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. 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 to gain insight into the strengths and limitations of deep learning and AI approaches for autonomous driving and assist with design choices

A survey of deep learning techniques for autonomous driving

A Survey of Deep Learning Techniques for Autonomous Driving

In this letter, we present a learning-based control approach for autonomous racing with an application to the AMZ Driverless race car gotthard 
. One major issue in autonomous racing is that accurate vehicle models that cover the entire performance envelope of a race car are highly nonlinear, complex, and complicated to identify, rendering them impractical for control. To address this issue, we employ a relatively simple nominal vehicle model, which is improved based on measurement data and tools from machine learning.The resulting formulation is an online learning data-driven model predictive controller, which uses Gaussian processes regression to take residual model uncertainty into account and achieve safe driving behavior. To improve the vehicle model online, we select from a constant in-flow of data points according to a criterion reflecting the information gain, and maintain a small dictionary of 300 data points. The framework is tested on the full-size AMZ Driverless race car, where it is able to improve the vehicle model and reduce lap times by $ {\mathbf{10}{\%}}$ while maintaining safety of the vehicle.

/pdf/learning-based-model-predictive-control-for-autonomous-hel0mymyfc.pdf

Learning-Based Model Predictive Control for Autonomous Racing

지속적 발전을 위한 한국형 Infrastructure Report Card 개발

We present a learning model predictive controller (LMPC) for autonomous racing. We model the autonomous racing problem as a minimum time iterative control task, where an iteration corresponds to a lap. The system trajectory and input sequence of each lap are stored and used to systematically update the controller for the next lap. In the proposed approach, the race time does not increase at each iteration. The first contribution is to propose a local LMPC which reduces the computational burden associated with existing LMPC strategies. In particular, we show how to construct a local safe set and approximation to the value function, using a subset of the stored data. The second contribution is to present a system identification strategy for the autonomous racing iterative control task. We use data from previous iterations and the vehicle’s kinematic equations of motion to build an affine time-varying prediction model. The effectiveness of the proposed strategy is demonstrated by experimental results on the Berkeley Autonomous Race Car (BARC) platform.

Learning How to Autonomously Race a Car: A Predictive Control Approach

This paper presents an omnidirectional aerial manipulation platform for robust and responsive interaction with unstructured environments, toward the goal of contact-based inspection. The fully actuated tilt-rotor aerial system is equipped with a rigidly mounted end-effector, and is able to exert a 6 degree of freedom force and torque, decoupling the system's translational and rotational dynamics, and enabling precise interaction with the environment while maintaining stability. An impedance controller with selective apparent inertia is formulated to permit compliance in certain degrees of freedom while achieving precise trajectory tracking and disturbance rejection in others. Experiments demonstrate disturbance rejection, push-and-slide interaction, and on-board state estimation with depth servoing to interact with local surfaces. The system is also validated as a tool for contact-based non-destructive testing of concrete infrastructure.

An Omnidirectional Aerial Manipulation Platform for Contact-Based Inspection

We propose an optimization based, data-driven framework to design controllers for repetitive tasks. The proposed framework builds on previous work of Learning Model Predictive Control and focuses on problems where the terminal condition of one iteration is the initial condition of the next iteration. A terminal cost and a sampled safe set are learned from data to guarantee recursive feasibility and non-decreasing performance cost at each iteration. The proposed control logic is tested on an autonomous racing example, where the vehicle dynamics are identified online. Experimental results on a 1:10 scale RC car illustrate the effectiveness of the proposed approach.

Repetitive learning model predictive control: An autonomous racing example

This article presents and validates active interaction force control and planning for fully actuated and omnidirectional aerial manipulation platforms, with the goal of aerial contact inspection in unstructured environments. We present a variable axis-selective impedance control which integrates direct force control for intentional interaction, using feedback from an on-board force sensor. The control approach aims to reject disturbances in free flight, while handling unintentional interaction and actively controlling desired interaction forces. A fully actuated and omnidirectional tilt-rotor aerial system is used to show capabilities of the control and planning methods. Experiments demonstrate disturbance rejection, push-and-slide interaction, and force-controlled interaction in different flight orientations. The system is validated as a tool for nondestructive testing of concrete infrastructure, and statistical results of interaction control performance are presented and discussed.

Active Interaction Force Control for Contact-Based Inspection With a Fully Actuated Aerial Vehicle

This paper presents and validates active interaction force control and planning for fully actuated and omnidirectional aerial manipulation platforms, with the goal of aerial contact inspection in unstructured environments. We present a variable axis-selective impedance control which integrates direct force control for intentional interaction, using feedback from an on-board force sensor. The control approach aims to reject disturbances in free flight, while handling unintentional interaction, and actively controlling desired interaction forces. A fully actuated and omnidirectional tilt-rotor aerial system is used to show capabilities of the control and planning methods. Experiments demonstrate disturbance rejection, push-and-slide interaction, and force controlled interaction in different flight orientations. The system is validated as a tool for non-destructive testing of concrete infrastructure, and statistical results of

Active Interaction Force Control for Contact-Based Inspection with a Fully Actuated Aerial Vehicle.

Omnidirectional micro aerial vehicles are a growing field of research, with demonstrated advantages for aerial interaction and uninhibited observation. While systems with complete pose omnidirectionality and high hover efficiency have been developed independently, a robust system that combines the two has not been demonstrated to date. This paper presents the design and optimal control of a novel omnidirectional vehicle that can exert a wrench in any orientation while maintaining efficient flight configurations. The system design is motivated by the result of a morphology design optimization. A six degrees of freedom optimal controller is derived, with an actuator allocation approach that implements task prioritization, and is robust to singularities. Flight experiments demonstrate and verify the system's capabilities.

Maximilian Brunner

Papers

An Omnidirectional Aerial Manipulation Platform for Contact-Based Inspection

Repetitive learning model predictive control: An autonomous racing example

Active Interaction Force Control for Contact-Based Inspection With a Fully Actuated Aerial Vehicle

Active Interaction Force Control for Contact-Based Inspection with a Fully Actuated Aerial Vehicle.

Design and optimal control of a tiltrotor micro aerial vehicle for efficient omnidirectional flight