Designing a controller for autonomous vehicles capable of providing adequate performance in all driving scenarios is challenging due to the highly complex environment and inability to test the system in the wide variety of scenarios which it may encounter after deployment. However, deep learning methods have shown great promise in not only providing excellent performance for complex and non-linear control problems, but also in generalising previously learned rules to new scenarios. For these reasons, the use of deep learning for vehicle control is becoming increasingly popular. Although important advancements have been achieved in this field, these works have not been fully summarised. This paper surveys a wide range of research works reported in the literature which aim to control a vehicle through deep learning methods. Although there exists overlap between control and perception, the focus of this paper is on vehicle control, rather than the wider perception problem which includes tasks such as semantic segmentation and object detection. The paper identifies the strengths and limitations of available deep learning methods through comparative analysis and discusses the research challenges in terms of computation, architecture selection, goal specification, generalisation, verification and validation, as well as safety. Overall, this survey brings timely and topical information to a rapidly evolving field relevant to intelligent transportation systems.

A Survey of Deep Learning Applications to Autonomous Vehicle Control

Genetic Algorithm Based Approach for Autonomous Mobile Robot Path Planning

This paper presents a hybrid approach for path planning of multiple mobile robots in continuous environments. For this purpose, first, an innovative Artificial Potential Field (APF) algorithm is presented to find all feasible paths between the start and destination locations in a discrete gridded environment. Next, an enhanced Genetic Algorithm (EGA) is developed to improve the initial paths in continuous space and find the optimal path between start and destination locations. The proposed APF works based on a time-efficient deterministic scheme to find a set of feasible initial paths and is guaranteed to find a feasible path if one exists. The EGA utilizes five customized crossover and mutation operators to improve the initial paths. In this paper, path length, smoothness, and safety are combined to form a multi-objective path planning problem. In addition, the proposed method is extended to deal with multiple mobile robot path planning problem. For this purpose, a new term is added to the objective function which measures the distance between robots and a collision removal operator is added to the EGA to remove possible collision between paths. To assess the efficiency of the proposed algorithm, 12 planar environments with different sizes and complexities were examined. Evaluations showed that the control parameters of the proposed algorithm do not affect the performance of the EGA considerably. Moreover, a comparative study has been made between the proposed algorithm, A*, PRM, B-RRT and Particle Swarm Optimization (PSO). The comparative study showed that the proposed algorithm outperforms PSO as well as well-recognized deterministic (A*) and probabilistic (PRM and B-RRT) path planning algorithms in terms of path length, run time, and success rate. Finally, simulations proved the efficiency of the proposed algorithm for a four-robot path planning problem. In this case, not only the proposed algorithm determined collision-free paths, but also it found near optimal solution for all robots.

Multi-objective multi-robot path planning in continuous environment using an enhanced genetic algorithm

Solving the optimal path planning of a mobile robot using improved Q-learning

A path planning approach for crowd evacuation in buildings based on improved artificial bee colony algorithm

Heuristic approaches in robot path planning

Display Omitted A novel hierarchical global path planning approach for mobile robots in a cluttered environment.A proposed particle swarm optimization with an accelerated update methodology based on Pareto dominance principle.Providing optimal global robot paths with computational efficiency. In this paper, a novel hierarchical global path planning approach for mobile robots in a cluttered environment is proposed. This approach has a three-level structure to obtain a feasible, safe and optimal path. In the first level, the triangular decomposition method is used to quickly establish a geometric free configuration space of the robot. In the second level, Dijkstra's algorithm is applied to find a collision-free path used as input reference for the next level. Lastly, a proposed particle swarm optimization called constrained multi-objective particle swarm optimization with an accelerated update methodology based on Pareto dominance principle is employed to generate the global optimal path with the focus on minimizing the path length and maximizing the path smoothness. The contribution of this work consists in: (i) The development of a novel optimal hierarchical global path planning approach for mobile robots moving in a cluttered environment; (ii) The development of proposed particle swarm optimization with an accelerated update methodology based on Pareto dominance principle to solve robot path planning problems; (iii) Providing optimal global robot paths in terms of the path length and the path smoothness taking into account the physical robot system limitations with computational efficiency. Simulation results in various types of environments are conducted in order to illustrate the superiority of the hierarchical approach.

/pdf/a-hierarchical-global-path-planning-approach-for-mobile-3v3z7u8dt3.pdf

A hierarchical global path planning approach for mobile robots based on multi-objective particle swarm optimization

emantic segmentation is an essential task in developing medical image diagnosis systems. However, building an annotated medical dataset is expensive. Thus, semi-supervised methods are significant in this circumstance. In semi-supervised learning, the quality of labels plays a crucial role in modelperformance. In this work, we present a new pseudo labeling strategy that enhances the quality of pseudo labels used for training student networks. We follow the multi-stage semi-supervised training approach, which trains a teacher model on a labeled dataset and then uses the trained teacher to render pseudo labels for student training. By doing so, the pseudo labels will be updated and more precise as training progress. The key difference between previous and our methods is that we update the teacher model during the student training process. So the quality of pseudo labels is improved during the student training process. We also propose a simple but effective strategy to enhance the quality of pseudo labels using a momentum model - a slow copy version of the original model during training. By applying the momentum model combined with re-rendering pseudo labels during student training, we achieved an average of 84.1% Dice Score on five datasets (i.e., Kvarsir, CVC-ClinicDB, ETIS-LaribPolypDB, CVC-ColonDB, and CVC-300) with only 20% of the dataset used as labeled data. Our results surpass common practice by 3% and even approach fully-supervised results on some datasets. Oursource code and pre-trained models are available at https://github.com/sun-asterisk-research/online_learning_ssl

Online pseudo labeling for polyp segmentation with momentum networks

We propose a simple strategy when training the semi-supervised segmentation model. Traditional semi-supervised segmentation methods use all unlabeled data without any priority. However, it is not reasonable to consider all pseudo labels have the same confidence. Our idea is to divide pseudo labels into two sets, high stable and low stable, to alleviate the negative impact of the wrongly pseudo labeled images. We propose a simple algorithm to calculate the reliability scores of pseudo labels and retraining strategies. The experiments on popular colonoscopy polyp datasets show that our method yields satisfactory results and achieves a Dice Coefficient higher than the result of the traditional semi-supervised method using all unlabeled data about 2.3%. Code is available at https://github.com/sun-asterisk-research/prioritizing_stable_images_ssl

Duc Trung Tran

Papers

Heuristic approaches in robot path planning

A hierarchical global path planning approach for mobile robots based on multi-objective particle swarm optimization

Online pseudo labeling for polyp segmentation with momentum networks

Improve polyp semi-supervised segmentation with prioritizing the reliability of unlabeled images