Special Issue "Recent Advances in Motion Planning and Control of Autonomous Vehicles"

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Electrical and Autonomous Vehicles".

Deadline for manuscript submissions: 20 August 2023 | Viewed by 10528

Special Issue Editors

College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082, China
Interests: motion planning; computational optimal control; numerical optimization
Department of Mechanical, Industrial and Aerospace Engineering, Concordia University, Montreal, QC H3G 1M8, Canada
Interests: avionics and flight control for manned and unmanned aerial vehicles; monitoring; fault detection and diagnosis (FDD); fault-tolerant (flight) control systems; intelligent and hybrid control systems; UAVs and remote sensing techniques
Special Issues, Collections and Topics in MDPI journals
College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China
Interests: artificial intelligence; motion planning; control for intelligent systems
Department of Computer Engineering, Galatasaray University, Istanbul 34349, Turkey
Interests: intelligent vehicle technologies; driver assistance systems; performance evaluation of inter-vehicle communication

Special Issue Information

Dear Colleagues,

An autonomous vehicle refers to one that runs without a human driver. There has been rapid progress made in the applications of autonomous vehicles on a structured urban road or in an unstructured indoor scenario. Planning and control are two critical modules in an autonomous vehicle system. Concretely, the planning module is responsible for generating an open-loop trajectory, while the control module is to track the desired reference trajectory from the planning module in a closed-loop way and under all possible road, weather, disturbing driving conditions, including even abnormal conditions such as physical failures and cyberattacks. The planning and control modules are important as they directly reflect the intelligence level of an autonomous system. The purpose of this Special Issue is to present the most recent advances in the planning or control methodologies used for an autonomous vehicle. Submitted papers should focus on how the proposed planning and/or control method can solve real-world problems. The editorial board will maintain a high standard to prescreen the submissions which simply propose a generic method without sufficient discussions on its potential to address the real-world bottleneck problems in the community of autonomous driving. Note that we also welcome papers that discuss methods relevant to planning or control, as long as they can make the planning or control module perform better.

Topics of interest include but are not limited to:

  • Path/trajectory/motion planning and replanning;
  • Path/trajectory/motion control;
  • On-road/off-road planning and control;
  • Modeling and simulation method for planning and/or control;
  • Testing and validation method related to planning and/or control;
  • Safety-related issues with planning and control;
  • Security-related issues with planning and control;
  • Human–machine interaction related to planning and/or control;
  • Intelligent techniques/methods to planning and/or control;
  • Integration of planning and control;
  • Reviews of planning or control methodologies;
  • Data-driven/model-based planning or control;
  • Comparisons among different types of planning or control methods;
  • Fault-tolerant planning and control;
  • Cooperative planning and control;
  • Real-world applications of planning and control.

Prof. Dr. Bai Li
Prof. Dr. Youmin Zhang
Prof. Dr. Xiaohui Li
Prof. Dr. Tankut Acarman
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • motion planning
  • path planning
  • trajectory planning
  • motion control
  • path tracking
  • trajectory tracking
  • autonomous driving
  • unmanned system

Published Papers (6 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Article
Space Discretization-Based Optimal Trajectory Planning for Automated Vehicles in Narrow Corridor Scenes
Electronics 2022, 11(24), 4239; https://doi.org/10.3390/electronics11244239 - 19 Dec 2022
Viewed by 701
Abstract
The narrow corridor is a common working scene for automated vehicles, where it is pretty challenging to plan a safe, feasible, and smooth trajectory due to the narrow passable area constraints. This paper presents a space discretization-based optimal trajectory planning method for automated [...] Read more.
The narrow corridor is a common working scene for automated vehicles, where it is pretty challenging to plan a safe, feasible, and smooth trajectory due to the narrow passable area constraints. This paper presents a space discretization-based optimal trajectory planning method for automated vehicles in a narrow corridor scene with the consideration of travel time minimization and boundary collision avoidance. In this method, we first design a mathematically-described driving corridor model. Then, we build a space discretization-based trajectory optimization model in which the objective function is travel efficiency, and the vehicle-kinematics constraints, collision avoidance constraints, and several other constraints are proposed to ensure the feasibility and comfortability of the planned trajectory. Finally, the proposed method is verified with both simulations and field tests. The experimental results demonstrate the trajectory planned by the proposed method is smoother and more computationally efficient compared with the baseline methods while significantly reducing the tracking error indicating the proposed method has huge application potential in trajectory planning in the narrow corridor scenario for automated vehicles. Full article
(This article belongs to the Special Issue Recent Advances in Motion Planning and Control of Autonomous Vehicles)
Show Figures

Figure 1

Article
A Hybrid Asynchronous Brain–Computer Interface Based on SSVEP and Eye-Tracking for Threatening Pedestrian Identification in Driving
Electronics 2022, 11(19), 3171; https://doi.org/10.3390/electronics11193171 - 02 Oct 2022
Viewed by 700
Abstract
A brain–computer interface (BCI) based on steady-state visual evoked potential (SSVEP) has achieved remarkable performance in the field of automatic driving. Prolonged SSVEP stimuli can cause driver fatigue and reduce the efficiency of interaction. In this paper, a multi-modal hybrid asynchronous BCI system [...] Read more.
A brain–computer interface (BCI) based on steady-state visual evoked potential (SSVEP) has achieved remarkable performance in the field of automatic driving. Prolonged SSVEP stimuli can cause driver fatigue and reduce the efficiency of interaction. In this paper, a multi-modal hybrid asynchronous BCI system combining eye-tracking and EEG signals is proposed for dynamic threatening pedestrian identification in driving. Stimuli arrows of different frequencies and directions are randomly superimposed on pedestrian targets. Subjects scan the stimuli according to the direction of arrows until the threatening pedestrian is selected. The thresholds determined by offline experiments are used to distinguish between working and idle states of the asynchronous online experiments. Subjects need to judge and select potentially threatening pedestrians in online experiments according to their own subjective experience. The three proposed decisions filter out the results with low confidence and effectively improve the selection accuracy of hybrid BCI. The experimental results of six subjects show that the proposed hybrid asynchronous BCI system achieves better performance compared with a single SSVEP-BCI, with an average selection time of 1.33 s, an average selection accuracy of 95.83%, and an average information transfer rate (ITR) of 67.50 bits/min. These results indicate that our hybrid asynchronous BCI has great application potential in dynamic threatening pedestrian identification in driving. Full article
(This article belongs to the Special Issue Recent Advances in Motion Planning and Control of Autonomous Vehicles)
Show Figures

Figure 1

Article
Real-Time Drift-Driving Control for an Autonomous Vehicle: Learning from Nonlinear Model Predictive Control via a Deep Neural Network
Electronics 2022, 11(17), 2651; https://doi.org/10.3390/electronics11172651 - 24 Aug 2022
Cited by 1 | Viewed by 2895
Abstract
A drift-driving maneuver is a control technique used by an expert driver to control a vehicle along a sharply curved path or slippery road. This study develops a nonlinear model predictive control (NMPC) method for the autonomous vehicle to perform a drift maneuver [...] Read more.
A drift-driving maneuver is a control technique used by an expert driver to control a vehicle along a sharply curved path or slippery road. This study develops a nonlinear model predictive control (NMPC) method for the autonomous vehicle to perform a drift maneuver and generate the datasets necessary for training the deep neural network(DNN)-based drift controller. In general, the NMPC method is based on numerical optimization which is difficult to run in real-time. By replacing the previously designed NMPC method with the proposed DNN-based controller, we avoid the need for complex numerical optimization of the vehicle control, thereby reducing the computational load. The performance of the developed data-driven drift controller is verified through realistic simulations that included drift scenarios. Based on the results of the simulations, the DNN-based controller showed similar tracking performance to the original nonlinear model predictive controller; moreover, the DNN-based controller can demonstrate stable computation time, which is very important for the safety critical control objective such as drift maneuver. Full article
(This article belongs to the Special Issue Recent Advances in Motion Planning and Control of Autonomous Vehicles)
Show Figures

Figure 1

Article
A Hybrid and Hierarchical Approach for Spatial Exploration in Dynamic Environments
Electronics 2022, 11(4), 574; https://doi.org/10.3390/electronics11040574 - 14 Feb 2022
Cited by 1 | Viewed by 796
Abstract
Exploration in unknown dynamic environments is a challenging problem in an AI system, and current techniques tend to produce irrational exploratory behaviours and fail in obstacle avoidance. To this end, we present a three-tiered hierarchical and modular spatial exploration model that combines the [...] Read more.
Exploration in unknown dynamic environments is a challenging problem in an AI system, and current techniques tend to produce irrational exploratory behaviours and fail in obstacle avoidance. To this end, we present a three-tiered hierarchical and modular spatial exploration model that combines the intrinsic motivation integrated deep reinforcement learning (DRL) and rule-based real-time obstacle avoidance approach. We address the spatial exploration problem in two levels on the whole. On the higher level, a DRL based global module learns to determine a distant but easily reachable target that maximizes the current exploration progress. On the lower level, another two-level hierarchical movement controller is used to produce locally smooth and safe movements between targets based on the information of known areas and free space assumption. Experimental results on diverse and challenging 2D dynamic maps show that the proposed model achieves almost 90% coverage and generates smoother trajectories compared with a state-of-the-art IM based DRL and some other heuristic methods on the basis of avoiding obstacles in real time. Full article
(This article belongs to the Special Issue Recent Advances in Motion Planning and Control of Autonomous Vehicles)
Show Figures

Figure 1

Article
A Path Planning Method for Underground Intelligent Vehicles Based on an Improved RRT* Algorithm
Electronics 2022, 11(3), 294; https://doi.org/10.3390/electronics11030294 - 18 Jan 2022
Cited by 10 | Viewed by 1863
Abstract
Path planning is one of the key technologies for unmanned driving of underground intelligent vehicles. Due to the complexity of the drift environment and the vehicle structure, some improvements should be made to adapt to underground mining conditions. This paper proposes a path [...] Read more.
Path planning is one of the key technologies for unmanned driving of underground intelligent vehicles. Due to the complexity of the drift environment and the vehicle structure, some improvements should be made to adapt to underground mining conditions. This paper proposes a path planning method based on an improved RRT* (Rapidly-Exploring Random Tree Star) algorithm for solving the problem of path planning for underground intelligent vehicles based on articulated structure and drift environment conditions. The kinematics of underground intelligent vehicles are realized by vectorized map and dynamic constraints. The RRT* algorithm is selected for improvement, including dynamic step size, steering angle constraints, and optimal tree reconnection. The simulation case study proves the effectiveness of the algorithm, with a lower path length, lower node count, and 100% steering angle efficiency. Full article
(This article belongs to the Special Issue Recent Advances in Motion Planning and Control of Autonomous Vehicles)
Show Figures

Figure 1

Article
Occlusion-Aware Path Planning to Promote Infrared Positioning Accuracy for Autonomous Driving in a Warehouse
Electronics 2021, 10(24), 3093; https://doi.org/10.3390/electronics10243093 - 13 Dec 2021
Cited by 1 | Viewed by 2113
Abstract
Infrared positioning is a critical module in an indoor autonomous vehicle platform. In an infrared positioning system, the ego vehicle is equipped with an infrared emitter while the infrared receivers are fixed onto the ceiling. The infrared positioning result is accurate only when [...] Read more.
Infrared positioning is a critical module in an indoor autonomous vehicle platform. In an infrared positioning system, the ego vehicle is equipped with an infrared emitter while the infrared receivers are fixed onto the ceiling. The infrared positioning result is accurate only when the number of valid infrared receivers is more than three. An infrared receiver easily becomes invalid if it does not receive light from the infrared emitter due to indoor occlusions. This study proposes an occlusion-aware path planner that enables an autonomous vehicle to navigate toward the occlusion-free part of the drivable area. The planner consists of four layers. In layer one, a homotopic A* path is searched for in the 2D grid map to roughly connect the initial and goal points. In layer two, a curvature-continuous reference line is planned close to the A* path using numerical optimal control. In layer three, a Frenet frame is constructed along the reference line, followed by a search for an occlusion-aware path within that frame via dynamic programming. In layer four, a curvature-continuous path is optimized via quadratic programming within the Frenet frame. A path planned within the Frenet frame may violate the curvature bounds in a real-world Cartesian frame; thus, layer four is implemented through trial and error. Simulation results in CarSim software show that the derived paths reduce the poor positioning risk and are easily tracked by a controller. Full article
(This article belongs to the Special Issue Recent Advances in Motion Planning and Control of Autonomous Vehicles)
Show Figures

Figure 1

Back to TopTop