Evaluation of End-To-End Learning for Autonomous Driving: The Good, the Bad and the Ugly

in 2nd International Conference on Intelligent Autonomous Systems, Singapore, Feb. 28 to Mar. 2, 2019 (2019, March 01)

Ecological Advanced Driver Assistance System for Optimal Energy Management in Electric Vehicles

in IEEE Intelligent Transportation Systems Magazine (2018)

Battery Electric Vehicles have a high potential in modern transportation, however, they are facing limited cruising range. The driving style, the road geometries including slopes, curves, the static and ... [more ▼]

Battery Electric Vehicles have a high potential in modern transportation, however, they are facing limited cruising range. The driving style, the road geometries including slopes, curves, the static and dynamic traffic conditions such as speed limits and preceding vehicles have their share of energy consumption in the host electric vehicle. Optimal energy management based on a semi-autonomous ecological advanced driver assistance system can improve the longitudinal velocity regulation in a safe and energy-efficient driving strategy. The main contribution of this paper is the design of a real-time risk-sensitive nonlinear model predictive controller to plan the online cost-effective cruising velocity in a stochastic traffic environment. The basic idea is to measure the relevant states of the electric vehicle at runtime, and account for the road slopes, the upcoming curves, and the speed limit zones, as well as uncertainty in the preceding vehicle behavior to determine the energy-efficient velocity profile. Closed-loop Entropic Value-at-Risk as a coherent risk measure is introduced to quantify the risk involved in the system constraints violation. The obtained simulation and field experimental results demonstrate the effectiveness of the proposed method for a semi-autonomous electric vehicle in terms of safe and energy-efficient states regulation and constraints satisfaction. [less ▲]

Model Predictive Control for Aerial Collision Avoidance in Dynamic Environments

in 26th Mediterranean Conference on Control and Automation (MED), Zadar, Croatia, 19-22 June 2018 (2018, June)

Autonomous navigation in unknown environments populated by humans and other robots is one of the main challenges when working with mobile robots. In this paper, we present a new approach to dynamic ... [more ▼]

Autonomous navigation in unknown environments populated by humans and other robots is one of the main challenges when working with mobile robots. In this paper, we present a new approach to dynamic collision avoidance for multi-rotor unmanned aerial vehicles (UAVs). A new nonlinear model predictive control (NMPC) approach is proposed to safely navigate in a workspace populated by static and/or moving obstacles. The uniqueness of our approach lies in its ability to anticipate the dynamics of multiple obstacles, avoiding them in real-time. Exploiting active set algorithms, only the obstacles that affect to the UAV during the prediction horizon are considered at each sample time. We also improve the fluency of avoidance maneuvers by reformulating the obstacles as orientable ellipsoids, being less prone to local minima and allowing the definition of a preferred avoidance direction. Finally, we present two real-time implementations based on simulation. The former demonstrates that our approach outperforms its analog static formulation in terms of safety and efficiency. The latter shows its capability to avoid multiple dynamic obstacles. [less ▲]

Deadzone-Quadratic Penalty Function for Predictive Extended Cruise Control with Experimental Validation

in ROBOT 2017: Third Iberian Robotics Conference, Sevilla, Spain 22-24 November 2017 (2017, November)

Battery Electric Vehicles have high potentials for the modern transportations, however, they are facing limited cruising range. To address this limitation, we present a semi-autonomous ecological driver ... [more ▼]

Battery Electric Vehicles have high potentials for the modern transportations, however, they are facing limited cruising range. To address this limitation, we present a semi-autonomous ecological driver assistance system to regulate the velocity with energy-efficient techniques. The main contribution of this paper is the design of a real-time nonlinear receding horizon optimal controller to plan the online cost-effective cruising velocity. Instead of conventional L2-norms, a deadzone-quadratic penalty function for the nonlinear model predictive controller is proposed. Obtained field experimental results demonstrate the effectiveness of the proposed method for a semi-autonomous electric vehicle in terms of real-time energy-efficient velocity regulation and constraints satisfaction. [less ▲]

Fast Stochastic Non-linear Model Predictive Control for Electric Vehicle Advanced Driver Assistance Systems

in 13th IEEE International Conference on Vehicular Electronics and Safety, Vienna, Austria 27-28 June 2017 (2017, June 27)

Semi-autonomous driving assistance systems have a high potential to improve the safety and efficiency of the battery electric vehicles that are enduring limited cruising range. This paper presents an ... [more ▼]

Semi-autonomous driving assistance systems have a high potential to improve the safety and efficiency of the battery electric vehicles that are enduring limited cruising range. This paper presents an ecologically advanced driver assistance system to extend the functionality of the adaptive cruise control system. A real-time stochastic non-linear model predictive controller with probabilistic constraints is presented to compute on-line the safe and energy-efficient cruising velocity profile. The individual chance-constraint is reformulated into a convex second-order cone constraint which is robust for a general class of probability distributions. Finally, the performance of proposed approach in terms of states regulation, constraints fulfilment, and energy efficiency is evaluated on a battery electric vehicle. [less ▲]

An Extended Cooperative Adaptive Cruise Control (CACC) Algorithm for Efficient Energy Consumption & Traffic Density Formulation

in Traffic Flow Theory and Characteristics Committee (AHB45) 2016 Summer Meeting, Sydney, Australia, 2016 (2016, July 02)

Electric transportation, one of the most promising technologies of the century, can contribute to a greener environment as it is emission-free and sustainable. Although this technology promises a clean ... [more ▼]

Electric transportation, one of the most promising technologies of the century, can contribute to a greener environment as it is emission-free and sustainable. Although this technology promises a clean transportation style, it also has some drawbacks. One of the most significant one is cruising range, which needs to be addressed sustainably. The most eco-friendly solution is decreasing energy consumption by addressing driving behaviour. This can be achieved by taking the advantage of implementing an advancing vehicle automation technology which controls vehicles using a driver-assistance system such as Eco-Cruise Control (Eco-CC). Variety of systems already exist in the literature and a little known advanced version Eco-Adaptive Cruise Control (Eco-ACC) systems are developed as well. The next step of the vehicle automation is vehicle cooperation and information sharing, so-called Cooperative Adaptive Cruise Control (CACC). It is already developed and tested by various researcher. However, the largest deal of existing studies focus on assessing the performance in terms of safety, possible contributions to the energy consumption is not taken into account. This study covers the extension of Cooperative Adaptive Cruise Control systems while aiming to provide an energy efficient extended control algorithm to increase the energy efficiency and battery usage for electric vehicles. An energy efficient control algorithm is aimed to be derived to decrease the consumption of the vehicle. Cruising velocities and vehicle positions are received from the leading vehicles and accordingly traction force is adjusted to achieve efficient energy consumption. By providing vehicle to vehicle (V2V) communication tighter spacing gaps, lower time headway, are aimed to obtain while traffic disturbances are damped, whereas in the cases ACC applications amplify the disturbance. Traffic density formula is introduced by using V2V communication which might be useful for ADAS and ITS framework. As a result, increase in traffic stability, density, and reduction in the total energy consumption is expected. Moreover, possible reductions in air drag with tighter spacing gaps may lead reduction in energy consumption. For the energy calculations and the validation of the proposed method, vehicle dynamics and energy consumption of an electric car is formulated, which has completely different characteristics and limitations than combustion engine cars. Hence the study aims to provide additional understanding of behaviour of a fleet of CACC-equipped electric vehicles. Even though the proposed control algorithm is developed for Electric Vehicles, it can be extended to other vehicle types based on their energy consumption characteristics and vehicle dynamics. [less ▲]

Nonlinear Model Predictive Extended Eco-Cruise Control for Battery Electric Vehicles

in 24th Mediterranean Conference on Control and Automation (MED), Athens, Greece, 2016 (2016, June 22)

Battery Electric Vehicles are becoming a promising technology for road transportation. However, the main disadvantage is the limited cruising range they can travel on a single battery charge. This paper ... [more ▼]

Battery Electric Vehicles are becoming a promising technology for road transportation. However, the main disadvantage is the limited cruising range they can travel on a single battery charge. This paper presents a novel extended ecological cruise control system to increase the autonomy of an electric vehicle by using energy-efficient driving techniques. Driven velocity, acceleration profile, geometric and traffic characteristics of roads largely affect the energy consumption. An energy-efficient velocity profile should be derived based on anticipated optimal actions for future events by considering the electric vehicle dynamics, its energy consumption relations, traffic and road geometric information. A nonlinear model predictive control method with a fast numerical algorithm is adapted to determine proper velocity profile. In addition, a novel model to describe the energy consumption of a series- production electric vehicle is introduced. The hyperfunctions concept is used to model traffic and road geometry data in a new way. The proposed system is simulated on a test track scenario and obtained results reveal that the extended ecological cruise control can significantly reduce the energy consumption of an electric vehicle. [less ▲]

Model Predictive Control for Spacecraft Rendezvous

in 4th International Conference on Control, Mechatronics and Automation ICCMA '16, Barcelona, Spain, 2016 (2016)

The current paper addresses the problem of Spacecraft Rendezvous using Model Predictive Control (MPC). The Clohessy-Wiltshire-Hill equations are used to model the spacecraft relative motion. Here the ... [more ▼]

The current paper addresses the problem of Spacecraft Rendezvous using Model Predictive Control (MPC). The Clohessy-Wiltshire-Hill equations are used to model the spacecraft relative motion. Here the rendezvous problem is discussed by trajectory control using MPC method. Two different scenarios are addressed in trajectory control. The first scenario consist of position control with fuel constraint, secondly the position control is performed in the presence of obstacles. Here the problem of fuel consumption and obstacle avoidance is addressed directly in the cost function. The proposed methods are successfully analysed through simulations. [less ▲]

Learnable problem solution data structure ABS control for brake by wire vehicles

in Computer Design and Applications (ICCDA), 2010 International Conference on (2010)