of learning these conditions, we have built an encoder-decoder network which merges visual features' information using a global-local definition of capsules. Two types of capsules are distinguished: representational capsules for features and discriminative capsules for conditions. The latter and the use of eye fixations recorded with wearable eye tracking glasses allow the model to learn both to predict contextual conditions and to estimate visual attention, by means of a multi-task loss function. Experiments show how our approach is able to express either frame-level (global) or pixel-wise (local) relationships between features and contextual conditions, allowing for interpretability while maintaining or improving the performance of black-box related systems in the literature. Indeed, our proposal offers an improvement of 29% in terms of information gain with respect to the best performance reported in the literature. INDEX TERMS Top-down visual attention, eye fixation prediction, context-based learning, interpretability, capsule networks, convolutional neural networks, autonomous driving.

show abstract

Intervention minimized semi-autonomous control using decoupled model predictive control

Cited by 20 publications

References 12 publications

Model predictive control for autonomous ground vehicles: a review

Model predictive control for autonomous ground vehicles: a review

An improved traffic lights recognition algorithm for autonomous driving in complex scenarios

Interpretable Global-Local Dynamics for the Prediction of Eye Fixations in Autonomous Driving Scenarios

Contact Info

Product

Resources

About