There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Self-driving vehicles are a maturing technology with the potential to reshape mobility by enhancing the safety, accessibility, efficiency, and convenience of automotive transportation. Safety-critical tasks that must be executed by a self-driving vehicle include planning of motions through a dynamic environment shared with other vehicles and pedestrians, and their robust executions via feedback control. The objective of this paper is to survey the current state of the art on planning and control algorithms with particular regard to the urban setting. A selection of proposed techniques is reviewed along with a discussion of their effectiveness. The surveyed approaches differ in the vehicle mobility model used, in assumptions on the structure of the environment, and in computational requirements. The side by side comparison presented in this survey helps to gain insight into the strengths and limitations of the reviewed approaches and assists with system level design choices.

A Survey of Motion Planning and Control Techniques for Self-Driving Urban Vehicles

Self-driving vehicles are a maturing technology with the potential to reshape mobility by enhancing the safety, accessibility, efficiency, and convenience of automotive transportation. Safety-critical tasks that must be executed by a self-driving vehicle include planning of motions through a dynamic environment shared with other vehicles and pedestrians, and their robust executions via feedback control. The objective of this paper is to survey the current state of the art on planning and control algorithms with particular regard to the urban setting. A selection of proposed techniques is reviewed along with a discussion of their effectiveness. The surveyed approaches differ in the vehicle mobility model used, in assumptions on the structure of the environment, and in computational requirements. The side-by-side comparison presented in this survey helps to gain insight into the strengths and limitations of the reviewed approaches and assists with system level design choices.

A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehicles

With the objective to improve road safety, the automotive industry is moving toward more “intelligent” vehicles. One of the major challenges is to detect dangerous situations and react accordingly in order to avoid or mitigate accidents. This requires predicting the likely evolution of the current traffic situation, and assessing how dangerous that future situation might be. This paper is a survey of existing methods for motion prediction and risk assessment for intelligent vehicles. The proposed classification is based on the semantics used to define motion and risk. We point out the tradeoff between model completeness and real-time constraints, and the fact that the choice of a risk assessment method is influenced by the selected motion model.

/pdf/a-survey-on-motion-prediction-and-risk-assessment-for-39io9df2mm.pdf

A survey on motion prediction and risk assessment for intelligent vehicles

In this paper we propose a path following Model Predictive Control-based (MPC) scheme utilizing steering and braking. The control objective is to track a desired path for obstacle avoidance maneuver, by a combined use of braking and steering. The proposed control scheme relies on the Nonlinear MPC (NMPC) formulation we used in [1] and [2]. In this work, the NMPC formulation will be used in order to derive two different approaches. The first relies on a full tenth order vehicle model and has high computational burden. The second approach is based on a simplified bicycle model and has a lower computational complexity compared to the first. The effectiveness of the proposed approaches is demonstrated through simulations and experiments.

MPC-based yaw and lateral stabilisation via active front steering and braking

A Model Predictive Control (MPC) approach for controlling an Active Front Steering (AFS) system in an autonomous vehicle is presented. At each time step a trajectory is assumed to be known over a finite horizon, and an MPC controller computes the front steering angle in order to best follow the desired trajectory on slippery roads at the highest possible entry speed. We start from the results presented in [2], [6] and formulate the MPC problem based on successive on-line linearization of the nonlinear vehicle model (LTV MPC). We present a sufficient stability conditions for such LTV MPC scheme. The condition is derived for a general class of nonlinear discrete time systems and results into an additional convex constraint to be included in the LTV MPC design. For the AFS control problem, we compare the proposed LTV MPC scheme against the LTV MPC scheme in [6] where stability has been enforced with an ad-hoc constraint. Simulation and experimental tests up to 21 m/s on icy roads show the effectiveness of the LTV MPC formulation.

Linear Time Varying Model Predictive Control and its Application to Active Steering Systems: Stability Analysis and Experimental Validation

This survey paper aims to provide some insight into the design of suspension control system within the context of existing literature and share observations on current hardware implementation of active and semi-active suspension systems. It reviews the performance envelop of active, semi-active, and passive suspensions with a focus on linear quadratic-based optimisation including a specific example. The paper further discusses various design aspects including other design techniques, the decoupling of load and road disturbances, the decoupling of pitch and heave modes, the use of an inerter as an additional design element, and the application of preview. Various production and near production suspension systems were examined and described according to the features they offer, including self-levelling, variable damping, variable geometry, and anti-roll damping and stiffness. The lessons learned from these analytical insights and related hardware implementations are valuable and can be applied towards future active or semi-active suspension design.

State of the art survey: active and semi-active suspension control

Lane changing is a critical task for autonomous driving, especially in heavy traffic. Numerous automatic lane-changing algorithms have been proposed. However, surrounding vehicles are usually treated as moving obstacles without considering the interaction between vehicles/drivers. This paper presents a game theory-based lane-changing model, which mimics human behavior by interacting with surrounding drivers using the turn signal and lateral moves. The aggressiveness of the surrounding vehicles/drivers is estimated based on their reactions. With this model, the controller is capable of extracting information and learning from the interaction in real time. As such, the optimal timing and acceleration for changing lanes with respect to a variety of aggressiveness in target lane vehicle behavior are found accordingly. The game theory-based controller was tested in Simulink and dSPACE. Scenarios were designed so that a vehicle controlled by a game theory-based controller could interact with vehicles controlled by both robot and human drivers. Test results show that the game theory-based controller is capable of changing lanes in a human-like manner and outperforms fixed rule-based controllers.

A human-like game theory-based controller for automatic lane changing

This paper presents a hierarchical control framework for the obstacle avoidance of autonomous and semi-autonomous ground vehicles. The high-level planner is based on motion primitives created from a four-wheel nonlinear dynamic model. Parameterized clothoids and drifting maneuvers are used to improve vehicle agility. The low-level tracks the planned trajectory with a nonlinear Model Predictive Controller. The first part of the paper describes the proposed control architecture and methodology. The second part presents simulative and experimental results with an autonomous and semi-autonomous ground vehicle traveling at high speed on an icy surface.

H. Eric Tseng

Papers

MPC-based yaw and lateral stabilisation via active front steering and braking

Linear Time Varying Model Predictive Control and its Application to Active Steering Systems: Stability Analysis and Experimental Validation

State of the art survey: active and semi-active suspension control

A human-like game theory-based controller for automatic lane changing

Predictive control for agile semi-autonomous ground vehicles using motion primitives