The last decade witnessed increasingly rapid progress in self‐driving vehicle technology, mainly backed up by advances in the area of deep learning and artificial intelligence (AI). The objective of this paper is to survey the current state‐of‐the‐art on deep learning technologies used in autonomous driving. We start by presenting AI‐based self‐driving architectures, convolutional and recurrent neural networks, as well as the deep reinforcement learning paradigm. These methodologies form a base for the surveyed driving scene perception, path planning, behavior arbitration, and motion control algorithms. We investigate both the modular perception‐planning‐action pipeline, where each module is built using deep learning methods, as well as End2End systems, which directly map sensory information to steering commands. Additionally, we tackle current challenges encountered in designing AI architectures for autonomous driving, such as their safety, training data sources, and computational hardware. The comparison presented in this survey helps gain insight into the strengths and limitations of deep learning and AI approaches for autonomous driving and assist with design choices.

SUMMARYIn this paper, a Brain–Computer Interface (BCI) control approach for the assistive robotic system FRIEND is presented. The objective of the robot is to assist elderly and persons with disabilities in their daily and professional life activities. FRIEND is presented here from an architectural point of view, that is, as an overall robotic device that includes many subareas of research, such as human–robot interaction, perception, object manipulation and path planning, robotic safety, and so on. The integration of the hardware and software components is described relative to the interconnections between the various elements of FRIEND and the approach used for human–machine interaction. Since the robotic system is intended to be used especially by patients suffering from a high degree of disability (e.g., patients which are quadriplegic, have muscle diseases or serious paralysis due to strokes, or any other diseases with similar consequences for their independence), an alternative non-invasive BCI has been investigated. The FRIEND–BCI paradigm is explained within the overall structure of the robot. The capabilities of the robotic system are demonstrated in three support scenarios, one that deals with Activities of daily living (ADL) and two that are taking place in a rehabilitation workshop. The proposed robot was clinically evaluated through different tests that directly measure task execution time and hardware performance, as well as the acceptance of robot by end-users.

Autonomous vehicles are controlled today either based on sequences of decoupled perception-planning-action operations, either based on End2End or Deep Reinforcement Learning (DRL) systems. Current deep learning solutions for autonomous driving are subject to several limitations (e.g. they estimate driving actions through a direct mapping of sensors to actuators, or require complex reward shaping methods). Although the cost function used for training can aggregate multiple weighted objectives, the gradient descent step is computed by the backpropagation algorithm using a singleobjective loss. To address these issues, we introduce NeuroTrajectory, which is a multi-objective neuroevolutionary approach to local state trajectory learning for autonomous driving, where the desired state trajectory of the ego-vehicle is estimated over a finite prediction horizon by a perception-planning deep neural network. In comparison to DRL methods, which predict optimal actions for the upcoming sampling time, we estimate a sequence of optimal states that can be used for motion control. We propose an approach which uses genetic algorithms for training a population of deep neural networks, where each network individual is evaluated based on a multi-objective fitness vector, with the purpose of establishing a so-called Pareto front of optimal deep neural networks. The performance of an individual is given by a fitness vector composed of three elements. Each element describes the vehicle's travel path, lateral velocity and longitudinal speed, respectively. The same network structure can be trained on synthetic, as well as on real-world data sequences. We have benchmarked our system against a baseline Dynamic Window Approach (DWA), as well as against an End2End supervised learning method.

No abstract

Current state of the art solutions in the control of an autonomous vehicle mainly use supervised end-to-end learning, or decoupled perception, planning and action pipelines. Another possible solution is deep reinforcement learning, but such a method requires that the agent interacts with its surroundings in a simulated environment. In this paper we introduce GridSim, which is an autonomous driving simulator engine running a car-like robot architecture to generate occupancy grids from simulated sensors. We use GridSim to study the performance of two deep learning approaches, deep reinforcement learning and driving behavioral learning through genetic algorithms. The deep network encodes the desired behavior in a two elements fitness function describing a maximum travel distance and a maximum forward speed, bounded to a specific interval. The algorithms are evaluated on simulated highways, curved roads and innercity scenarios, all including different driving limitations.

Highly Autonomous Driving (HAD) systems rely on deep neural networks for the visual perception of the driving environment. Such networks are trained on large manually annotated databases. In this work, a semi-parametric approach to one-shot learning is proposed, with the aim of bypassing the manual annotation step required for training perceptions systems used in autonomous driving. The proposed generative framework, coined Generative One-Shot Learning (GOL), takes as input single one-shot objects, or generic patterns, and a small set of so-called regularization samples used to drive the generative process. New synthetic data is generated as Pareto optimal solutions from one-shot objects using a set of generalization functions built into a generalization generator. GOL has been evaluated on environment perception challenges encountered in autonomous vision.

No abstract

No abstract